diff --git a/4b284b84b20c4py/evaluation/4b284b84b20c4py_0_babi.json b/4b284b84b20c4py/evaluation/4b284b84b20c4py_0_babi.json
new file mode 100644
index 0000000000000000000000000000000000000000..468e06153cdcc2116259b14b7b9815a27f043e06
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/4b284b84b20c4py_0_babi.json
@@ -0,0 +1,22 @@
+{
+  "results": {
+    "babi": {
+      "em": 0.0,
+      "em_stderr": 0.0
+    }
+  },
+  "versions": {
+    "babi": 0
+  },
+  "config": {
+    "model": "gpt2",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers",
+    "num_fewshot": 0,
+    "batch_size": null,
+    "device": null,
+    "no_cache": true,
+    "limit": 3000,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/4b284b84b20c4py_1_babi.json b/4b284b84b20c4py/evaluation/4b284b84b20c4py_1_babi.json
new file mode 100644
index 0000000000000000000000000000000000000000..16f26782b1d57f027aea8509444d37fe3cd0f279
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/4b284b84b20c4py_1_babi.json
@@ -0,0 +1,22 @@
+{
+  "results": {
+    "babi": {
+      "em": 0.12233333333333334,
+      "em_stderr": 0.005983412909004561
+    }
+  },
+  "versions": {
+    "babi": 0
+  },
+  "config": {
+    "model": "gpt2",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers",
+    "num_fewshot": 1,
+    "batch_size": null,
+    "device": null,
+    "no_cache": true,
+    "limit": 3000,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/4b284b84b20c4py_2_babi.json b/4b284b84b20c4py/evaluation/4b284b84b20c4py_2_babi.json
new file mode 100644
index 0000000000000000000000000000000000000000..5c23d69f32eccafbac8033bab062ed1542d3e5e5
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/4b284b84b20c4py_2_babi.json
@@ -0,0 +1,22 @@
+{
+  "results": {
+    "babi": {
+      "em": 0.26266666666666666,
+      "em_stderr": 0.008036115729316689
+    }
+  },
+  "versions": {
+    "babi": 0
+  },
+  "config": {
+    "model": "gpt2",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers",
+    "num_fewshot": 2,
+    "batch_size": null,
+    "device": null,
+    "no_cache": true,
+    "limit": 3000,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/4b284b84b20c4py_3_babi.json b/4b284b84b20c4py/evaluation/4b284b84b20c4py_3_babi.json
new file mode 100644
index 0000000000000000000000000000000000000000..fc33c26d8655006d2fe09facf608a71bfbd41767
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/4b284b84b20c4py_3_babi.json
@@ -0,0 +1,22 @@
+{
+  "results": {
+    "babi": {
+      "em": 0.316,
+      "em_stderr": 0.00848952436877369
+    }
+  },
+  "versions": {
+    "babi": 0
+  },
+  "config": {
+    "model": "gpt2",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers",
+    "num_fewshot": 3,
+    "batch_size": null,
+    "device": null,
+    "no_cache": true,
+    "limit": 3000,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/4b284b84b20c4py_4_babi.json b/4b284b84b20c4py/evaluation/4b284b84b20c4py_4_babi.json
new file mode 100644
index 0000000000000000000000000000000000000000..c9be4ec256992d4083cc90e819664452aa4038d1
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/4b284b84b20c4py_4_babi.json
@@ -0,0 +1,22 @@
+{
+  "results": {
+    "babi": {
+      "em": 0.338,
+      "em_stderr": 0.008637719803347023
+    }
+  },
+  "versions": {
+    "babi": 0
+  },
+  "config": {
+    "model": "gpt2",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers",
+    "num_fewshot": 4,
+    "batch_size": null,
+    "device": null,
+    "no_cache": true,
+    "limit": 3000,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/4b284b84b20c4py_5_babi.json b/4b284b84b20c4py/evaluation/4b284b84b20c4py_5_babi.json
new file mode 100644
index 0000000000000000000000000000000000000000..4a00c75b86933c9efd051b1e232b96d5262aba58
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/4b284b84b20c4py_5_babi.json
@@ -0,0 +1,22 @@
+{
+  "results": {
+    "babi": {
+      "em": 0.3344370860927152,
+      "em_stderr": 0.01568294007623687
+    }
+  },
+  "versions": {
+    "babi": 0
+  },
+  "config": {
+    "model": "gpt2",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers",
+    "num_fewshot": 5,
+    "batch_size": null,
+    "device": null,
+    "no_cache": false,
+    "limit": 906,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_0.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_0.json
new file mode 100644
index 0000000000000000000000000000000000000000..50dc07d6dccc99f597c04a256b82ef50953e383f
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_0.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.5821529903006863, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.04918999046303147}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.07386641694533813, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.001473585372150955}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.39567846626033865, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.005414503089578944}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.11648399520322475, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.001962734009745805}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.03248305080433679, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0009633290737548379}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.1832552775488699, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.004031339201967509}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.05110539884351626, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0011859538860275287}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.0686187411531768, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0013133622767438772}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.37529249384927266, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.005205708562785746}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.10857448831592628, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017327757539863185}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.0678966567842991, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0013783793387494858}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.3611732242180814, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0048968470368908395}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.10680966736431895, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018094617190232258}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_1.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_1.json
new file mode 100644
index 0000000000000000000000000000000000000000..92345c0d18f0ac786a60ce9dcacc8acf77ea8892
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_1.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.7223543082267028, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.04821949690776964}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.1544990164378509, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.005109936829222964}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.29750968177881815, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0053921734698164}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.16315293939256764, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.00406606391553416}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.08128625147185826, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.003552808995225472}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.1541419771733494, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.003687653662432468}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.08390644664058856, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.002709652420328561}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.13931328945798263, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.004639745020801835}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.2742437769894535, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004851674974111816}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.14654695823818142, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.003492184169587925}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.1423726476383948, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0047153719491208395}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.2782302214571647, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.004924012809456184}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.14985047771566065, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0035906957715719674}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_2.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_2.json
new file mode 100644
index 0000000000000000000000000000000000000000..07bb72741e1fd4a698eb6252b6837218922109ad
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_2.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.7378703499833328, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.05244772521664121}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.1563219057138968, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.004858791940078939}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.34096200412946576, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0052420535074354235}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.18021130544779096, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.004272941447400605}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.08318072395118746, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.003239501070654235}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.17995254809157346, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0038237592317804203}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.09440270765882894, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0028820359666008894}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.13592667591898291, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.004122751284116168}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.31128419898844045, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0046882721291824836}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.15883054738596875, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0035788011689506607}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.14180027524312472, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0043181462846973075}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.31911419618669157, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.004792670653494021}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.16488490511394102, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.003755662348446356}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_3.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_3.json
new file mode 100644
index 0000000000000000000000000000000000000000..b47e9550697bced9d574484b2d5cabc58e413f1c
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_3.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.8455200709652629, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.04196246583354288}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.1657620132776089, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.005043163950083002}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.3530523030067534, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.005295085557460209}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.18931101361421848, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.00441175543523593}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.09113130928821495, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.00352182450003332}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.19048234238417183, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.003997027920968389}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.10149124697611836, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0030597860330415136}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.1447000344818964, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0043508515855694265}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.32151424349582025, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004751436169912958}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.16703960549823277, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.003744018185437013}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.15117602656048074, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.004540593426899662}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.3302972415087775, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0048599048694187045}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.1737022822557869, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.003918765580791864}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_4.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_4.json
new file mode 100644
index 0000000000000000000000000000000000000000..c1e8941fc49fd5fe6883191f0790686f733af7ea
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_4.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 1.0438894385302977, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.04793858954840552}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.17498650423231482, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.005226003580397081}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.36780447034284164, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.005431475165656425}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.19902765425868502, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.004577559193842631}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.09974409410725339, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.003653629975759034}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.20509195524896126, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.004169873380236561}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.11095071967065845, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0032440936870027355}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.15273278924825234, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.004512681594242828}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.3341937179899564, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004863935699990443}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.17536389049505893, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0038982782803899446}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.16022092144366937, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0047478422151604575}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.3441177829627617, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.005004731636362767}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.18302148806966395, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0041088067443544605}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_5.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_5.json
new file mode 100644
index 0000000000000000000000000000000000000000..845a3b856bd252d64414fbce210b5b7917c7d41c
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_5.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 1.0466750858653324, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.05396570601295072}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.18406549705329572, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.005371878868504491}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.3719286607456516, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.005364333907557689}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.20551706538102096, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.004610400264565149}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.10307937795923339, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0036674716128668973}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.20381389809228248, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.004056676150979306}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.11183554919456225, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.003125085276400022}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.1593440951510111, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.004547392408505862}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.33912003411872, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004834061594195042}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.18043825832369542, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0038675119824013696}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.16770822931202312, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.004841756735009651}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.34856549792968894, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.004968142545978921}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.1884167521241184, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n  ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0040990266910383025}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_0.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_0.json
new file mode 100644
index 0000000000000000000000000000000000000000..44003416fbfbf2d88bccaa175ffc589cabb1b2ab
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_0.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.17666729161870398, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002564314103617473}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.2592480740561813, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003244297331582796}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.19105005971268485, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0023103077379001513}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.04362509472364397, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0010895791924211578}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.06638238429547004, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0016626273617933336}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.04782253241118541, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0010918302847590757}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.13256720312713946, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001929533760984254}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.1991189509046663, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002560502239462447}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.14392086336616933, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0016839270045610358}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.16494730429754728, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0024267862201027405}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.24216666142985147, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.003059394679821919}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.17821464833251138, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.002170363421403627}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 2.8644959703383694, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.09840283116549842}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_1.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_1.json
new file mode 100644
index 0000000000000000000000000000000000000000..3fe29038c85025c4e17eaea0d68d0d48db2abee8
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_1.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.3284115430545649, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0044703231640133324}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.23063838463945993, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002967307451046764}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.21138936951170206, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0021119436014965126}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.10638602617553335, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0032259378569320244}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.06165529786910488, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0015606126487480723}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.05830265243888475, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0013343876301249531}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.2614059247131426, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.004001018574808426}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.17470934598435137, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002291915300777273}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.1612495154940211, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.00164535062263176}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.30990128884139945, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.004333017412295463}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.21562666164817174, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0027832898109490414}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.19781460859524516, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019870772811840932}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 3.2291930252196894, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.0813662472819421}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_2.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_2.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c4b05f9038cc63cc675f8d673dec6a771282daf
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_2.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.35516121344732815, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.004503744620650759}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.22637157441136155, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002939317731121365}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.22002063765271593, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002220610600873451}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.12089774581306544, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0033596165725887587}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.06380383704660388, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0015307708282999337}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.06455785570484715, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001428269385467915}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.28750238667680816, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.00406689065814819}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.17391305276884944, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.00227935817197457}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.1710811281214488, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001767537350938728}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.3377932043147537, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.004415802851933227}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.2129690629149275, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0027739680144594427}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.20737584657014088, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.002104069411424446}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 3.5225452851718835, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.11186704613999687}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_3.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_3.json
new file mode 100644
index 0000000000000000000000000000000000000000..7c5b4fed5eb9b54697e7ce54bc604680bd59ebbc
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_3.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.30492171131094353, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0047772838466778565}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.18429202449323562, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0030852957702281756}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.1842523172993621, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0025270968369157606}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.09877293469478084, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.003042979575375095}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.05222761350470907, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0015128302917191373}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.05320436365331453, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0013871858417417512}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.24798805756012632, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.004187155485268946}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.14302881144547364, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002414714553340016}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.14440728205894401, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0019982150797446126}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.2898125284191609, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.004617020091129872}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.17345207821084954, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002903285955613911}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.17378946036020648, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0023823495138698175}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 2.36637952818202, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.09034253842241578}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_4.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_4.json
new file mode 100644
index 0000000000000000000000000000000000000000..fe23318024105617bac06b105b575225f20478f6
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_4.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.10059288555045104, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0038158421954036007}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.0629899973616509, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002443758406766456}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.06118855220434953, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0021661323525031715}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.03429382030631058, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.002180070026084628}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.01817045547905002, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0010725598013084623}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.017957660778235317, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0009566364194150249}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.08431661025154882, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.003371556566767307}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.049720662704722134, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.001944703599780324}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.0489275300669287, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001745459259837189}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.09577435530540411, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.003676164831864219}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.05915809171587482, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0022962397310322636}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.05752768159536108, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.002029725801391926}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 0.06457564141470507, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.008329756004432651}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_5.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_5.json
new file mode 100644
index 0000000000000000000000000000000000000000..acd769e15bfe81630aef04e5056f7eb564f49d8a
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_5.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.016898017901863373, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0017750990265208825}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.010082034086545925, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0010784380652309026}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.009984147630959901, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0009984248511469506}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.0065299458009213975, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.001035120513731759}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.0031770613695000236, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0004797988402385803}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.0032253758284172046, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.00046285054343731663}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.014479800935916555, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0016146849938303849}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.00801090505543412, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0008700009740388975}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.008077159759742726, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0008280485118836229}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.016184294097583637, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001720217259749641}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.009470184917356883, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0010100495348991784}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.00943652067919951, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0009461154098825179}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 1.8380765632449567e-14, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 2.3549500616400215e-13}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_0.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_0.json
new file mode 100644
index 0000000000000000000000000000000000000000..1857f53c611901c07fdc0766269b63665660d074
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_0.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 0.43247677184685024, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.033875851652353954}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.10959397607392916, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0015082486108122235}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.11864984727835637, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0022176499929626235}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.10950171614553199, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.001695097915251923}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.01527462996638652, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0006638299650542848}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.019999829904043694, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0009341184850982453}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.01661379695567998, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0007317122404629029}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.09436066788883278, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0010570471723853009}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.09932327469630105, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0015360141973192033}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.09304292066966034, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0011571807694826105}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.10077063698381258, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.00127965803739232}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.10731074612593083, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0018385590198386557}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.0998911245421451, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0014072933040335162}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_1.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_1.json
new file mode 100644
index 0000000000000000000000000000000000000000..f006832c66b2a8b0521545b178ce2857b195f9a2
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_1.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 14.138799978501053, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.15480830784903687}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.5968366957436839, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.003015142456201993}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.48954973616011194, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003154110033453677}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.5125167205611227, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0023651662897042755}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.28811459984378174, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0026040248998219972}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.23475714793970334, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.002314968393870581}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.24536868897035313, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0021152678254568883}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.42787430905551216, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0028633121423425455}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.3470673946354127, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0025728563437977126}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.36458967944121407, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0021531883816726166}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.48668255912820346, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.00301880494587729}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.3985290767399889, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0029315744162868814}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.417350163512538, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0024012705814720663}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_2.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_2.json
new file mode 100644
index 0000000000000000000000000000000000000000..5a4c4723075dc2a2724bd885fca8623d032d5948
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_2.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 16.67584789617738, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.24934972090088892}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.6044891850192401, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002962047333298037}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.5296091433441801, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0029699728553327985}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.5434492838820844, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0022798657306134494}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.3060578998541716, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0026210349607320195}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.2663332824849255, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0023940282146509124}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.2731108373811898, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0021911774712661926}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.4339464538873811, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0027896307194930727}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.37822202655327963, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0025535736155600725}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.3886806544508872, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0021844936986815003}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.500797595703899, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0030140205124491366}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.43833203269544485, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0028575376559899297}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.44995734822290556, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.002414589606781355}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_3.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_3.json
new file mode 100644
index 0000000000000000000000000000000000000000..23d8d8c05258b78908cd1ed81ac231845f3a5605
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_3.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 17.9289834939611, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.2213809634052702}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.6095035638446965, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002930771405927963}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.5400385856426181, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002958534482681524}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.5531025638271319, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002287431155068112}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.31735677434972087, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.002652924486773051}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.2801209686683005, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0024697622358377117}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.28644947317730374, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0022634076265008176}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.44321547746696427, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0028028512374731335}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.39096477845132616, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0026123031329029745}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.4009270336830942, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0022477469014727212}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.5103701959134134, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002984407196868822}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.4522481230027106, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0028960497978095996}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.46312437456752364, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.002440885766456274}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_4.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_4.json
new file mode 100644
index 0000000000000000000000000000000000000000..67ba5c7283c32f306c5c354d83ecfda08eda4fa5
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_4.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 18.149147747916913, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.20148633900165086}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.6065356554980276, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0029114663522908494}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.5407131752166793, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0028869233555941847}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.5535709465739721, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0022696074476917737}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.3175050521033487, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0026446629424917993}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.28222258859716826, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0024700817238289944}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.2885935293923734, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.00227878913447549}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.43968215201631833, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0027559200740548723}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.3912634075317438, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0026077143358096103}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.40073709641210925, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.002259079219646151}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.509403064079757, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0029861554036300585}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.45442412908463375, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0028784777463463844}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.46512455647571105, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.00246162611684128}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_5.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_5.json
new file mode 100644
index 0000000000000000000000000000000000000000..033839932e594ba11c85bb2372a88d0619b1558f
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_5.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 18.293098564935043, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.2015089174052472}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.6077504578417503, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0029261887327982562}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.5415558465280581, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002846550944908392}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.5549735351709728, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002267759028289067}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.3196575755449254, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0027013822082627096}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.28374451994336647, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.002479580564388698}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.29047091894764593, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0023151393500169828}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.4429726081641192, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.002791198713554071}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.39397526144610207, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0025934124726939927}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.4038165297365153, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0022641228045925934}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.5137249582242605, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0030010894093243884}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.4579977387073725, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0028534759678292203}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.4692296832791923, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.002459426145702881}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_gem_xsum_article_DOC_summary_0.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_gem_xsum_article_DOC_summary_0.json
new file mode 100644
index 0000000000000000000000000000000000000000..16ecb647d9d0ee67a51af9870071db46b9238d17
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_gem_xsum_article_DOC_summary_0.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.15957877260264566, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002268991781760454}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.32811311012769145, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.00437654661974792}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.20585322846240078, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0025590515279682287}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.0321492286692698, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0011871798504177848}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.07023735951022572, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0024919186942029548}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.04236381811374163, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0014754029359749594}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.11772435407501897, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0017511876283900834}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.24205558291065699, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0032633158272913202}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.15149462132825195, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001896257149928836}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.1252147373709473, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0018424550712854318}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.2599266014362882, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0036876361603540428}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.16193719293154057, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0021003252791642214}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 1.7077858100284875, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.06318104051496665}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_gem_xsum_article_DOC_summary_1.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_gem_xsum_article_DOC_summary_1.json
new file mode 100644
index 0000000000000000000000000000000000000000..6c901b4c53daab98b72b9362a0adeca3c2d142c2
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_gem_xsum_article_DOC_summary_1.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.18241736362419408, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0035671793011444824}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.28088578439333156, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004150802521339531}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.20198994819537205, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002984694518793648}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.03766732268521147, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0018002611735446364}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.05744303705984819, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.002394118114694247}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.041266355576914736, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0017486414825347912}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.13852250267452665, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0027600347382047627}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.21557457573877506, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0032748640854860915}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.1537399711922189, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0023040866331068065}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.14149023067517916, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002779812720023245}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.2224713251909163, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0035223603046659778}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.157801209736622, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0023904477003575016}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 1.8282472672146812, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.1020121938444088}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_gem_xsum_article_DOC_summary_2.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_gem_xsum_article_DOC_summary_2.json
new file mode 100644
index 0000000000000000000000000000000000000000..bc4f56b1f281533556a6e52d92e7e46c5443ce6d
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_gem_xsum_article_DOC_summary_2.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.21893354662011963, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.004048272249341602}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.260092993109534, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003902306781441875}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.2195684919577384, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.003254265138077691}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.04791765027513919, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0022980519753049485}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.053493298501079714, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0023052325119618023}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.046526613891962755, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.00204903807224034}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.16473734247474792, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0031841165642595994}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.19604258368067826, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0030444450297627}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.16501217387582887, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0025424570393059753}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.1671435431989699, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0031935413338326185}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.20091357776545432, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.003229501111978948}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.16810787872676755, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0025882089916786253}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 2.0883920440199915, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.11737825754959746}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_gem_xsum_article_DOC_summary_3.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_gem_xsum_article_DOC_summary_3.json
new file mode 100644
index 0000000000000000000000000000000000000000..7faf68811e36d1dab7c1db8597afe0815ec5d1da
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_gem_xsum_article_DOC_summary_3.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.22154258705050656, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.004416958718487466}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.2427641584174357, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.00420050957184403}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.21513910465275415, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0036788747099070216}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.050821433347839264, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0023945363772249644}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.05453094107822012, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.002408142744637484}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.04886471919044582, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.002157338930931576}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.16668887518076203, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.003514628068406048}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.18226837233438312, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.003295475230668282}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.16128891406853352, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.002880789024699209}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.16896742575336499, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.00351461682461915}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.1869678121534825, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.003429064046115561}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.1642209135986658, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0029068460098697737}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 2.4903444029414104, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.16888554758075064}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_gem_xsum_article_DOC_summary_4.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_gem_xsum_article_DOC_summary_4.json
new file mode 100644
index 0000000000000000000000000000000000000000..99b758272ecf42147ea4cc2d45203bcdf531951f
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_gem_xsum_article_DOC_summary_4.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.06587717027902634, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0039704424509340985}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.06115142824616809, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003616406533465941}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.0572325652119175, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0032468616776549866}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.014030183412219063, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.001506975166878615}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.013471932961216628, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0013203271107582826}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.01224992383643623, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0011777335201229031}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.050416403187604805, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0032341383122656336}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.0450041617246973, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002689245329612641}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.04246528505415009, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0024489654144463574}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.05133449482703434, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0032661771463960336}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.046814652800863985, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002844770088636042}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.04361018726263517, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0025148690575369646}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 0.215456941864469, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.06941440736262179}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_gem_xsum_article_DOC_summary_5.json b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_gem_xsum_article_DOC_summary_5.json
new file mode 100644
index 0000000000000000000000000000000000000000..ed183b9e80e413fc965a18731a11e395ed3142db
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/agg.4b284b84b20c4py_gem_xsum_article_DOC_summary_5.json
@@ -0,0 +1 @@
+{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.0023814022915898026, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0007101439263166566}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.0020217833554038362, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0005950726577170537}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.00214003217049867, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0006281208747948269}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 9.874063374559899e-05, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 7.004654141515487e-05}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 6.729119936667107e-05, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 4.7570795295869234e-05}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 7.982297862229252e-05, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 5.643442046339631e-05}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.0017095297689958592, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0005079974336227376}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.0014314059035737939, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0004049546110440357}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.0015217948267156234, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0004371612073436473}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.0018171542939344795, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0005294219136072831}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.0015326542359542015, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0004286235600707048}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.001626133579867523, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.00046047748478715914}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 4.047824391489386e-39, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 1.7044826243904522e-34}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_0.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_0.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..0f75e53e09da651fb8cbef6d7b57cfbbbdb4b3f4
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_0.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dec0eabbcf2d263ff206a83741152358fe175774289055e3681efec1969894b
+size 4263139
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_1.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_1.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..aa927ebee09a32772222b1160bf7c9a01fcde4af
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_1.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:791eca1c5cea18104d2bd08fc54c03cfbb9726b162cdb0b91dbbb19ac189ed64
+size 4566387
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_2.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_2.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..a40f96addc3eb9bc7333ee9e2feee13baf480769
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_2.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:682737d5deef5b6d5ed679def3ce0b497e542c5dd0b687f0529b8d0b1d8ccb96
+size 5576443
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_3.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_3.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..61541db1c270ec047524263096810267205a9bac
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_3.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a83a50f16179dcee9e46f24ffb3d656d973a95b2e5fa0b93a5f1a665f1e9c5e0
+size 6475705
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_4.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_4.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..82ba5a4eebdef5a634410060cfbe740ff94037e3
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_4.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de6eb9d1e2a85e75d840028944e34800d62e3aebc91fdc88385ac0144e7d036d
+size 7364243
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_5.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_5.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..8f2cdeb44211b665cad65fca292eaad950457149
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_5.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83fd64128c9c0dbef974e4b8c4632d486530cb242635c68da4ffde14c6754226
+size 8241342
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_0.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_0.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..76f00d9e5f55e35dfda3b93c46a41ab04fede4d3
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_0.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:895f03f559ab631170f0598415c7500c653c29d2d5e891765e01b97a1f9a3aa4
+size 7555412
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_1.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_1.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..c48122ee157789224959653bceb4c67b89575981
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_1.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6a64a6b5c7dba574d8642c340856eef7b9ded6f3e44c89589ae44dd291a138
+size 12965818
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_2.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_2.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..23652d3ae4f3c6ea28d8cec507735bfb538d9e68
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_2.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f84bdec74a549308cd8e3409af8dfe49c0b33fe73e395b034c835fa990459586
+size 18521438
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_3.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_3.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..faaae6f85dbf113a86e9a4af2379c92be190fb1b
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_3.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99ffdb61ccd86600a5435e8fde98c0e29be0e794c27bc45b14d3366a6e4cb7a2
+size 23996660
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_4.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_4.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..3342ec22c8e8002aa9ddaa516a541c872cb12c6a
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_4.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cce1b77918dc7152731367967fb557fb0de84f53646243860c4aaa0194b230b
+size 29368122
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_5.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_5.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..607cc6b50672029a2dc3eb26dcb55ccbcd9c7caf
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_5.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00235a8a4441f883cd9d14307a920377c4be666f29514fc85effefbcfc5f0e87
+size 34783824
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..2d0b23beace88d193a92b43f0703a23fd79a4e01
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a07fa307cb763673ed47e4c3e109025d00e7a4e71422e93836ac312e026f3473
+size 4238903
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..6546ed615de635202ce02f48262d49385b643c3a
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8ba8d6de1e62b57b09d40adc320ca25e3cb4761b75de57656783621ff9830cc
+size 5026168
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..637832d30ac5f7a9253f690d4a6ea1f1ec8cca75
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d47d41fb8d5206936caa682e8592344fbc00136c5a26429fadb3f626702bae84
+size 6130630
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..e02f4fff8492a16c84fefeefc304293ea999a0d4
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d82631f92f41fc518184edf9fb57d326d9ff9c3106004fafc480249155b4387
+size 7212892
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..610586e97a37a8951c8de6a28f4dee4280a5e8b9
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc7e1ab6da11f4a4f082c5145d0b4486a7d86474f12c237fd4f78cdf9ae2c1ee
+size 8291388
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..761cc15de258e46d6ac16b5eb3ae37d678cc4e89
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d30f28cce5a55bcd88f3a4ef84e40a4b424b3f775be14a60c53a365911ed575
+size 9378481
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_gem_xsum_article_DOC_summary_0.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_gem_xsum_article_DOC_summary_0.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..b0b0efea11fea4197dd729d46582e65a7cf26e2a
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_gem_xsum_article_DOC_summary_0.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5a51fb63a59113ac95542cd7b736c23a27b1e2ac636102675f203eaec115c3a
+size 2800280
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_gem_xsum_article_DOC_summary_1.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_gem_xsum_article_DOC_summary_1.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..bd7cc43de04de4bfe6f3db80a8f74564a8a57c5c
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_gem_xsum_article_DOC_summary_1.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c31a4cd2daaaaac1976f3e9589609970d6ebd3ce6d9e8f121f71cf668614547
+size 5013901
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_gem_xsum_article_DOC_summary_2.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_gem_xsum_article_DOC_summary_2.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..0c8d70667e5dd0a822f36a9820862211b8d96501
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_gem_xsum_article_DOC_summary_2.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d22ac6b1a37814f7c991bfcc600b9227b8ecaf9a31b602718179033b768d883d
+size 7231853
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_gem_xsum_article_DOC_summary_3.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_gem_xsum_article_DOC_summary_3.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..3f96114a93423021e3dbe265fc3311e0120fd509
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_gem_xsum_article_DOC_summary_3.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b404d1e0dc8e43019cd6410e185d951e88f9a8f5e0184fac805ec2188ba4ce97
+size 9494300
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_gem_xsum_article_DOC_summary_4.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_gem_xsum_article_DOC_summary_4.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..a0ff9ee74adc0e1e069cc4f01724dc142fce5535
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_gem_xsum_article_DOC_summary_4.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9693f1ae1d5ae8326bfe66c34fedb93a5789471b4c7938612587607a5193c9
+size 11635552
diff --git a/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_gem_xsum_article_DOC_summary_5.jsonl b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_gem_xsum_article_DOC_summary_5.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..11a84362a41d9f03a53240b1126c2e998fc6e1c2
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/examples.4b284b84b20c4py_gem_xsum_article_DOC_summary_5.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:350fad9de76f0d8298214e79ba96039a8b89f4e462c91fc6cd9850bb67d1e3ad
+size 13897461
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_0.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_0.json
new file mode 100644
index 0000000000000000000000000000000000000000..5ff67d83fe16d0f0bde5e9206f76e15322071882
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_0.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "bleu": 0.5821529903006863,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.04918999046303147
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_precision": 0.07386641694533813,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.001473585372150955
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_recall": 0.39567846626033865,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.005414503089578944
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_fmeasure": 0.11648399520322475,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.001962734009745805
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_precision": 0.03248305080433679,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.0009633290737548379
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_recall": 0.1832552775488699,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.004031339201967509
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_fmeasure": 0.05110539884351626,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0011859538860275287
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_precision": 0.0686187411531768,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.0013133622767438772
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_recall": 0.37529249384927266,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.005205708562785746
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_fmeasure": 0.10857448831592628,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0017327757539863185
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_precision": 0.0678966567842991,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.0013783793387494858
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_recall": 0.3611732242180814,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0048968470368908395
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_fmeasure": 0.10680966736431895,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0018094617190232258
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 0,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_1.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_1.json
new file mode 100644
index 0000000000000000000000000000000000000000..5d6ad572d6f9cc8ddbf826322413e28904db4a86
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_1.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "bleu": 0.7223543082267028,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.04821949690776964
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_precision": 0.1544990164378509,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.005109936829222964
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_recall": 0.29750968177881815,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.0053921734698164
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_fmeasure": 0.16315293939256764,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.00406606391553416
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_precision": 0.08128625147185826,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.003552808995225472
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_recall": 0.1541419771733494,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.003687653662432468
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_fmeasure": 0.08390644664058856,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.002709652420328561
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_precision": 0.13931328945798263,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.004639745020801835
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_recall": 0.2742437769894535,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.004851674974111816
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_fmeasure": 0.14654695823818142,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.003492184169587925
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_precision": 0.1423726476383948,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.0047153719491208395
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_recall": 0.2782302214571647,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.004924012809456184
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_fmeasure": 0.14985047771566065,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0035906957715719674
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 1,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_2.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_2.json
new file mode 100644
index 0000000000000000000000000000000000000000..eae91e97273bfd686460b5b928ad20dd547a9331
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_2.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "bleu": 0.7378703499833328,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.05244772521664121
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_precision": 0.1563219057138968,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.004858791940078939
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_recall": 0.34096200412946576,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.0052420535074354235
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_fmeasure": 0.18021130544779096,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.004272941447400605
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_precision": 0.08318072395118746,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.003239501070654235
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_recall": 0.17995254809157346,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.0038237592317804203
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_fmeasure": 0.09440270765882894,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0028820359666008894
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_precision": 0.13592667591898291,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.004122751284116168
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_recall": 0.31128419898844045,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.0046882721291824836
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_fmeasure": 0.15883054738596875,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0035788011689506607
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_precision": 0.14180027524312472,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.0043181462846973075
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_recall": 0.31911419618669157,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.004792670653494021
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_fmeasure": 0.16488490511394102,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.003755662348446356
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 2,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_3.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_3.json
new file mode 100644
index 0000000000000000000000000000000000000000..23a7fafced373eaa84d172330d2a4c7fc0549a86
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_3.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "bleu": 0.8455200709652629,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.04196246583354288
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_precision": 0.1657620132776089,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.005043163950083002
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_recall": 0.3530523030067534,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.005295085557460209
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_fmeasure": 0.18931101361421848,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.00441175543523593
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_precision": 0.09113130928821495,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.00352182450003332
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_recall": 0.19048234238417183,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.003997027920968389
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_fmeasure": 0.10149124697611836,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0030597860330415136
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_precision": 0.1447000344818964,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.0043508515855694265
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_recall": 0.32151424349582025,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.004751436169912958
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_fmeasure": 0.16703960549823277,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.003744018185437013
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_precision": 0.15117602656048074,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.004540593426899662
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_recall": 0.3302972415087775,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0048599048694187045
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_fmeasure": 0.1737022822557869,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.003918765580791864
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 3,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_4.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_4.json
new file mode 100644
index 0000000000000000000000000000000000000000..4f4c6cc123365db091ecbbf4e34a22d5c5e9796f
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_4.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "bleu": 1.0438894385302977,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.04793858954840552
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_precision": 0.17498650423231482,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.005226003580397081
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_recall": 0.36780447034284164,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.005431475165656425
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_fmeasure": 0.19902765425868502,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.004577559193842631
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_precision": 0.09974409410725339,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.003653629975759034
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_recall": 0.20509195524896126,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.004169873380236561
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_fmeasure": 0.11095071967065845,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0032440936870027355
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_precision": 0.15273278924825234,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.004512681594242828
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_recall": 0.3341937179899564,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.004863935699990443
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_fmeasure": 0.17536389049505893,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0038982782803899446
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_precision": 0.16022092144366937,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.0047478422151604575
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_recall": 0.3441177829627617,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.005004731636362767
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_fmeasure": 0.18302148806966395,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0041088067443544605
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 4,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_5.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_5.json
new file mode 100644
index 0000000000000000000000000000000000000000..14f344185f1c7a5d43ad06185b17cc151229a8f6
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-web_nlg_en_PALM_prompt_5.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "bleu": 1.0466750858653324,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.05396570601295072
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_precision": 0.18406549705329572,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.005371878868504491
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_recall": 0.3719286607456516,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.005364333907557689
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge1_fmeasure": 0.20551706538102096,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.004610400264565149
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_precision": 0.10307937795923339,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.0036674716128668973
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_recall": 0.20381389809228248,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.004056676150979306
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rouge2_fmeasure": 0.11183554919456225,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.003125085276400022
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_precision": 0.1593440951510111,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.004547392408505862
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_recall": 0.33912003411872,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.004834061594195042
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeL_fmeasure": 0.18043825832369542,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0038675119824013696
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_precision": 0.16770822931202312,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.004841756735009651
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_recall": 0.34856549792968894,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.004968142545978921
+    },
+    {
+      "task_name": "GEM/web_nlg_en",
+      "prompt_name": "PALM_prompt",
+      "rougeLsum_fmeasure": 0.1884167521241184,
+      "dataset_path": "GEM/web_nlg",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0040990266910383025
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 5,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_0.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_0.json
new file mode 100644
index 0000000000000000000000000000000000000000..fd4e9ae268833c962e8e8855f9c2abcec286087c
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_0.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_precision": 0.17666729161870398,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.002564314103617473
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_recall": 0.2592480740561813,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.003244297331582796
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_fmeasure": 0.19105005971268485,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0023103077379001513
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_precision": 0.04362509472364397,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.0010895791924211578
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_recall": 0.06638238429547004,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.0016626273617933336
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_fmeasure": 0.04782253241118541,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0010918302847590757
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_precision": 0.13256720312713946,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.001929533760984254
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_recall": 0.1991189509046663,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.002560502239462447
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_fmeasure": 0.14392086336616933,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0016839270045610358
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_precision": 0.16494730429754728,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.0024267862201027405
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_recall": 0.24216666142985147,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.003059394679821919
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_fmeasure": 0.17821464833251138,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.002170363421403627
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "bleu": 2.8644959703383694,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.09840283116549842
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 0,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_1.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_1.json
new file mode 100644
index 0000000000000000000000000000000000000000..ee13be923cd259bdf2838a34d37bcfa65032d671
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_1.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_precision": 0.3284115430545649,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.0044703231640133324
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_recall": 0.23063838463945993,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.002967307451046764
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_fmeasure": 0.21138936951170206,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0021119436014965126
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_precision": 0.10638602617553335,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.0032259378569320244
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_recall": 0.06165529786910488,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.0015606126487480723
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_fmeasure": 0.05830265243888475,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0013343876301249531
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_precision": 0.2614059247131426,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.004001018574808426
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_recall": 0.17470934598435137,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.002291915300777273
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_fmeasure": 0.1612495154940211,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.00164535062263176
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_precision": 0.30990128884139945,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.004333017412295463
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_recall": 0.21562666164817174,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0027832898109490414
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_fmeasure": 0.19781460859524516,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0019870772811840932
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "bleu": 3.2291930252196894,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.0813662472819421
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 1,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_2.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_2.json
new file mode 100644
index 0000000000000000000000000000000000000000..8119788ddbe7d59cde8f3d2f788a59b443d213a5
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_2.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_precision": 0.35516121344732815,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.004503744620650759
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_recall": 0.22637157441136155,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.002939317731121365
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_fmeasure": 0.22002063765271593,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.002220610600873451
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_precision": 0.12089774581306544,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.0033596165725887587
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_recall": 0.06380383704660388,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.0015307708282999337
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_fmeasure": 0.06455785570484715,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.001428269385467915
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_precision": 0.28750238667680816,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.00406689065814819
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_recall": 0.17391305276884944,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.00227935817197457
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_fmeasure": 0.1710811281214488,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.001767537350938728
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_precision": 0.3377932043147537,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.004415802851933227
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_recall": 0.2129690629149275,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0027739680144594427
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_fmeasure": 0.20737584657014088,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.002104069411424446
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "bleu": 3.5225452851718835,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.11186704613999687
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 2,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_3.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_3.json
new file mode 100644
index 0000000000000000000000000000000000000000..a627bdd41f6e799741ce72575eb03e7f2d3f09e0
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_3.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_precision": 0.30492171131094353,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.0047772838466778565
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_recall": 0.18429202449323562,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.0030852957702281756
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_fmeasure": 0.1842523172993621,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0025270968369157606
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_precision": 0.09877293469478084,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.003042979575375095
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_recall": 0.05222761350470907,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.0015128302917191373
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_fmeasure": 0.05320436365331453,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0013871858417417512
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_precision": 0.24798805756012632,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.004187155485268946
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_recall": 0.14302881144547364,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.002414714553340016
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_fmeasure": 0.14440728205894401,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0019982150797446126
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_precision": 0.2898125284191609,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.004617020091129872
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_recall": 0.17345207821084954,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.002903285955613911
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_fmeasure": 0.17378946036020648,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0023823495138698175
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "bleu": 2.36637952818202,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.09034253842241578
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 3,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_4.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_4.json
new file mode 100644
index 0000000000000000000000000000000000000000..5beee11ae846d50a6e3217bbc351a1567a42d1e2
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_4.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_precision": 0.10059288555045104,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.0038158421954036007
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_recall": 0.0629899973616509,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.002443758406766456
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_fmeasure": 0.06118855220434953,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0021661323525031715
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_precision": 0.03429382030631058,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.002180070026084628
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_recall": 0.01817045547905002,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.0010725598013084623
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_fmeasure": 0.017957660778235317,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0009566364194150249
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_precision": 0.08431661025154882,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.003371556566767307
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_recall": 0.049720662704722134,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.001944703599780324
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_fmeasure": 0.0489275300669287,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.001745459259837189
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_precision": 0.09577435530540411,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.003676164831864219
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_recall": 0.05915809171587482,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0022962397310322636
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_fmeasure": 0.05752768159536108,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.002029725801391926
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "bleu": 0.06457564141470507,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 0.008329756004432651
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 4,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_5.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_5.json
new file mode 100644
index 0000000000000000000000000000000000000000..599b4fc5ff00c436a96d2aaca06022b94f476cc8
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_GEM-wiki_lingua_en_tldr_en_5.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_precision": 0.016898017901863373,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_precision_stderr": 0.0017750990265208825
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_recall": 0.010082034086545925,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_recall_stderr": 0.0010784380652309026
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge1_fmeasure": 0.009984147630959901,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0009984248511469506
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_precision": 0.0065299458009213975,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_precision_stderr": 0.001035120513731759
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_recall": 0.0031770613695000236,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_recall_stderr": 0.0004797988402385803
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rouge2_fmeasure": 0.0032253758284172046,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.00046285054343731663
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_precision": 0.014479800935916555,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_precision_stderr": 0.0016146849938303849
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_recall": 0.00801090505543412,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_recall_stderr": 0.0008700009740388975
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeL_fmeasure": 0.008077159759742726,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0008280485118836229
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_precision": 0.016184294097583637,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.001720217259749641
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_recall": 0.009470184917356883,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0010100495348991784
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "rougeLsum_fmeasure": 0.00943652067919951,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0009461154098825179
+    },
+    {
+      "task_name": "GEM/wiki_lingua_en",
+      "prompt_name": "tldr_en",
+      "bleu": 1.8380765632449567e-14,
+      "dataset_path": "GEM/wiki_lingua",
+      "dataset_name": "en",
+      "subset": null,
+      "bleu_stderr": 2.3549500616400215e-13
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 5,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_0.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_0.json
new file mode 100644
index 0000000000000000000000000000000000000000..6fa661583ace1cf1a27e6602be537a9883ce647c
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_0.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "bleu": 0.43247677184685024,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "bleu_stderr": 0.033875851652353954
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_precision": 0.10959397607392916,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_precision_stderr": 0.0015082486108122235
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_recall": 0.11864984727835637,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_recall_stderr": 0.0022176499929626235
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_fmeasure": 0.10950171614553199,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.001695097915251923
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_precision": 0.01527462996638652,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_precision_stderr": 0.0006638299650542848
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_recall": 0.019999829904043694,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_recall_stderr": 0.0009341184850982453
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_fmeasure": 0.01661379695567998,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0007317122404629029
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_precision": 0.09436066788883278,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_precision_stderr": 0.0010570471723853009
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_recall": 0.09932327469630105,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_recall_stderr": 0.0015360141973192033
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_fmeasure": 0.09304292066966034,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0011571807694826105
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_precision": 0.10077063698381258,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.00127965803739232
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_recall": 0.10731074612593083,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0018385590198386557
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_fmeasure": 0.0998911245421451,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0014072933040335162
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 0,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_1.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_1.json
new file mode 100644
index 0000000000000000000000000000000000000000..2d32a532165746dafc19bfcbda4de2ecdcd90498
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_1.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "bleu": 14.138799978501053,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "bleu_stderr": 0.15480830784903687
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_precision": 0.5968366957436839,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_precision_stderr": 0.003015142456201993
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_recall": 0.48954973616011194,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_recall_stderr": 0.003154110033453677
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_fmeasure": 0.5125167205611227,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0023651662897042755
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_precision": 0.28811459984378174,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_precision_stderr": 0.0026040248998219972
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_recall": 0.23475714793970334,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_recall_stderr": 0.002314968393870581
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_fmeasure": 0.24536868897035313,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0021152678254568883
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_precision": 0.42787430905551216,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_precision_stderr": 0.0028633121423425455
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_recall": 0.3470673946354127,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_recall_stderr": 0.0025728563437977126
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_fmeasure": 0.36458967944121407,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0021531883816726166
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_precision": 0.48668255912820346,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.00301880494587729
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_recall": 0.3985290767399889,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0029315744162868814
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_fmeasure": 0.417350163512538,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.0024012705814720663
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 1,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_2.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_2.json
new file mode 100644
index 0000000000000000000000000000000000000000..4135689ab88a54330b0d1f16a2dab64445900f73
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_2.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "bleu": 16.67584789617738,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "bleu_stderr": 0.24934972090088892
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_precision": 0.6044891850192401,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_precision_stderr": 0.002962047333298037
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_recall": 0.5296091433441801,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_recall_stderr": 0.0029699728553327985
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_fmeasure": 0.5434492838820844,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0022798657306134494
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_precision": 0.3060578998541716,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_precision_stderr": 0.0026210349607320195
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_recall": 0.2663332824849255,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_recall_stderr": 0.0023940282146509124
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_fmeasure": 0.2731108373811898,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0021911774712661926
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_precision": 0.4339464538873811,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_precision_stderr": 0.0027896307194930727
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_recall": 0.37822202655327963,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_recall_stderr": 0.0025535736155600725
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_fmeasure": 0.3886806544508872,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0021844936986815003
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_precision": 0.500797595703899,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.0030140205124491366
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_recall": 0.43833203269544485,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0028575376559899297
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_fmeasure": 0.44995734822290556,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.002414589606781355
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 2,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_3.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_3.json
new file mode 100644
index 0000000000000000000000000000000000000000..57a29ea82aa117ce5061153a718b125d4ea4bf48
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_3.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "bleu": 17.9289834939611,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "bleu_stderr": 0.2213809634052702
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_precision": 0.6095035638446965,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_precision_stderr": 0.002930771405927963
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_recall": 0.5400385856426181,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_recall_stderr": 0.002958534482681524
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_fmeasure": 0.5531025638271319,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.002287431155068112
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_precision": 0.31735677434972087,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_precision_stderr": 0.002652924486773051
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_recall": 0.2801209686683005,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_recall_stderr": 0.0024697622358377117
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_fmeasure": 0.28644947317730374,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0022634076265008176
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_precision": 0.44321547746696427,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_precision_stderr": 0.0028028512374731335
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_recall": 0.39096477845132616,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_recall_stderr": 0.0026123031329029745
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_fmeasure": 0.4009270336830942,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0022477469014727212
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_precision": 0.5103701959134134,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.002984407196868822
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_recall": 0.4522481230027106,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0028960497978095996
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_fmeasure": 0.46312437456752364,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.002440885766456274
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 3,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_4.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_4.json
new file mode 100644
index 0000000000000000000000000000000000000000..ba50212a083a8f17477176b37e0187289b6f7999
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_4.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "bleu": 18.149147747916913,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "bleu_stderr": 0.20148633900165086
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_precision": 0.6065356554980276,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_precision_stderr": 0.0029114663522908494
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_recall": 0.5407131752166793,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_recall_stderr": 0.0028869233555941847
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_fmeasure": 0.5535709465739721,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.0022696074476917737
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_precision": 0.3175050521033487,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_precision_stderr": 0.0026446629424917993
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_recall": 0.28222258859716826,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_recall_stderr": 0.0024700817238289944
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_fmeasure": 0.2885935293923734,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.00227878913447549
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_precision": 0.43968215201631833,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_precision_stderr": 0.0027559200740548723
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_recall": 0.3912634075317438,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_recall_stderr": 0.0026077143358096103
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_fmeasure": 0.40073709641210925,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.002259079219646151
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_precision": 0.509403064079757,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.0029861554036300585
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_recall": 0.45442412908463375,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0028784777463463844
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_fmeasure": 0.46512455647571105,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.00246162611684128
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 4,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_5.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_5.json
new file mode 100644
index 0000000000000000000000000000000000000000..59a5bcd0320dc2cff6efcde4b4366ddb46c87efd
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_e2e_nlg_cleaned_generate_text_restaurant_5.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "bleu": 18.293098564935043,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "bleu_stderr": 0.2015089174052472
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_precision": 0.6077504578417503,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_precision_stderr": 0.0029261887327982562
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_recall": 0.5415558465280581,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_recall_stderr": 0.002846550944908392
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge1_fmeasure": 0.5549735351709728,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge1_fmeasure_stderr": 0.002267759028289067
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_precision": 0.3196575755449254,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_precision_stderr": 0.0027013822082627096
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_recall": 0.28374451994336647,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_recall_stderr": 0.002479580564388698
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rouge2_fmeasure": 0.29047091894764593,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rouge2_fmeasure_stderr": 0.0023151393500169828
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_precision": 0.4429726081641192,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_precision_stderr": 0.002791198713554071
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_recall": 0.39397526144610207,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_recall_stderr": 0.0025934124726939927
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeL_fmeasure": 0.4038165297365153,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeL_fmeasure_stderr": 0.0022641228045925934
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_precision": 0.5137249582242605,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_precision_stderr": 0.0030010894093243884
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_recall": 0.4579977387073725,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_recall_stderr": 0.0028534759678292203
+    },
+    {
+      "task_name": "e2e_nlg_cleaned",
+      "prompt_name": "generate_text_restaurant",
+      "rougeLsum_fmeasure": 0.4692296832791923,
+      "dataset_path": "e2e_nlg_cleaned",
+      "dataset_name": null,
+      "subset": null,
+      "rougeLsum_fmeasure_stderr": 0.002459426145702881
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 5,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_gem_xsum_article_DOC_summary_0.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_gem_xsum_article_DOC_summary_0.json
new file mode 100644
index 0000000000000000000000000000000000000000..19dc1ddd457ea3074c0656074a8e92492c735f8d
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_gem_xsum_article_DOC_summary_0.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_precision": 0.15957877260264566,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_precision_stderr": 0.002268991781760454
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_recall": 0.32811311012769145,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_recall_stderr": 0.00437654661974792
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_fmeasure": 0.20585322846240078,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_fmeasure_stderr": 0.0025590515279682287
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_precision": 0.0321492286692698,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_precision_stderr": 0.0011871798504177848
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_recall": 0.07023735951022572,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_recall_stderr": 0.0024919186942029548
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_fmeasure": 0.04236381811374163,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_fmeasure_stderr": 0.0014754029359749594
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_precision": 0.11772435407501897,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_precision_stderr": 0.0017511876283900834
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_recall": 0.24205558291065699,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_recall_stderr": 0.0032633158272913202
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_fmeasure": 0.15149462132825195,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_fmeasure_stderr": 0.001896257149928836
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_precision": 0.1252147373709473,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_precision_stderr": 0.0018424550712854318
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_recall": 0.2599266014362882,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_recall_stderr": 0.0036876361603540428
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_fmeasure": 0.16193719293154057,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_fmeasure_stderr": 0.0021003252791642214
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "bleu": 1.7077858100284875,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "bleu_stderr": 0.06318104051496665
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 0,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_gem_xsum_article_DOC_summary_1.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_gem_xsum_article_DOC_summary_1.json
new file mode 100644
index 0000000000000000000000000000000000000000..6cae2ffed5c4d75a132caf734f57328bf57ef1db
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_gem_xsum_article_DOC_summary_1.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_precision": 0.18241736362419408,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_precision_stderr": 0.0035671793011444824
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_recall": 0.28088578439333156,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_recall_stderr": 0.004150802521339531
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_fmeasure": 0.20198994819537205,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_fmeasure_stderr": 0.002984694518793648
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_precision": 0.03766732268521147,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_precision_stderr": 0.0018002611735446364
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_recall": 0.05744303705984819,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_recall_stderr": 0.002394118114694247
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_fmeasure": 0.041266355576914736,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_fmeasure_stderr": 0.0017486414825347912
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_precision": 0.13852250267452665,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_precision_stderr": 0.0027600347382047627
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_recall": 0.21557457573877506,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_recall_stderr": 0.0032748640854860915
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_fmeasure": 0.1537399711922189,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_fmeasure_stderr": 0.0023040866331068065
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_precision": 0.14149023067517916,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_precision_stderr": 0.002779812720023245
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_recall": 0.2224713251909163,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_recall_stderr": 0.0035223603046659778
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_fmeasure": 0.157801209736622,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_fmeasure_stderr": 0.0023904477003575016
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "bleu": 1.8282472672146812,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "bleu_stderr": 0.1020121938444088
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 1,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_gem_xsum_article_DOC_summary_2.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_gem_xsum_article_DOC_summary_2.json
new file mode 100644
index 0000000000000000000000000000000000000000..e1826a66c036b9bc821d428c3a0c701e7428fb02
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_gem_xsum_article_DOC_summary_2.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_precision": 0.21893354662011963,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_precision_stderr": 0.004048272249341602
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_recall": 0.260092993109534,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_recall_stderr": 0.003902306781441875
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_fmeasure": 0.2195684919577384,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_fmeasure_stderr": 0.003254265138077691
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_precision": 0.04791765027513919,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_precision_stderr": 0.0022980519753049485
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_recall": 0.053493298501079714,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_recall_stderr": 0.0023052325119618023
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_fmeasure": 0.046526613891962755,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_fmeasure_stderr": 0.00204903807224034
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_precision": 0.16473734247474792,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_precision_stderr": 0.0031841165642595994
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_recall": 0.19604258368067826,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_recall_stderr": 0.0030444450297627
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_fmeasure": 0.16501217387582887,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_fmeasure_stderr": 0.0025424570393059753
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_precision": 0.1671435431989699,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_precision_stderr": 0.0031935413338326185
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_recall": 0.20091357776545432,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_recall_stderr": 0.003229501111978948
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_fmeasure": 0.16810787872676755,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_fmeasure_stderr": 0.0025882089916786253
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "bleu": 2.0883920440199915,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "bleu_stderr": 0.11737825754959746
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 2,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_gem_xsum_article_DOC_summary_3.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_gem_xsum_article_DOC_summary_3.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa4bcf4d147be59cff11476fd4d3dc25adde70e4
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_gem_xsum_article_DOC_summary_3.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_precision": 0.22154258705050656,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_precision_stderr": 0.004416958718487466
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_recall": 0.2427641584174357,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_recall_stderr": 0.00420050957184403
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_fmeasure": 0.21513910465275415,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_fmeasure_stderr": 0.0036788747099070216
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_precision": 0.050821433347839264,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_precision_stderr": 0.0023945363772249644
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_recall": 0.05453094107822012,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_recall_stderr": 0.002408142744637484
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_fmeasure": 0.04886471919044582,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_fmeasure_stderr": 0.002157338930931576
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_precision": 0.16668887518076203,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_precision_stderr": 0.003514628068406048
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_recall": 0.18226837233438312,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_recall_stderr": 0.003295475230668282
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_fmeasure": 0.16128891406853352,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_fmeasure_stderr": 0.002880789024699209
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_precision": 0.16896742575336499,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_precision_stderr": 0.00351461682461915
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_recall": 0.1869678121534825,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_recall_stderr": 0.003429064046115561
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_fmeasure": 0.1642209135986658,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_fmeasure_stderr": 0.0029068460098697737
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "bleu": 2.4903444029414104,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "bleu_stderr": 0.16888554758075064
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 3,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_gem_xsum_article_DOC_summary_4.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_gem_xsum_article_DOC_summary_4.json
new file mode 100644
index 0000000000000000000000000000000000000000..b681fd8f8edb612d936c0c4859ad766076a5f3bc
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_gem_xsum_article_DOC_summary_4.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_precision": 0.06587717027902634,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_precision_stderr": 0.0039704424509340985
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_recall": 0.06115142824616809,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_recall_stderr": 0.003616406533465941
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_fmeasure": 0.0572325652119175,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_fmeasure_stderr": 0.0032468616776549866
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_precision": 0.014030183412219063,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_precision_stderr": 0.001506975166878615
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_recall": 0.013471932961216628,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_recall_stderr": 0.0013203271107582826
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_fmeasure": 0.01224992383643623,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_fmeasure_stderr": 0.0011777335201229031
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_precision": 0.050416403187604805,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_precision_stderr": 0.0032341383122656336
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_recall": 0.0450041617246973,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_recall_stderr": 0.002689245329612641
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_fmeasure": 0.04246528505415009,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_fmeasure_stderr": 0.0024489654144463574
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_precision": 0.05133449482703434,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_precision_stderr": 0.0032661771463960336
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_recall": 0.046814652800863985,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_recall_stderr": 0.002844770088636042
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_fmeasure": 0.04361018726263517,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_fmeasure_stderr": 0.0025148690575369646
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "bleu": 0.215456941864469,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "bleu_stderr": 0.06941440736262179
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 4,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_gem_xsum_article_DOC_summary_5.json b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_gem_xsum_article_DOC_summary_5.json
new file mode 100644
index 0000000000000000000000000000000000000000..e60cbed99b41e334110bee96fc17faea492156a2
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/generation/slim.4b284b84b20c4py_gem_xsum_article_DOC_summary_5.json
@@ -0,0 +1,133 @@
+{
+  "results": [
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_precision": 0.0023814022915898026,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_precision_stderr": 0.0007101439263166566
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_recall": 0.0020217833554038362,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_recall_stderr": 0.0005950726577170537
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge1_fmeasure": 0.00214003217049867,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge1_fmeasure_stderr": 0.0006281208747948269
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_precision": 9.874063374559899e-05,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_precision_stderr": 7.004654141515487e-05
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_recall": 6.729119936667107e-05,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_recall_stderr": 4.7570795295869234e-05
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rouge2_fmeasure": 7.982297862229252e-05,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rouge2_fmeasure_stderr": 5.643442046339631e-05
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_precision": 0.0017095297689958592,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_precision_stderr": 0.0005079974336227376
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_recall": 0.0014314059035737939,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_recall_stderr": 0.0004049546110440357
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeL_fmeasure": 0.0015217948267156234,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeL_fmeasure_stderr": 0.0004371612073436473
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_precision": 0.0018171542939344795,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_precision_stderr": 0.0005294219136072831
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_recall": 0.0015326542359542015,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_recall_stderr": 0.0004286235600707048
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "rougeLsum_fmeasure": 0.001626133579867523,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "rougeLsum_fmeasure_stderr": 0.00046047748478715914
+    },
+    {
+      "task_name": "gem_xsum",
+      "prompt_name": "article_DOC_summary",
+      "bleu": 4.047824391489386e-39,
+      "dataset_path": "GEM/xsum",
+      "dataset_name": null,
+      "subset": "",
+      "bleu_stderr": 1.7044826243904522e-34
+    }
+  ],
+  "config": {
+    "model": "hf-causal",
+    "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4py/4b284b84b20c4py/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
+    "task_args": "",
+    "num_fewshot": 5,
+    "batch_size": 16,
+    "device": "cuda",
+    "use_cache": false,
+    "limit": 3000,
+    "bootstrap_iters": 10,
+    "seed": 1234
+  }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/rankeval/4b284b84b20c4py_0.json b/4b284b84b20c4py/evaluation/rankeval/4b284b84b20c4py_0.json
new file mode 100644
index 0000000000000000000000000000000000000000..c6161a869a5c6ca7ca3319ba02054e4db7db6759
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/rankeval/4b284b84b20c4py_0.json
@@ -0,0 +1,87 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.335,
+            "acc_stderr": 0.014933117490932573
+        },
+        "anli_r2": {
+            "acc": 0.327,
+            "acc_stderr": 0.014842213153411245
+        },
+        "anli_r3": {
+            "acc": 0.32916666666666666,
+            "acc_stderr": 0.01357080625843362
+        },
+        "cb": {
+            "acc": 0.32142857142857145,
+            "acc_stderr": 0.06297362289056342,
+            "f1": 0.16901408450704228
+        },
+        "copa": {
+            "acc": 0.74,
+            "acc_stderr": 0.04408440022768077
+        },
+        "hellaswag": {
+            "acc": 0.39613622784305913,
+            "acc_stderr": 0.004880937933163286,
+            "acc_norm": 0.5023899621589325,
+            "acc_norm_stderr": 0.0049897244086645216
+        },
+        "rte": {
+            "acc": 0.5306859205776173,
+            "acc_stderr": 0.03003973059219781
+        },
+        "winogrande": {
+            "acc": 0.5382794001578532,
+            "acc_stderr": 0.014011242594964118
+        },
+        "storycloze_2016": {
+            "acc": 0.6648850881881346,
+            "acc_stderr": 0.010915644164980039
+        },
+        "boolq": {
+            "acc": 0.5948012232415902,
+            "acc_stderr": 0.008586427929715526
+        },
+        "arc_easy": {
+            "acc": 0.5467171717171717,
+            "acc_stderr": 0.010214901516731618,
+            "acc_norm": 0.48358585858585856,
+            "acc_norm_stderr": 0.010254253565929301
+        },
+        "arc_challenge": {
+            "acc": 0.23378839590443687,
+            "acc_stderr": 0.012368225378507139,
+            "acc_norm": 0.257679180887372,
+            "acc_norm_stderr": 0.012780770562768409
+        },
+        "sciq": {
+            "acc": 0.843,
+            "acc_stderr": 0.011510146979230194,
+            "acc_norm": 0.729,
+            "acc_norm_stderr": 0.014062601350986186
+        },
+        "piqa": {
+            "acc": 0.7132752992383025,
+            "acc_stderr": 0.010551314503108063,
+            "acc_norm": 0.7154515778019587,
+            "acc_norm_stderr": 0.010527218464130635
+        }
+    },
+    "versions": {
+        "anli_r1": 0,
+        "anli_r2": 0,
+        "anli_r3": 0,
+        "cb": 1,
+        "copa": 0,
+        "hellaswag": 0,
+        "rte": 0,
+        "winogrande": 0,
+        "storycloze_2016": 0,
+        "boolq": 1,
+        "arc_easy": 0,
+        "arc_challenge": 0,
+        "sciq": 0,
+        "piqa": 0
+    }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/rankeval/4b284b84b20c4py_1.json b/4b284b84b20c4py/evaluation/rankeval/4b284b84b20c4py_1.json
new file mode 100644
index 0000000000000000000000000000000000000000..9746138188c7b5168795dddefe015eea4320eeb3
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/rankeval/4b284b84b20c4py_1.json
@@ -0,0 +1,87 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.327,
+            "acc_stderr": 0.014842213153411244
+        },
+        "anli_r2": {
+            "acc": 0.313,
+            "acc_stderr": 0.014671272822977892
+        },
+        "anli_r3": {
+            "acc": 0.345,
+            "acc_stderr": 0.013728421539454876
+        },
+        "cb": {
+            "acc": 0.5535714285714286,
+            "acc_stderr": 0.06703189227942397,
+            "f1": 0.3862470862470862
+        },
+        "copa": {
+            "acc": 0.72,
+            "acc_stderr": 0.04512608598542127
+        },
+        "hellaswag": {
+            "acc": 0.39494124676359293,
+            "acc_stderr": 0.004878390226591719,
+            "acc_norm": 0.5043815972913762,
+            "acc_norm_stderr": 0.004989589816180231
+        },
+        "rte": {
+            "acc": 0.5740072202166066,
+            "acc_stderr": 0.02976495674177765
+        },
+        "winogrande": {
+            "acc": 0.5430149960536701,
+            "acc_stderr": 0.01400038676159829
+        },
+        "storycloze_2016": {
+            "acc": 0.6632816675574559,
+            "acc_stderr": 0.010928525619392455
+        },
+        "boolq": {
+            "acc": 0.581039755351682,
+            "acc_stderr": 0.008629425249245244
+        },
+        "arc_easy": {
+            "acc": 0.5681818181818182,
+            "acc_stderr": 0.010163945352271723,
+            "acc_norm": 0.5349326599326599,
+            "acc_norm_stderr": 0.010234713052723674
+        },
+        "arc_challenge": {
+            "acc": 0.24658703071672355,
+            "acc_stderr": 0.012595726268790122,
+            "acc_norm": 0.26023890784982934,
+            "acc_norm_stderr": 0.01282193022511256
+        },
+        "sciq": {
+            "acc": 0.893,
+            "acc_stderr": 0.00977991035984717,
+            "acc_norm": 0.881,
+            "acc_norm_stderr": 0.010244215145336666
+        },
+        "piqa": {
+            "acc": 0.7165397170837867,
+            "acc_stderr": 0.010515057791152058,
+            "acc_norm": 0.7138193688792165,
+            "acc_norm_stderr": 0.010545318576106659
+        }
+    },
+    "versions": {
+        "anli_r1": 0,
+        "anli_r2": 0,
+        "anli_r3": 0,
+        "cb": 1,
+        "copa": 0,
+        "hellaswag": 0,
+        "rte": 0,
+        "winogrande": 0,
+        "storycloze_2016": 0,
+        "boolq": 1,
+        "arc_easy": 0,
+        "arc_challenge": 0,
+        "sciq": 0,
+        "piqa": 0
+    }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/rankeval/4b284b84b20c4py_2.json b/4b284b84b20c4py/evaluation/rankeval/4b284b84b20c4py_2.json
new file mode 100644
index 0000000000000000000000000000000000000000..15e7d0fc2ce6877d2501762b15958580a340fd7a
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/rankeval/4b284b84b20c4py_2.json
@@ -0,0 +1,87 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.331,
+            "acc_stderr": 0.014888272588203947
+        },
+        "anli_r2": {
+            "acc": 0.34,
+            "acc_stderr": 0.014987482264363935
+        },
+        "anli_r3": {
+            "acc": 0.3308333333333333,
+            "acc_stderr": 0.013588208070709002
+        },
+        "cb": {
+            "acc": 0.5535714285714286,
+            "acc_stderr": 0.06703189227942395,
+            "f1": 0.3899371069182391
+        },
+        "copa": {
+            "acc": 0.71,
+            "acc_stderr": 0.045604802157206845
+        },
+        "hellaswag": {
+            "acc": 0.39384584744074885,
+            "acc_stderr": 0.004876028037941942,
+            "acc_norm": 0.5052778331009758,
+            "acc_norm_stderr": 0.004989503417767287
+        },
+        "rte": {
+            "acc": 0.5379061371841155,
+            "acc_stderr": 0.03000984891252912
+        },
+        "winogrande": {
+            "acc": 0.5374901341752171,
+            "acc_stderr": 0.014012928183336573
+        },
+        "storycloze_2016": {
+            "acc": 0.6509887760555852,
+            "acc_stderr": 0.011022640519108541
+        },
+        "boolq": {
+            "acc": 0.5743119266055046,
+            "acc_stderr": 0.008647930658219415
+        },
+        "arc_easy": {
+            "acc": 0.5782828282828283,
+            "acc_stderr": 0.01013325528401233,
+            "acc_norm": 0.561026936026936,
+            "acc_norm_stderr": 0.010183076012972057
+        },
+        "arc_challenge": {
+            "acc": 0.25170648464163825,
+            "acc_stderr": 0.01268249633404296,
+            "acc_norm": 0.2713310580204778,
+            "acc_norm_stderr": 0.012993807727545794
+        },
+        "sciq": {
+            "acc": 0.902,
+            "acc_stderr": 0.009406619184621249,
+            "acc_norm": 0.902,
+            "acc_norm_stderr": 0.009406619184621228
+        },
+        "piqa": {
+            "acc": 0.7181719260065288,
+            "acc_stderr": 0.01049667523125817,
+            "acc_norm": 0.7290533188248096,
+            "acc_norm_stderr": 0.010369718937426844
+        }
+    },
+    "versions": {
+        "anli_r1": 0,
+        "anli_r2": 0,
+        "anli_r3": 0,
+        "cb": 1,
+        "copa": 0,
+        "hellaswag": 0,
+        "rte": 0,
+        "winogrande": 0,
+        "storycloze_2016": 0,
+        "boolq": 1,
+        "arc_easy": 0,
+        "arc_challenge": 0,
+        "sciq": 0,
+        "piqa": 0
+    }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/rankeval/4b284b84b20c4py_3.json b/4b284b84b20c4py/evaluation/rankeval/4b284b84b20c4py_3.json
new file mode 100644
index 0000000000000000000000000000000000000000..8422e4a4cfbdfc79db10fb2c79e8965537c20a1d
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/rankeval/4b284b84b20c4py_3.json
@@ -0,0 +1,87 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.31,
+            "acc_stderr": 0.014632638658632896
+        },
+        "anli_r2": {
+            "acc": 0.323,
+            "acc_stderr": 0.014794927843348635
+        },
+        "anli_r3": {
+            "acc": 0.31916666666666665,
+            "acc_stderr": 0.013462309712005129
+        },
+        "cb": {
+            "acc": 0.5714285714285714,
+            "acc_stderr": 0.06672848092813058,
+            "f1": 0.399067599067599
+        },
+        "copa": {
+            "acc": 0.74,
+            "acc_stderr": 0.04408440022768079
+        },
+        "hellaswag": {
+            "acc": 0.39533957379008167,
+            "acc_stderr": 0.00487924284847347,
+            "acc_norm": 0.510655247958574,
+            "acc_norm_stderr": 0.004988648260010036
+        },
+        "rte": {
+            "acc": 0.5487364620938628,
+            "acc_stderr": 0.02995314924180894
+        },
+        "winogrande": {
+            "acc": 0.5509076558800315,
+            "acc_stderr": 0.013979459389140846
+        },
+        "storycloze_2016": {
+            "acc": 0.6622127204703367,
+            "acc_stderr": 0.01093703499100388
+        },
+        "boolq": {
+            "acc": 0.5685015290519878,
+            "acc_stderr": 0.008662594569027307
+        },
+        "arc_easy": {
+            "acc": 0.5728114478114478,
+            "acc_stderr": 0.010150415974210868,
+            "acc_norm": 0.563973063973064,
+            "acc_norm_stderr": 0.010175459582759732
+        },
+        "arc_challenge": {
+            "acc": 0.25170648464163825,
+            "acc_stderr": 0.012682496334042961,
+            "acc_norm": 0.26706484641638223,
+            "acc_norm_stderr": 0.01292893319649635
+        },
+        "sciq": {
+            "acc": 0.906,
+            "acc_stderr": 0.009233052000787743,
+            "acc_norm": 0.897,
+            "acc_norm_stderr": 0.009616833339695796
+        },
+        "piqa": {
+            "acc": 0.7219804134929271,
+            "acc_stderr": 0.010453117358332799,
+            "acc_norm": 0.720892274211099,
+            "acc_norm_stderr": 0.010465657948498231
+        }
+    },
+    "versions": {
+        "anli_r1": 0,
+        "anli_r2": 0,
+        "anli_r3": 0,
+        "cb": 1,
+        "copa": 0,
+        "hellaswag": 0,
+        "rte": 0,
+        "winogrande": 0,
+        "storycloze_2016": 0,
+        "boolq": 1,
+        "arc_easy": 0,
+        "arc_challenge": 0,
+        "sciq": 0,
+        "piqa": 0
+    }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/rankeval/4b284b84b20c4py_4.json b/4b284b84b20c4py/evaluation/rankeval/4b284b84b20c4py_4.json
new file mode 100644
index 0000000000000000000000000000000000000000..3bc4f599a2a5b4c9285810ada9a33a3b9dd2a90d
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/rankeval/4b284b84b20c4py_4.json
@@ -0,0 +1,87 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.342,
+            "acc_stderr": 0.015008706182121733
+        },
+        "anli_r2": {
+            "acc": 0.327,
+            "acc_stderr": 0.014842213153411245
+        },
+        "anli_r3": {
+            "acc": 0.32166666666666666,
+            "acc_stderr": 0.013490095282989521
+        },
+        "cb": {
+            "acc": 0.48214285714285715,
+            "acc_stderr": 0.0673769750864465,
+            "f1": 0.3335679099225897
+        },
+        "copa": {
+            "acc": 0.71,
+            "acc_stderr": 0.04560480215720684
+        },
+        "hellaswag": {
+            "acc": 0.39623580959968135,
+            "acc_stderr": 0.004881148866874186,
+            "acc_norm": 0.5078669587731528,
+            "acc_norm_stderr": 0.004989163747650759
+        },
+        "rte": {
+            "acc": 0.5054151624548736,
+            "acc_stderr": 0.030094698123239966
+        },
+        "winogrande": {
+            "acc": 0.5453827940015785,
+            "acc_stderr": 0.013994481027065997
+        },
+        "storycloze_2016": {
+            "acc": 0.65793693212186,
+            "acc_stderr": 0.01097044950238848
+        },
+        "boolq": {
+            "acc": 0.5623853211009174,
+            "acc_stderr": 0.008676717715731629
+        },
+        "arc_easy": {
+            "acc": 0.577020202020202,
+            "acc_stderr": 0.010137328382209097,
+            "acc_norm": 0.5664983164983165,
+            "acc_norm_stderr": 0.010168640625454101
+        },
+        "arc_challenge": {
+            "acc": 0.23464163822525597,
+            "acc_stderr": 0.012383873560768678,
+            "acc_norm": 0.2696245733788396,
+            "acc_norm_stderr": 0.012968040686869148
+        },
+        "sciq": {
+            "acc": 0.912,
+            "acc_stderr": 0.008963053962592065,
+            "acc_norm": 0.903,
+            "acc_norm_stderr": 0.009363689373248116
+        },
+        "piqa": {
+            "acc": 0.719804134929271,
+            "acc_stderr": 0.01047812201557708,
+            "acc_norm": 0.7181719260065288,
+            "acc_norm_stderr": 0.010496675231258152
+        }
+    },
+    "versions": {
+        "anli_r1": 0,
+        "anli_r2": 0,
+        "anli_r3": 0,
+        "cb": 1,
+        "copa": 0,
+        "hellaswag": 0,
+        "rte": 0,
+        "winogrande": 0,
+        "storycloze_2016": 0,
+        "boolq": 1,
+        "arc_easy": 0,
+        "arc_challenge": 0,
+        "sciq": 0,
+        "piqa": 0
+    }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/evaluation/rankeval/4b284b84b20c4py_5.json b/4b284b84b20c4py/evaluation/rankeval/4b284b84b20c4py_5.json
new file mode 100644
index 0000000000000000000000000000000000000000..d344b78fb207fc4dee3f5f1ca1f5e6c1390082c7
--- /dev/null
+++ b/4b284b84b20c4py/evaluation/rankeval/4b284b84b20c4py_5.json
@@ -0,0 +1,87 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.332,
+            "acc_stderr": 0.014899597242811476
+        },
+        "anli_r2": {
+            "acc": 0.302,
+            "acc_stderr": 0.014526080235459557
+        },
+        "anli_r3": {
+            "acc": 0.3516666666666667,
+            "acc_stderr": 0.013789711695404801
+        },
+        "cb": {
+            "acc": 0.4107142857142857,
+            "acc_stderr": 0.0663363415035954,
+            "f1": 0.28648018648018647
+        },
+        "copa": {
+            "acc": 0.74,
+            "acc_stderr": 0.04408440022768079
+        },
+        "hellaswag": {
+            "acc": 0.3934475204142601,
+            "acc_stderr": 0.004875162699121656,
+            "acc_norm": 0.5103565026887075,
+            "acc_norm_stderr": 0.004988710917169336
+        },
+        "rte": {
+            "acc": 0.555956678700361,
+            "acc_stderr": 0.029907396333795994
+        },
+        "winogrande": {
+            "acc": 0.5382794001578532,
+            "acc_stderr": 0.014011242594964122
+        },
+        "storycloze_2016": {
+            "acc": 0.6691608765366115,
+            "acc_stderr": 0.010880601338204657
+        },
+        "boolq": {
+            "acc": 0.5663608562691131,
+            "acc_stderr": 0.00866769046434468
+        },
+        "arc_easy": {
+            "acc": 0.5791245791245792,
+            "acc_stderr": 0.01013050216406634,
+            "acc_norm": 0.5732323232323232,
+            "acc_norm_stderr": 0.010149141043955631
+        },
+        "arc_challenge": {
+            "acc": 0.24829351535836178,
+            "acc_stderr": 0.012624912868089758,
+            "acc_norm": 0.26535836177474403,
+            "acc_norm_stderr": 0.012902554762313967
+        },
+        "sciq": {
+            "acc": 0.918,
+            "acc_stderr": 0.008680515615523706,
+            "acc_norm": 0.913,
+            "acc_norm_stderr": 0.0089168666307459
+        },
+        "piqa": {
+            "acc": 0.7219804134929271,
+            "acc_stderr": 0.010453117358332811,
+            "acc_norm": 0.7230685527747551,
+            "acc_norm_stderr": 0.010440499969334554
+        }
+    },
+    "versions": {
+        "anli_r1": 0,
+        "anli_r2": 0,
+        "anli_r3": 0,
+        "cb": 1,
+        "copa": 0,
+        "hellaswag": 0,
+        "rte": 0,
+        "winogrande": 0,
+        "storycloze_2016": 0,
+        "boolq": 1,
+        "arc_easy": 0,
+        "arc_challenge": 0,
+        "sciq": 0,
+        "piqa": 0
+    }
+}
\ No newline at end of file
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7900d2a11618f4a886dd119bebe11eeae7731e26
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f90eb0212c9b5bcc1592eddb12c4a77d662df62b380a55d3be190b42089cf07
+size 199058647
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..38c2e8c9ec9efd10be0ff2e3434e6d0f2d370288
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18b175722d6a500208611c092ba414b6eb906a9e561e050f2bf857b9ca83e927
+size 199058647
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fc78498267e001b998105ae4fb73a2a0a1132461
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14c90521c0b47dd916fd6fb4f440c4ef9a8f071001d33bdcdd9e65070a390ddb
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..240f4ae63540993920227fa1605a0cb79c13add7
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9ced98047b5fab7427f428494f41202c289a3a111b5d8b6f1ee821bcc3b6574
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f3a82eb73c3fc8ace9e19d33cf9a235a43f456d3
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34f53b83e7cc40728eaae1638c2ef57ec40173e86b5e883ea22b82e8bb71ebc5
+size 199058797
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4a7d2a254b9004fde4524613780d38fc2376f948
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd7da31629cf259bb30a459a5def959275102a7a1b753f2cdf87a1a0207bc4ca
+size 199058797
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ce3497b45779edea16db79d42d9e3d3f7b620ec4
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0503d8f55bc97c9a02e015552ecbe9b35a28b30df6a70de834a09de439c9617b
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..39e107c8e677c418fab795609343f665dff5874e
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53680f168391f3d52bf3e0371a5f3df4a1c1fe5fd3631fabea416c6f552caa8e
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..47b396e4edfb154a252de7003330745e8c881e4c
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3b31ba4d897f32b53b53308dfd24a4cdbf662df7e1c93fdb9f75666a10a380
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..09aed556d70ee5985bae73c77bbe5521e0b1e893
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ca66ac42f4c189f0753c99a6b7394d2606b67d128e94e58106b1895d2496e1b
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bbcbcf8cb8287b3e69bffc54d3acb6895ed3f044
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5e8c900f3587eabe76fce6deb1567d0a69a4ec0ceceac6097132289443731aa
+size 199058797
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..76c9e50bb718faf6b0a0723e22d75c5d7c1a9323
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5247d5636915bd67ad476766999935039d6f4dd3f45c04aa5fbabb8e962bdce8
+size 199058797
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..335ca2526eb987a5201915efcaaab2c63054a84e
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf6a64eddda016090a498573b325c58380f13fb3bdbde4c014810f993c41c17e
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8dad93996d51fdc2a52220e54bdc6e9d47c5d3d0
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15c3b1505b8051ef29178e337cd3838b9f7764fb944a55ac9d7d02af0c4cf1ba
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a1e059a0b69fa7b5c07851f7d5dbf9254892be0d
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d67ed65144ebceac5d652dd746079faf47c4ef4997207bfd98075865b9265b6
+size 199058669
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1590581a057690b7159c4400e742b96cec148c15
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:931452c593ff4e3b96b2a215f205470b045497a946b263c0ddbe484f2b810bb5
+size 199058669
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c056504406f9f50de84c59ca7f5a9b857bf7e353
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6570447636664217e53393407beb41a5bbc73e34884407a9d2c19a3d5ea4226f
+size 199058797
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9eb58734fbe35746e296ab76048a4fd8fb9ad461
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8268998db535795533f29759669490e1f0c92949cb5024401f0f19919a752730
+size 199058797
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cd7a647333a500483d568e8699cf7637d58ca327
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:343142da9fc37f56298003919dfcedc3fc87fb870ac8105332b8a3cb1a3ad617
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2c3ecbd7fd33c5efbc5e375a6ec9542dcf644b9f
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5abb819aa8b8082905767fb6634e443f7ebaf0868bfce2abe3bdb28456491df
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2767a7b282c40d09f26ab98dafcca46b42ec2c54
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9e9f4bb404f384076d456e9d663ad12d38a3af0ff0e56731a5ff9b5bddd2056
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2ab56182786229bbe7914d3ea779cd8a261296c8
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6ae4b1c8ef349352c9ec1b5fa44072d32ee0ccee1c1975f08fc045a7ddd2a4f
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..98e1cd2517b5dde4caaf006031e231ffca095a91
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f327ae1f74f1969f75b69d504a66353efc5688c6df7c15c3e589411f8a77126
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0d483e0fa09b4ed845973b9202e0dc5827cee906
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dbebda97eeda3815858b31b117a447f3f14d0ec9c26fa3ea4856405a1f04383
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1744d4787df01762c414c2fe681b1d864f0e4a69
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38ffbc5eca2bef2530a11202c259c8999e1eea93f662c7819029e601325833db
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..390cc936d5b03ebb73557e1291569357ee7dad04
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de718a1a90da6c2117096505e5aae340f38d6123423bdd5e55fb74777dac7c79
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d74f83d37dc36bcf1422eb90291f9e06fef48417
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83eb9ca47bb76e9844d28024ca336539b0d09943084da416106eb350e3590551
+size 199058797
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..76fbb4d17185c94bef62164ca28e0a8b6c928fbb
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43470c5e78014cec49dc1e87c62085caeaf78ffdce1ef689179ef0fe4461cb9f
+size 199058797
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6c00ad8aa0b6ca0de48659bb7c01df35f6ac7c26
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db5535bdc0a224b228c992480d87ccc9290564fa5352ca8d655c009a304880d1
+size 199058605
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2c974bddf2245daba7abc02bea09c34a41912a10
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a0333ec795dda1a35d75fea95ac74ef1c6492ff57bee070a8cc601ffcbee5d
+size 199058605
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..aa860d1a7b6040f2d931379a85f1b8238e7337d0
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ce4b69e5e9c26fa4e614d37c48f0577b35139ed8fb49e02024157975e3ad088
+size 199058669
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2d1ef441cb6fc515aa4e5a05a1420c46fcb84a52
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1717b1778145b64946156e0786163fe873ef3f3f333b10c3c986203c88b0c46d
+size 199058669
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9af20da56309bd89101ed315b68a9bf7f8d3b4b3
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6833fc7df4a56b26e90d6a9fa99be0ebce0781439b0f7e335327ec4a47270436
+size 199058797
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..533ce89abc6ac3d300b8053dad4d89c8cdd645d9
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afb2574756c76e433362e2788177b6967fd18211df2ec14656509422f7f47eba
+size 199058797
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0f16ddd4511a91ff4933c76e7d013f7f0d68e397
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b06ae24e8465c7c6844d1e443a8e0a3b5969814181ababba8c147e506fe9ab
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..eb087e1065ff5574ef429371b9e81ba29a03f13d
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d289ef26895b9381f07c6c592a8cdab8c3513b21f08b6dd277efe78b6b49f72
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8e2a00f1f4aa8865fefbe62662c637a31e8a19a1
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:612013cc6547118dcc100977a873834ff5627b5bfc88fd2080b6520e6ffde3b8
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e3c329e90c86097065a83b062cc65e882bc8b72f
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:518df733e732bf2a40c8a53fc59977f5512f7fb2d7d8809eb3e8954882d522df
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4e87486d9c71024d60d63cac62fa4ef41fdff71e
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b563cf1302c42808df03a5010b3693e5f99a0e2dfc0dcf80cc66cfb46cce564
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7459a1ba49eb702d7c99da56ffad260eb66f768a
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f4ac48aa0e4bbaf6a273f08632fdfd4ad454d76cc1a0d7b39760194a0bfc5e
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8f3b9b250ae4bce9fe28bb1e39d6d5d65864f206
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8b38dcbfd0a712cd1b0a45f598f0a3301247f6e74ae4120049f691882b3b6cb
+size 199058797
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b5e07c898eca201be1e8ce41cc46c7cd8ff9d273
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51af86b0fbc9f0049aed837a961443d79949537ff8de32146fcec347b3c0115b
+size 199058797
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3ae68bbaaed16ee4a4d9bfc0488bef799ac1190d
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae19b960f2c4a6039dad7ade3f997d3aafdff5faf01427bde078a5221ce664ea
+size 199058669
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..dc1e7e7c76a734e7ad78f539682c5b2348dd1b90
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b98ecc187b5bd949f01eda38e6a7bc7b4d943dd123cab1202694e9e8c16408
+size 199058669
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d8c338123500591ccaa6c32f2d2155d572013b83
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ad339e0c52c326c6e1179bcc9106fea1e2dd14769f77d1bcbda44e2a4c47c30
+size 199058850
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..04ee7a1504311c156d705c55f91d724390e9231a
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd8773e685f8bd3cf8181cfbe40df4f291a7bdc3e9e37a1e8920744b3fc2176a
+size 199058850
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b6eeb9f3f0cdbd9ca5e4b8b9220b2d7f35a7ec5f
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b8143673a4d4f54d3e7312686dcd9dfd95bb860427f03fa9d995b24824383e
+size 199058669
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f692037ba0bb623cb9daf526c54a96b72587360f
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e5eae80316f11ac538ed299b34e7694d82a5fda82be15582a596bb9c9e01d1
+size 199058669
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..766e4bcfcd1b025b87872b7dbe5f077423028ac8
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a0a4e8a5f1b1f8a0e2ee2f0911ed7d67f48b63991c54bb3f94516abb6718a8f
+size 199058797
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fd38fa33ec19861687154b9932de1dc3f0ef79e0
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21af6724b5876bff276396cf8f7572e77fa8ddbebecf64e1aec2b4761918d8f6
+size 199058797
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ad97099774517308c30e6862b82bb7c49d39f9bc
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54715094a29cffe346be512a93f76b9da36493380e61136ef9761cd08987f675
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8dade304f1ad035bc233207867f6ca7550b6c864
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aca8420258b713d7d53a5841569ba668d9afceb92b6c29835766615a92245358
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fbcbf026a264ebe4de761a6051b8cf89ca0863e9
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:589434b1eba8a1260e465aa0b1e7639f9f6aaffea85c233ea1eb9b994cfcb136
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..21840a088c8e1586de836dbefea7e5cbe19b59bc
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b03623f9c4edc9b36528af6c1905b0662c957bb34cf76757061fc0d5e0bdc4f5
+size 199058733
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d612825341b89d69afb4ca38b9ec54407638588e
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb3f4b538cdfc7e00cb6210bafffdf2f58896481f2f4575473cd3d51166c5852
+size 199058669
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c88365f99b3a7c24b5ccb92543d98815df362484
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a6bc85f71629d99d056dfdb81e122bf2b2d38f88333a25a59414b654aa461a
+size 199058669
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ed7185bc84e474fdf34e88c9f0d28a59c83768f5
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d16bb84a5a13416e641ef2aa17ca2c5c24726ac1efbc504b731a1bdb2c0e3d17
+size 199058925
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fef1f1b26a5f29fa52df1a334b81d467b1194227
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08018d303b3bba358b7d3e82e41bd29c093d07342b730b164a0c0da494dcb797
+size 199058925
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b669f499fd6198d922e2a0d2386c73e630e7fd1b
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d5884745c48145d8eb6578b39287ac019707297a8ec033eba09e8cc7a281706
+size 199058605
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2e5844e3240bc7b7a9cc45bc32de960287ff5c2d
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03d17872915d1b581e9aa552ee26e05612c1513f6b2e2a6c76f07a1ec1d51fff
+size 199058605
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b2a67184e46a1939506a2680f8df402ebdb977f6
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7b5beb9df6fcb2d6d4540053d3bd2c155c141193cbb712e8f6601b896f83342
+size 199058605
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..325ee73c1601a9b28597558dc38e72e4057eb31d
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b79ffcafd7b0e33067454c42d0ff4ec5739f915108c8beedc8b7d4d8e588327
+size 199058605
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..60b9f88779a8eca4aa89302329bfe918054c5c3a
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6d77cf9306af870f0770f9ecebc9d44289d029f37c6cc2ded0b358f74dd6897
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..849e757179d4158d60aaa116b2c0c9fcf493a40e
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a126dccc5b2f8e0122b09010ade1981462343d8b0931f656d20c9bd64dd2dfc
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..72ccb1564f12000968f59f39278ca6aea87a3b35
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21d3a8f0c4dce7f5d3c5fddd01758ce3b6522f81a1275416dfaa259e9258813c
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..28b2afb5babfdd6546292ff8976f705db4bc8a91
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d13487442063dc4b44a76270d881928f1c348c15c8db893d1d3050e4a2d9902e
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d0e5ba1a3d062c812f8fc505da08fec78c2f6408
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf01be19675ee60a2b0b5f2670841cdf71c0b993267dcc300c0998b39ee8a7fd
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b84a0999eaf54843680cbb4892f749e8d2cf8b68
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deb9cc90ad6402fb188882bbee939db5b4e644fa856f0c4ca9e3fabbe928a7ca
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..42f465623328234dfc901032449485cdbacdb522
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e50ee8a64cb9167609d77b091c50fb48a652877abe06aa55d1f7c621273813
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..39aace2a360903e0bda7152e44a7ad82707171f2
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ccde26b9c38302920587e0748de70bb2abf4005dbed83b0d4228b6c4e03aada
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..19727e6e24d3a65d4be7c745d1aed195f62fe502
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:361c62f2401fd0f21fab90edd2835dad18730d5cdf936d963bab2eac798056bd
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fbad60ad0c33f50a93af8e4a5500372deba74d11
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e685d3482ecaeb1d6bb8e3a4babbbf1bc83a08be8179c8da4806e6bb5e49aced
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4a654995fc11bf29c8674c2857f317a77ff6b9da
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b09141630ffac2eac98f48111fa0096a81bca0db32826ba01caa93ae613a840a
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5a2ea88ea3be2246ff78c447f930b037d82e2c66
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f0ccee363073f426da31162f11ae0820cc9d9666cf4f079fad05e8907465099
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4203cbee163a7fccf34911dfa92efba8c03b008e
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12cb46a4f945eabb16de4675bfdb790ff39a5dc01e69c39a4644f57397eb3a20
+size 199058978
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a6b0b0e287dfac1ee941432dd7d111731269bf3a
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2054adeed5ef35a63543c6f20c7c88389c569e0a709888f2eea1cbd9c63204eb
+size 199058978
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..35ebd3b4c1117082ba380311fc92e0fe8e605646
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3cce185467fbe0252966d2ad3aa842fe1cfb78dcb3d835440c44af8aff7e1ee
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3daa31d3a94f69922f9df2649ba2ff768b41c680
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e127cc7e6f497b3fb73428e26745ad86ae6dcd2abd5cd0b015482a8b2a8634b3
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..87497c7b3e8a2ef35eb89940878442f47cf741e8
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8d8d411a099946ad1141e8426539d11a1d6dab4d46350da9d93af839143f6b3
+size 199058647
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..94a9a87fcea465ff407b25ec8795dba57fde0a03
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a243bd80073b04c2323e01f1ac9f636e1d2687dc892e3bbe188731b983f31e
+size 199058647
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..afea1e107b59d6d6635510164f55be9139a815db
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:174ee6a6a72bdd5e0514612429d4e5060f4177d3a16c0ef287ec71d80e70f84d
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f436642eb908a0742536be5bfa5b6935938d924e
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b78cf3eb2fce314bc328f9db2cd57d8bada5375e68a645b73c5853291d5543f5
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0a4bd8aa06b6f7c39ef78260255e46b6c1250b92
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:093913f5a4c09beecad3e8ce88ab148b3a581b0c170009a269aaa7c601876635
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6f0351ac44e91f210569f36b0b0d3f6a7da0e02e
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb1d5359df0a87cfa5142cc40606fc4639dd0b3fcd3a94c7e8db732fa49f1693
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8e44fc2e29880e2b7b49e759fe95d0afc69578fc
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:002757cea4e0b4b05ac87e14623179e2cd5d3bfeb32cb3348966d5429aab2f31
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a610841714375e701a397b3b939fb4a59f82da77
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1f391ce10ba117de4335f7a2b428ad055fadc53f426b44380ec4f352bd62bf1
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8dba6bab2295430551c941e0e5ebee560a9c880a
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bc67fd73a4e692d7c8050c39f516660ba7632eea44efe97a0307124f1c0a5d0
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a6942a318be7eb945648574807ac31eac2b2b17f
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41a07739d375dd4bccf2fdb6568bcfa2faf2c3f80e5f909243852cd4b0c034a4
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..276943657ba2f85a07e5b091dac334f389ad0730
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71af6ff2a790a158117d309bf36b603fbe08eac0eb635ba48e290ad1380c83f7
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..78a9b884054cffacf3acb0830ad579763a97c496
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e0dcb5e367fc6237f17f0a0152722a527638c5c965c17fa56c7d20793684be8
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a8934f09e6fca42d68d3d9d56d7486bc3574151d
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6b8c1d656264c8996a68c7a5fd8c03d416426f2843bb175a42cd752661b7a33
+size 199058850
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f6009cd99c324bf0e24a4b0f9f91bc50e89d1f9d
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb8e597592bc941688a686f4be2a4626f150549d20053bd04a40b264d30c46c
+size 199058850
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..dea4f8ec35f7314bf90220f5cadb542625241546
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cd1fc901b0888dfe13472bc57dc0d31bed3a8581fbf6cdb622f8b92cfe5e547
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5eb4034c2b2e3f01e71f814a7228283706126680
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:745911c449d090415346d8d5af92ba6c1fff29f1a62d483b94b65b69871c3873
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9ea2da44698a6e7a17c7e042b13c90bd2fc94bad
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e7e9504817c90c36cefd0e790e49b39225c0681ba7aace75ee566840ee055f2
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1674f7d5083c1160719313afe67d47343b33c39b
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:512ab86d5f72c9c78c7ff7ba186aa6ebb3bd4c38d766f4896c699156deee7ace
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8dde78b0f0faff125796aa578d73694ac35b022b
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d66778fd786fd8f5ad3c247bf7296f683994abe08c26882998f8ca0271a5a3dc
+size 199058594
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e073187996941e9382e3898e5afe71b1d12ff6a0
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0511eb975db2415b757102853de5e64f33ad0fc87d3e0962ae6c968abb09acbb
+size 199058594
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..51b0a086c12192c9fe2d4e125f16a78c97f080c5
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac1c47db86077632e511d73b4b6796856011cb1613be2e30b758dab89055e528
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4f74efcdb1ad956020e0265875a95327b86f32ff
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c2bf9a6c452d373e6b379e5449a0220a4e223de8bd22ad7015ece6c344d0745
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c494ba2c7ffe71d4eb4207191c3e8836fe4b8303
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deaeaa830d5c3f6e0f745aa10ba2191b19de36216bd8991e673bccf395cdb7f5
+size 199058711
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c5c68bbbbacddc3aa1c240324eb1aba56fdeee25
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8637ad773bebea7bbebfb67fbdb19c813ca94637e22b445340e7882f2bad3bb
+size 199058711
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..040c70213caeea328c42d0db87d766fbde50bb8b
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f322f936ac1c3cd1f6c51f2f5a8592fbcde39e99e212057fa8f720b97c9c4cc9
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e9829707895fefd590735e985337c5b0242874af
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b34072022faba411465dffcfdf078355455f34253337982c5abbd6e9e47c6b6
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..319c57edc2349cc8cc8e28c8ac031ea29c101ad1
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d910886220aec2dce4954240b0b9f6482709bebb1904477c058fb348b0b2df5b
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..05c56d67511d7ad4b7ca7c526e2c871b200069cd
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:203c44444c0c1f2a65159db786500bdf21aa594509d06be2b2756b627ac2b0b3
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d71c1dcd3c79efbbc1dc2b84072bc2092580f969
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c6ba2b2abc8dc3a97405cc1b1d1a96bdd22e8adcd9fb642a538a6f797bb8078
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9be7046cafcf55a9062434932418ebffb855dc48
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5465e54367aaa5415f04cfdb413e6632b8942b7f2c3be4ed5b60d0002649739
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0f4d5fce6dac7322dc5bfd14905f0eaf8fe429a7
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc2fd3e22e91461a96849c1af5b4afb20426096117bae16209d7d47ae9b28054
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..66b64810b7beed562256aa759c4d0485b9d8659b
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8f5b04fef34d673dc369188d2e54af895677c4f13863613800981cdfe18fec9
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..919f193ac28a5d6df843d59d442aa564563a857b
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d253c9f484bedc0fb0b6cefb46fde86b76dfedbe57291f641d8fe3b773752eb0
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..dc7a76b7707509daa3bdfcd82b038a33016f2659
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44e8dc64781ad2c121036e1f6694552b9893d3d632264af957bcf0ed8483a4f7
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5eba6aca16a29e4af34e6771cd93f757bcbba4f8
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1c978bc91e95547b1e3a629f13dab7e085e2944ceee5685b6dd49cd5f7b747b
+size 199058594
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bde956c563146d26a3699146eb4f49e19cc7b602
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:435eadbcb3b2b78a619e6dc1178eb18ac7187a4c5e0eba8b5076e65491f1feda
+size 199058594
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ca05041f983d5e32fca0607aefd62e8cc2976316
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c28b44754a098ff7f8d54a09d11279d96eef16f2db9a03a38892deeb2cbf23
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..51e78bf913318b088468a5c5b4da455668521350
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd73ef6de1711b02cab527a1561c6ab97dd45b402e8c035c67667095e565b7ee
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a960c4df8e07aeeac41b9e7424288fe2e45ee720
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:507135f590322188c966c62b7d8666801dcc5f77ec66386dea379208f2287ddb
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..93f40acb2b48a4537f3a7241e3a652024f73aac3
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf61585fa41aa8a6fd477fdf89cb6b313fb4d5408736d9825347be2b0c8609b7
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..be777d02e73f180bdbc430e174c25af722917093
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4019d4c7ae27980fd38cf25eecba159596efeb9f1e02c67966b2868d8b606d6e
+size 199058850
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..785e814609f26e355fdfb15f5fcf256ae87c701d
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89c5694b76918004e4d0dbd23a4ef0087c0b57e7ef387c91528d4082ba6d792b
+size 199058850
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8bfb32616c8edacadb5636aa8c79912f3561b42b
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a7d59cbb62fe1878a8145929e07620dc3a6475705cbdd0e573e06bb8af2be1b
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7822d6097aa4e02b83fc8b1c08607da186dc9273
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b83b2e6e650a1cb1884c7328e940202b1c85c87978f40c3b41368b02acd382e2
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ccceae1a8d3a4912423a69482035ea8e241cfd8a
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27cd6ba001159eb1f2300579f4fe7c5d34d17cea54a21a557aa9fa70e33672c9
+size 199058647
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b1828f8068fb32b06088be5e912abd8fc4d60934
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4bdaabd1db079b1d01abacdf0cf60b181c769ffd815c14fb3e8d1e6af2d83e0
+size 199058647
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..692298fc176cc1208cf4e03efa2902e452848ada
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcd9d3381da694e5029b63b16112cb9b6520592497ee73c038c6f9d568b02953
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1254b23189fe72f42107870c90baefde55dab6d7
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659b3e35f878568012463e4dd77b11aadeb36df1fba173eaf1f856132e5472e1
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ae33dba92c3a7fc11b67cc6b776e3af6e0242934
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bae554a6ff5b1ed728083828b3de0689fef7e609d1d98c8b368bec2ed79361c
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3d40ca0184949ea2aa0758a7f78ee7fbb4da5509
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c76344a7ecba112dac88280206870cb73087ad0bbd3e8aff0c498f9ecd8827e
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9e2570fc48d94100b2519ded2f4bbd62b7fe1df3
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9bab21a33663a0bd62f992408032d8bb1c8fc2250f2cad47fff3b6e586de7b8
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e56a4d0c11dafd10f99031f9d8040aecf99551af
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b00ea535def5e206b15ab4eb2beb92aa4310393db50db3fea0bf8d0f25e0ebb5
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..feb44db6dbbb5b842e36fc94cb660fe2d3366b3f
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8878e485060ab232ff1aa79ba7f93067c06e7597a23cfceffd842aa57f7f7ea5
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a7f9e6efd124e5c8df867aef9d57be560c5070a9
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01db8ac05657932e38874e828f436461d748a40e3053754ffebaac113dd8347e
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8a0ec59d8cf0e119983933f27b336bbbd8041bb3
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f89c7f232c9884e4d59ddbedd732bf589a30651eb0db3ac13c22cff291dedc
+size 199058850
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..932c07a871b7be2ba45e2d8c1ffc33dc305b14ea
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb19d7017493341256b92e5e06d195ff6db90118a14b802776191e21fd5d293c
+size 199058850
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d440107ce7e62c0b95ba9d18151cf53f9350350c
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da3edcdfa3bfa15066b34b42d74185fdac2f5673f69f3f9e35f124ac7ca08e50
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a532810087b3a8a9e3e015bf1fc87f3e1e17e59f
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9107af99f661115adc0942c4025499d2d9e04273aefd08e8adf6f98afdf8adb
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8e93ecf97c7abececf98571a7471fdfdb6dfe0e0
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40123e251968f8b4eaad6b77e8a3d88df03662df60806f61d87a32e6d70b3b75
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..322353c097b2c6d8b84f002b279ada35335ffd04
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a385467bc8c48db04bdb410b5f7aea3f46d7c1911f0042282c690905300b74e6
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0098f9dcee6855b36cba00f0c9f42b0da34696f6
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db0a471cfd6eda025719e64948f59f6706c99ffa7213a9fead6c4545d7d0a4ec
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c268041993a337f9d0a65555eba43d76ca7d97da
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bd607e4d3825f89f51359883b7e3230157d77fa212a7334a982c1ac341c8d68
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f65732ae9f8ddf8395378e700a7a87ee3f47edae
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:340a1c80296e41af67914af452316ba4b9c25221e8784da0af83950b83721a00
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a1bd000873936e8da2e2c4c063d42ab0f7223141
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:964fa74a84763ea1e3f37ddc59fb7381311ad4c4fc8265439798fa2e6c7ee074
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7f944308c1a49f1ca013fc605499efca4a1bba67
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ea956ed89f0534ee88500f678cc3eb66ba3b7b51407d8aa11920eab259f556
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a25d69243f472d1fedcba5f6682bb2a790f90a85
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5379082de2515f2f9832eb128fe63e1b4434be7c6176e3bc894ceaae0f4575fe
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d4611eea3ed1b8eecc49714b11e1d7565c7cddb2
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a13fc32a08651a5f14a671c3b960413fb49d1291247ffaf9d71096bc02b3db74
+size 199058775
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0b07f96eb3b7e64d3196fabea1b4ee43dcb43f96
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd0bcfd3bc2d05ec7bb7ced61f96fa908145f9384a676d20b6dd8a90da4f8883
+size 199058775
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0f4e171e020c50607c0a6d4c8f8b2a601648bc87
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55f7212c15eedd82ae481df0ffc35379c2da5ce7b2d74a5d3390e84e096ec9cf
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ee95b1f9132fb32090fc44a4ff6ea656096a897f
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfdfaed9e7b9c414a9ea16ba402a482864f319197873d8ccb0475f843d5fe97c
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5ba5f35b37219064d24b1017a34ed11eb470d5b2
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f9c6848e912bbdf82e6f8d906e4441ce303f4a5851d20fe319cc8941e50600b
+size 199058850
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a6cb26a685a6315e7cb66dc6fb864221870ad2d3
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c654f2c0a59c97cc33e0c40a196a3a252150a7bdea4808d94419daa545b28d1
+size 199058850
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..597c43471c9c5afb20a3bbd83da450e2d085ddca
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b67b2bb637ed586ac86063c99f4d49ff400121ded608432d9e94d68a4e77518e
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7abd367c52c4dd6c759a8ebee026f5079553fb32
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e940e135b53081e90bc017d7856791df44d7b6c970cfa90dcdbcb79242898150
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4a96f479b13bc449b18247fc21f910fc89bb0ef0
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d888ee971966c88a66de0798d7e8c75fe50979332999158e34adc70d325a6e
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7c2c8a0a50c91abfe641ae2d3eff1b614ff8a169
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb9b044e5444ee8e7164764d91798b8a8dbd13bcfdfdd96df3d1e2ffd0da339
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..12b452d5c708c88bfc978624f816faf0484c320d
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d59b5b3490823c78525d565a86639029fb6413aa18695d511a40ddaefd5e789
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f3b5c44847612a57eef03a9d1b978f3fb4ec3752
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d50789967fe2998584fb8f8db4436fb5acc9e6a81e44b77655f1a2463250b24
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..60c7eba8ac8f39406a30ee2d16149d4ab4380ab1
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60fc20d40c82cdb18ff0f3064086ec58fbb1302aa8eacff94625fab831e45542
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..27522749c1a93d62e114beb209afd9da453e4998
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a73f9208b87199384004654a2a7f8257c377c8eb17d5806f945abfed14ad7eb
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..49f2a1ba79fe5e61d83bf6ab63711753102b2172
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f389b233620b95f8eb1b6a124be11f3bccdd6b6d22287e4607ded569f6b5bf64
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..20cdece4c27be3501a4cb38959725b03958c26bb
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc59515d02566b69fa9184b87998530c57461cf5fc249eda83512255502b4406
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9bd985ffeecaf004a6b280e8b500c0a761af12a0
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86a696c9a5680b283c7bca4e61e248dd8e064c2b6932ec885862629314034031
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3dc8c526dc09fb8ce46a0efbac9c422d293b580f
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a611185602e454009a83ae10c25826c8e98bc14211300da106eebe1d62d88fff
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5ded3e27c93791d9e06896eca94627ca3bcab189
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:870c33f2e7509bfa6a6e12e989c3edd053327c3f959d2ff9ce05c72e4cd5a540
+size 199058914
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bf49f7a7403e8680ec5de5b29050f5142510ff88
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a39046f9774f6877bfbc0031a18c6fdeaeb0001e216ee38391628af189932fd8
+size 199058914
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a626f7e8f3f8858ef28aba2a02a1190b3b2e6522
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b9a4ee7d1174486078ff05f9332ae0cf66eece3bbcbc52248b2f9afb7130e8
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..94f332b37fdc75c79ca38a217f5d37cc298b45ea
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e348bfd37d1d34943396fe0d41141f0ca7e05a5ee4736bb3206b585ebd3f3c38
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a344c3a2f69483733ee4f110b6daebd10b39d2da
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e7e961684214dd1eb710ef2766025ef37cfaa8a2f11bf86776a6e9b4a8afe7a
+size 199058711
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c4b8171f06b32bd61d6d7aa663e15709f51f4b1f
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bdd187902fb74195ce843534674aa7d72543b7756719ecdae56b370fce1573d
+size 199058711
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..910e1fa57f78cf4f73d38a525d3e174f762eb280
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6fa10e9a38d953cb8f8f7dd3635ee0ee68cf5cec79c635d1a169ae94b695c5a
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..642105b738893f990b1c5667fefc5c6a9964d696
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad97f3c9a41fcb24b5534a00a76dda12d2d50ad94d39ffd60eaa56f9b52bafdf
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f8dd109d35318c9a97ec6014da1ab8819725fa89
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d46109b6324b857ad057c418e98b5eb331dfcb023927b951c491f1e6f7200188
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..02b64baa3673b355906a190461b6ab7ee9160204
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2dcbdeee405a99e269ebcff425f75b7d7cb81a1525797b5547c402db0a778df
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c84cf6deba88cff87cc6f464b4d6e5994f1b5c8b
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfc70c80a1fbcb50a3e824f4853bc8454456a261cf6b8b30a09c5443d5ad3559
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6963c767a9c5676ca4fe2fba5573900502bbbcbe
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aef1cff6e51ca280e28cd087a803a3d02ca4390de194361d1044113577d9ae2
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..86f2cad052b9aa599224d9d854cbead0dc657e0a
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cb3166ee0d6637602fabf7f03285a2d848a51ef14ff29dba8137d6aa3e5e1fa
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d862d3ace31f58e8a31cc86a957e98b4b751200c
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95fc79f0176bf3bd1e84b2345bbd30cda45007b8fb5bf397a6a9dd698d15cc14
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5b48dbeac825e32e25dc3754c1409cae1cb2bad4
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f09acdfcbf696045df0cfbbbba728aba0743f4294e3851c5f4403b81e9ae46c
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..eff4d0ed7311ddacaef4e9a9d9aecf358d374a90
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ab787efefabbaf9cd4149afdcc1e454d7c0792d79d1a8fa1437aaea10d3d97b
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2c4a0f0c01fe6c0766b2a93aa9c19c7a2d75a3cf
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f660a149e82a0f7d7107e68a09fc4a8781eb83c18c0677fa9c42d6a2031bc17
+size 199058850
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..759ef4dccb327101309c68ca8dd7bcd16caf42a0
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e50d4b42f060d078340eed9cf00f0378d1a170b646518dfb6a26324ef454fe2
+size 199058850
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9a93f64c104e78588d1fe4d60ebe81145446bc81
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:855802c35d6787b4f9ca090d45dcd32779c59971604bc3857655e5df6476d32d
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8023b006a701672d883d6d5058d93cf6cbc2514f
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2e3efbe56a35ef78d859d97afb1dd0ed49b7c3ceac4cdbf267b49b1db7ab0d2
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..77ccc81b5fb576b394bb01e7aa095226458e9679
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:991c9c32f167fabf0a3469bad9dbbc760591e77897b1d959db29df8a83e13a82
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8ab397ecfaf25000e658018ecadab8689d1c65b1
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b77b143e62d0a5233b6e8917b1fb30c413d98d143ffc1852e5f401e3ed8989c9
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7d21f1ba4d9785de5d7c410eb55d0310e43a640b
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bdf3d1c07f1070a5fdf849dcba0984981ec0a7d4adedce7f71f0f1b6cd94ef7
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0e8ad2eeee17d81c8ece8a2bb7d8614949967afd
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:654c19d645db556cf72bc5f22fc438b3a36d3605e3a081eadd1cb100ce5c98cb
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e63a3b4d52cb6f9bdddeb9cffdbb2681c6518038
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:448343e48815b0e59cb0a9aaf265e4f44ab7f4a21a7b813d27a67b3dba8cabe6
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..949aec708ad37a5ef941d976f51054317a624506
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e1f3107d9b668037ee04eaeae481f485f4d2dfcbf37412f7c55cbc1dde5adaf
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..31e98e8c8498e5f2323a35824656f870538952c4
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a2bdb385a9318a09a62ae29877ad18b7422369bc018b33bc5f822e9b28b8ce
+size 199058647
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..69f507e66ed16e4ec6f80108224ca0306b93884b
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e52f8fb6b70855bc025113d7ba8be35445b2667b99ee371ad8ff16411a29fc
+size 199058647
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cea3e8279455db3a1d9aebbdbd0b09b6dd74cbef
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34666f39d8a6e507ac6f4d271f272d4389e7e5449775aa3a3d74f4c8fd4719f1
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..af166084a2f21e31ce29a94762c10cb9db7af78e
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:009b735c64a38520526f6986bacdecd08454c11ff383eaa21875e5f403d7ae82
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f0246b785e97c9ed40381831aaf3b1fb7124340a
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbd8b71e74746c095a318d9d239a6e1404ebda817502ee1bd00c69b6e331524b
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7fca6b43b5248f58bb975cbff8b18021a5a8072e
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f15dc7e4ff1598229618808fc93393f4b12477a18deb0b9f1294e46889cde7b5
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e5e13a2403e9b91e119345e14310c6ad3be955a9
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ee6d3a032c167c8c23366aabeed15a249fd0c3a3abac9b98e29473b17cfa1a0
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..479aa095a54729a59b540a0e1a15908b52e6d8db
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ccc2ce9e5fb6539ef296aa8e7db4fc48dbcb29a8cc894238383eacec46bda11
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f11d34484a7c6602247a89fa9170eba4666013fe
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b5def349990a588a64bb9aceb8440905626b0d636253c9af097951a6997f402
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ec0a1a0dfb88c1b8b700fba23b6d271e77848c78
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35e127650b9f6d0618d3a37ad90a7f951f3794544ed4b29fef1eafc4a6dddbb1
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..672ef8372f781e606b18b83c2e187373eba47d28
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f23aae1be9d5db34a52b460679393a50a8c8f047f87f149294fa2572ba7eb2d
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ee0321bf29b5b45e8c48be50976951615bb9e10d
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c41d60d6d6e6f8b10eae1681088f5e69eaf2145e7b3b86bdea76a289f0843a
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b6de7972d3d41d70d98a08345b7ae7768755f7e7
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97b67b3bc65f50e79d20bc4d733ac40e9d26737d0be9a61a673338ec0ee85a5c
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..47ff2c02c909a591390dd5112dd6842cb06c5a91
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:339122e663036107b6626fc8ddebe370dd8d7881c72ceb4ff679e67528c2e3f5
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..92485d5ae9680de3b608fbfa38597b0ebac12453
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec727eaf3067c002c5eced22bda0e3da60dfedc6f9e86760b94ede046db53800
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c8310ebe8584a8e8e5613f07348ea3e525b9b343
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:167f60160c2dacc078fd45ee4b35a47455299b2b77c9d89af0fb29b98235b498
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e85fc8021f78ad507b1fffa6f6406f70ec95ff12
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:715094eb5ec534c827c4dacc2d8e6ea5f8f96b1ccca5c9fc33f0a976851c65ba
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ddd26e3f447f99bc9d05c2e25817eb279bd7f5a2
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4b12ec503ad1bb21f12954a077a83ff5c95c9440eed9ae9b9cb2fd92eee7062
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..54df40e00e2730c878efbde1cc6edb167b42e7d4
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b340679271787f7b5c6543b39ca8f8f426f68675a79c67f6634274bdd9397c30
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b03403d55f66cb4610df4667eb5ce15b75582a80
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1ee25dfa4c457b73919c998c9332f89884a0621fd3ec005c58607242546273
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a65dfd5f4a4e1f17ac9ea47161088c793c0dc8ee
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f61d7091173b75b6dbf1a527ab9708e3da33e955a55d55e86ffb06cd7e8d8ee1
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ea7504f53f0a3092629ba7deac24093355957b87
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b8c2618c6541e3be008814d24edd98d69ad3fabed491d5565409388b3000f53
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d46fb47e22a94fe9b2f80aaa48bfb65150cfd796
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c64bb96dc6d332b6547258c07f22e586e62b66bb9bb33bd755cf55057f30f130
+size 199058647
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..78ce732631a4006790b08c1993327389d2b26c7e
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ad54fe521ecd5fce1a4f99f0b174ee265635eff45faa77bc3f30a7c66b7ec79
+size 199058647
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..76b7312787030c31c81a74b694d8912cabe60f7b
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1fefea45262775079195fcfa16e71b7f1686ec10336737203d86668d7fdf24b
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8d7b2bc3afc3036e93677f56753a7397a93ad139
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cb04113aac4fb0f9a5774cceb9cf9392165ffb187360f39908e848b1a6c2811
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..deab65c2b8409acc39b591233dfdf6e0b4bc405f
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad2f92e9e478e468085d1966a4460a106451f7bfc04ea8dfc9887538c7e8b7b
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..17e074f0e9de7b4c88a93b6ccd8419131c3d01e9
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c75120f420dbb301f2117fdf1cdf3ee0f67aee53feb4270d434ad7263fe9b19a
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..eecf281b1c3f02f444d701bd5f242929070ca222
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f389237d0b4bda77ea6d9f277e085a6e0180ac06424ac5ee7bfb11a6346fcac
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8aff89f8e519cda18cdb11fc57f3bfc995f15ee0
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:739df1220b23dc8d11673a1221daca978b80133920fa9d18d4679bcdab11c7d7
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..43c7ef57e69abf9186ee122b7a53100b5488d375
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2badbaea61630a8acb1f80a9f625fcfed6c50cbbf5f8186cf5002bf55458d175
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6c8b0c4b342c9946e78c67af1ed61efc6588f362
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67b6b5c848192d3e7b104913fa999fcf79bb4ce03a183a0f75e157d09183f2ae
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..95d0e1637cb96781ab387be249d81581ddb0e861
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2db8c9109f514299eb99f785164114f2101f3cd4092e6b0cb08404e897a28de
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a0fa889a4ea65aa4231b3c5e10221d78993196cb
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1ce0b6d093b6172bbc1428f634a350107db71a8895635b96a097ccaf52c7a5d
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d8c899f29225e6ff109811c5f539e034daaec8d9
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc712cc0026a3d319b7b2ff8059bde93c5909cbab237267a1b485ef219897f8f
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e60eace9d2929ddb0747095cf08698de96ba79f1
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2894664c2dae38e301679d3202faeb291c0e6c56a0261b9a4a4882a1651266ca
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a4211643c0a0c5a9f344894a99816181b3ef6e5b
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f3f9b5e62f813fbd8223675edd4bf0e2a69f1a9c7324b0b66aa328056a59de5
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d07c252cc65f815715b5c57f2a8a9ccdfbedaaed
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f4d76b6cabbd376dd11260b40f1178eb4af491e3c0f58e2482e0e2add617dcf
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..313451013e404492caf176b73c1114f2adc2e8b0
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf55a80c6f653bdcc61145b021381a614ad2b10045605ab7751698e58674252
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2245ed4860fe377663941abfc0e66c09dc696cf2
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69bd3816165511c7c9f92f1121ab0545ad4908ea2fbda2dd51251f60941a72e1
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7eef8104271bfbd8b7c399dd0373492714b7512b
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40cfb484475898a5bd49cc1aaf5deaee7b7ff1ddc95488d69bdb1cfbcfae2aca
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8cc0ad13d0d48fbd72cef9aca57509d12b8e139a
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8de51e89a4ed35b34a536c42bf05736a5d875520da9f9be20d641ac2c5903ca8
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fbb349cd06f0d0ccfaad3a3ace494e38ab6445f5
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0996d6c7e783b6f66db8daa4d70817835efa89f365d1feba1ee9395e2a002f9a
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0ccbd1eb8b9e8cbefcea016e329000564f35cb7d
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a14b31e12e452e5a3c7a04c132b2f25c238150af92d40ca980afd75e983d039
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..17180d3f9785608d0bfa971c0bc19dd674f39505
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f530aed7ddb0232e2581125443854e89a93ac76825e370ade302907ede0d1159
+size 199058647
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..38ac44ea4097ad7def740b2e9edca3bff7b1c478
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3e3c46f72db80bc6a396b75373ff2ca632005d3091343c8d97829c0f372d55d
+size 199058647
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..32cec033651a45c8fe1833f96d0fedf2bc43ccd2
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7abb36f74ee1587624662695a26b2a961a18cb85861c575e699e970d2a7fafe3
+size 199058850
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..09c24b9f186620c49e8380ae246a5d3757b58a2f
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2927b85aaeef3ed1f3aa62cac85a04c534c126cfaff479a1fcddfb7b3a21664b
+size 199058850
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a37f3e82c37e1b22e94d72e156ae6fef78b1ce0e
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:492128cd5c0c6db5521fde520f0c9255aa60aabc01e1aa938d2cdddf6e421efe
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4bdb8262827712a95ceeb893427fb31b87bb45da
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbef4ad544130c46e94bf7d57c70aadeddf1453ed0264de11f5a32cf57381446
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bee38f153c451c7c878732f2bca33d3259190655
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46724aef8908d5db7992d172865aa87411d1c08c1de39ce1ed088f54ff64daad
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4990ff21d759545f6fb5e7dfc26d1bcde92fc8d5
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f474b9ef368c1c2c6695652ce7a656b1f9acd7cada141f0a78dc3a912d9dd6bb
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4ba17076c178b21f1ac6b3ca5b1a726592b462eb
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1678365575925d970246d7150ecad80b57bb6121c649163de55a78ceb9ad9054
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fc1555937f24c2b4fd653b1f2023b6f34d6ff4c0
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86303585f7d25b9eb82440f3250bb7b85fdbef74803dd50c82d84c7da535fdc1
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4870679ed2638de390513cbec475b17ae65aa648
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a7ea1f97b0f981cd3a5d3cfbba23bbe1b7800cb0d8152c4e30eda2eb7c035e4
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3b03ae4f0cb40c1ef9665c4ba0db59c656de75c9
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6707cd3d65731afebbe8bf8e6b4e81c6b18ab2ccd081f14ebd04130f627a953f
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bf7d646513f7c390618e2e01fa5d24417dbdca3a
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecbfc342398eabbc6a8448612b680c359e770e18faea6bd7bf6072744288bf28
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8c7462a564c2399daa2f5f186ba0d08f9d60e26a
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8455f12c72c058be16d6f892c3a9721039d1ab5e1b4ad2aa05120307552de7f9
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6ef539bf062db6d4a73bfdbd34e2325be660310d
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e06596ac5c2cafb7cc830fff693ad6f0b494df64e619a7ac1b650cf96ea58092
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e3cc38a2286eae180f3776fe5afd301d6bc31ace
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b5ae4f27650931e95c9762a43a498ecbddf976ca95a7b57802f42dbc43ea476
+size 199058722
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b5f31316c9304e3e96610f28aa016bcb76303727
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53fad531275fa91935e53bafcce9d3ca2c0e803f7da2b34f659c474b92cc8690
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1aad81490a05b0e72329189a8e46b71bdf029cf8
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54c8873164b915bbd48562ab2d651de7747ff57da48ff22f67bd23ad99a3781c
+size 199058786
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0bdbd3ad3bcca5df6876517e6ded263ede804cda
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf24dead02611789c6c11ca5f71ba11f32c95db46ed15f7fe3520ac0a8c11642
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5f20631b3d49c7e46a6517e03dd138a63495eaca
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02d55f27b4d779a061edefebc106f5f01b3d041c8cd85cd1871b120b81ba8ece
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..836fc1650fa00894d23b570138b07991c2e2ebc3
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60694635f645902c0f31238176b8849437642aafa133faba3ea95c681262783a
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d667a37863d6507098cc4b48a8ade495f9df4046
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e720d2ae71e083f77c64413689f84b6f859083de07c280f0f9856c725e13ead
+size 199058658
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..50fb1ef74ce1348cb04c4f145a28ce182f64cae7
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f5bd39d2cecc81c0929d71be1c2eb58650409e4d9c1295ef3011209a05860cd
+size 199058839
diff --git a/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ad8e809282a6da47c30bda160bf46f18636b9474
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e2c3286bd1ff8aaf2a2e53a9b2533952953d32e6c1bfb9b95c47ba38c4cc27
+size 199058839
diff --git a/4b284b84b20c4py/global_step80108/layer_01-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_01-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d18841fe39cce64ed47e4a81078927796038299b
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_01-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a847d67e161f194952599904df2b9f6102a14086c13cbe5a392de32fbf659b9
+size 167511299
diff --git a/4b284b84b20c4py/global_step80108/layer_01-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_01-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6dabf2ab5f536c19d37808b8274c445551137b89
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_01-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e21bc63973f9e1c02087b17fec24f4cea8b6d7333bcb53250b448b47fae94b91
+size 167511299
diff --git a/4b284b84b20c4py/global_step80108/layer_03-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_03-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0091c92634f845cd2fda2b47ea74c11ed79d7dab
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_03-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3548d07526b750371a29bc629f38ede1a73cba2e93e4a5e0e599b04d015177a7
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_03-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_03-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..64312542a148d53e87fb298b46245aeaae9b32a1
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_03-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0322af42dc3e8629043c43626c58b9f4c80d2e242c934f6ffe9906ae1723a37e
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_04-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_04-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..977952a1e2fbeba383b5ba254d83d5b3b42e90ea
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_04-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cf6eef755c4f8e7df2680998d3d5796247788b4d326ded0d0f4db3878f3bf10
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_04-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_04-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9a5fbc918c44e6b42d84b6b03b8b23bbd61d0e69
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_04-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7e24cfc547248fc5249d8b78798efd6cf0bd9cd957fa88c4cad1850524f9582
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_05-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_05-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..07077b9edfd1e46f52f76221a3258c88636fbe3d
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_05-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:927bcae75cec843a3cc85a65751be8e35f08f042f4a72433302b292dd04914f4
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_05-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_05-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..60832b439ecb0ee63491ce64d8665c75094d99a5
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_05-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2258af327e54dac0d05a69148acefa318cb641b8ec932155429f712c53dff45
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_06-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_06-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1eb5130a85461d0f006bd0c0ea5d82e6fd7311bd
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_06-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:083f151bed1af47af5a8122416cf3a2c664c741811319f58efeab87f9245dc0f
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_06-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_06-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1a1c9da9ef6b0a136cfa8a11516dc24905d856e9
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_06-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09a32dcba56c6c20dd195708a7967e5d6d2f66c7784b24777d162261b081c47d
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_07-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_07-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..536c417c2bd7616bf33cdfe729abb449486469b4
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_07-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a7efcd4d0c8ee317163ae13236470df875572d564a64932aef677050dd4ae4e
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_07-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_07-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9d03a299b593a5422cdfa32eb117ba4754b5b2d4
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_07-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9611a4ccd568a2cf313ab9d95d13e039c133f91013a177052ee7c28bc35b3093
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_08-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_08-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a0b735cb0ae3ef995f1fdece6bdf4e526871833c
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_08-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a5a52f2f289455346074c32fba89c5eed05638c200118af13abb4d29bc2538
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_08-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_08-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1520caf7228bee4360b5d1f2a16230028451336a
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_08-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede99e6869666ac5fcc9fd381794aa81e379e717817c60c879ef0d1f17f9728d
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_09-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_09-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..81e9437b1d7f23223668384f6b4def8cdf4abcee
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_09-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:845af8aea702297ecce373500175ef942097b4767b0a2114d81552c0c4048ac3
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_09-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_09-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5ecc44fc9e317f2dc6ac6289fb8cbedc46495b26
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_09-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40b1fce51a1bdb0450d47dab313cf031c500720ebf6cd68c1a8058e18278da0f
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_10-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_10-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..012da9ddcb3c11eb8dfb1959e7a279c36cfeee31
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_10-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8a85a985ad3ffbc28818952eb290b1c13e8fcad90109ec4fb719d7c27eb080e
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_10-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_10-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e092547bfd947ecfafbb9817a6ed21c877f83501
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_10-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08c27459e5eaee4e5effa6729810b96befc8eeb053a2b2fe39763552ba0f7400
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_11-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_11-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bbfdcc2f4beca287a68af0b9be514bf81a77d84a
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_11-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a24fd097c226e65a0f2dba475b8d42d2674940590ccd10a0ae3bade66b02129
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_11-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_11-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..176fe607b9fab4d9c89f3e9376609f1590940ebd
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_11-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d23dce579f9a49b8791dd458c2885b262475e4afc9ef0ca09e3b76489038efe9
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_12-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_12-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..60676b047a89ca02888db4d7ff59de8c746532e5
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_12-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1867a01bcafef50da54bd2f980c9cc72f0c42cf58ee4887bae9146d876961650
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_12-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_12-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c23dda82dcede2e038809a5ad9a594933ff4614b
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_12-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a68f39424de8078aedd8162b152f007b0495fe748f0e1401f81b584dc681fe92
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_13-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_13-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7d5b912836c2aa5505401b7bfcc997b32851cc52
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_13-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20eb4e66f54f8f077ed160c03de81c7d2a02601b7b7e1500b2f9c9de3a195e53
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_13-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_13-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..90e1d9c74d80dca8c1e5bdc7ab6b73ab586a980b
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_13-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78343331c00212f72cc94cfbf31567a7d7c410da1d8e2e7b75a2daa8164864c5
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_14-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_14-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..04b4f28dc5a7c646c74094beb2b967cf55e3997c
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_14-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2288a2aadc60063394183c728a03b3d486f8968606a09f8fe83153acf0ba4e
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_14-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_14-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..693d6e4858c61cd399a4186bc0f08e0918332788
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_14-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8624efbb2bcc9b73491c679d43a395d6b1d20239668188f34f8936e6ae41a96
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_15-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_15-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..79d7e3d75565652133dc0eeb8881fe5ff11a9972
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_15-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8ad2c3af0729be97906d96726dc8504244994e4aea7e025809279739b703863
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_15-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_15-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..36b890ba6900a03536539f0cf1f3405e8a58f052
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_15-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59cdd292d95009c83aaa50a7ec62ad6e87646db9110b6d24972db8b076d7c035
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_16-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_16-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0734afeffc7de0e64391c979d60a78ee9f3df2e6
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_16-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1668f1a562546ae4f39a9f138a85c7076535f6f14f0244f0dadeaaa8d5f4358f
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_16-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_16-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2c7e0e7e8188385a99ff864e4ed546479acfbdf1
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_16-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b85e8e2c47d952157a6877c425d98e3e946d9e13f79eb925795c6ba6096f4a71
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_17-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_17-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0440ed75578002fd7bb7858ae3fcac8d4a47b8fb
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_17-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:932f1af9feab85022f353bbaa2bd3bbae77a44151b874f84bc013a88133e9199
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_17-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_17-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..094e32117d419047bf07824713539babcdb917a3
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_17-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a255468c2117790dc91aaf6d5668001aae36613bfbe03a3b2b044875f316fd24
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_18-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_18-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ad7de61e58e112907c917f9497aa2388795837ca
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_18-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dff7fddebb238b70c4f8a579d7c1a8d687c60475d7fe1fa751a2e82fcbb21642
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_18-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_18-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7b16be611af61d80dc395c814120752c15da4c8d
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_18-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed37778add93532b7fb0c01d8d829adbf719422f8328b22bb64ee293b189257
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_19-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_19-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..029f99a1a1a18e9438ea110cce38ace249f21d42
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_19-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:258a9eec400fb0ee2b9703ba74f9561dad5e267cfea7c8bd574f4d44166a1d8a
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_19-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_19-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e93bca0a735ff5456a425dc03f10c41c0dc92e4e
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_19-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48757733937038c7a4e2df6d864d4a9a06b65f1095ab386297c24e4876d64b0
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_20-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_20-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a9caffe81baae54b2bdad3eaaf213145bbec02ca
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_20-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:928dca7167dcb86a7ca9da1aa93844f0b54da6292dc1b44c561376a2c8e26d39
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_20-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_20-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..13d35e8faa81eee16fb11ebe9f8c9801b3700aa4
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_20-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df5a57bf0ed8cd56d824a943926240d6d758e981692beddda4e894945397ccbe
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_21-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_21-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7e011bb33ec4e9ee2099375f4ecb35663d513141
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_21-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db1df7872bb62181719f533c6cd8523d7ab4d12d95211228574e495c3b71e4e
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_21-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_21-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e03bebba73213e24c0996f31a316586b3f5502e0
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_21-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:174f1707ceee4a8c2472036f299739f9a8168106b4caf9a9a0c5998ba511adc8
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_22-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_22-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1fedea6fcfb8f4ffcb3e1400ee8cd24e288eb4df
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_22-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f640107cfd8f02bd0a750f70bb3d766ef84469439eef7d818147192229c2e12
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_22-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_22-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6f0589e05c35683592963d10b9a19cd993885449
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_22-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:284ad7849cc462c4d6f4912affbe443f731cbe6ce3627efea7e539bd9ffeb745
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_23-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_23-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9dcd90bcbc18fac894edc3a02e57e62f7f138846
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_23-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d060ab2beaac05292c6fdd2d8ec30694dd5d51a5d49dff4396067af56b93929
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_23-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_23-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..76050816fe30df060eb370a9f4d9d4352b17192e
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_23-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988f31773b9b51639de9a5fed59b1432539b565272ea12bf5150d6f45b12e403
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_24-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_24-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8dbecec90627bae43905c7a3dc467fd970774b18
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_24-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a29d688e202c06749e7642e78802608cb50c6b982c1b65f1789a474967a2d7
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_24-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_24-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fd8f100a279c34d3e2f006c82e907ab67b025f72
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_24-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:378cb662ee6436a3002c06b492324727c0f14d423cd1ca70c5bbbcde3f46f385
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_25-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_25-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7a3b36025afd4b10054323cd0a756f63813d49c7
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_25-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53b793d3bcd70a16dcca9141e29f91807ade6d9c8976118e9a1545339f54fd24
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_25-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_25-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..853913f5cca93e929061a1e652a991b2ed45ff74
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_25-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19d5e77c99b054592d26fe935b705c28a06e1ee1e88b3fed9515e39f6ec06a15
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_26-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_26-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c95340a20fe5bd0392996895710db0880da452df
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_26-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21ca44a82da2bcd9008d898c9bb03c9be16d075eee67b312335c9d9c094d50af
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_26-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_26-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..70ee9fe5989f95718b755bbc7fc670910654c101
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_26-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a7af49eefd6034d48a0d975e8c47c57bfd7a8ecfa1b4367570efe20b761c07d
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_27-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_27-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..98e7417e32b353d98587f6fce5e69cfc0ad55aee
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_27-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:552d6354182d5cf5a0fa121c227c40ede212b9e35d0c51b8303e6748cef9bbf0
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_27-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_27-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1127e5e61a4bd442ca2be8ce3d16c7434780cd80
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_27-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91a8f38d683134da71ff80129ba1ebe1bd0bd8862f07590b73ea17c4f53e5865
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_28-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_28-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2516f8ef63078547b399244e85fdba44e66d37c8
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_28-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1b0cc92118add63818a025d98f117b20fec3de83c70c0a6a7346ac56eff4d39
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_28-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_28-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c274c103ebc4b556b9e0b12e866fa9baa13ca35d
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_28-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:530174a31737bbf312e5a2a984d4b4b16cfd2901ccd9130edfd817d7e7dc4a12
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_29-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_29-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2a634b7151316aed16b5332e92f063a8a5337ff7
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_29-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56d2a2924ea2eae0fbb3463c670efeb32c3731f58bda8b02993fe72f509f24bb
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_29-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_29-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8e52aa6102c1cff78e9b49103b317439c76f3302
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_29-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:753f9190987f546c345f1d8755e824cde78a192f80edefc04acbe49b26365a45
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_30-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_30-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..65553b8ad0dea855ea9d1f494e7011fc5ed999e0
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_30-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2211a7f4e236809c1e8c5938cf47a793b79056074a1c09f440a2d7c395a166b
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_30-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_30-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4486a4c3313156e8e10c7ccf15d655c84fcdec02
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_30-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80ed5ac3cb4930e502cb17d20ed0932890f15ffd91eb5eb3d271476a910dd2ef
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_31-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_31-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..051e15e6d80487d657a4cce0dc1d0e20072686b7
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_31-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf6c24d8ac0db2ef1b0d9574ade52f432459148fd51780860088b286e2454fcc
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_31-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_31-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..98c357dfb9f61e07e23187babb3356b3cc64d7c0
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_31-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e98a703d13e10c3c31804933f59b228e964c663ee66abe4799178a5e0c076db0
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_32-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_32-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..69ead9bb86c47e9ad26f412fe6b0c8c40c8d9a39
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_32-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c67559ae849073e4a34b2e8e9eb433c2c3b323aa0a38f2c405a7b03001e3a30a
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_32-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_32-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..dd9e09049ae7656817e8c0808cbef7c9f2768096
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_32-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bcd4744aeacfb873969ca8dc247a02679787fa2eb8e8d6df0e7c95039694286
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_33-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_33-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7a81a6c5a49aaf13aaeaa3e188bfc16d94ea6cfe
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_33-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5078e5dde7002b80e4c2d9804cdcd203f6735cfd6403e5106e7d62a10c0bbc4
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_33-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_33-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..389a9fa99703ef6dfc04c6bd7d6e2cae7def9a63
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_33-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2490d5eacd755cfa96b7155932865b30061c8f92e60d4c1dee6a08b65dcc8c30
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_34-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_34-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..931879bd700868443745f89d400b65a644f82bd9
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_34-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74c1d7c6af899d9ddc983071b05e26ad35fed391741ca1b9ca4cf8fe4c3bf6b
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_34-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_34-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d03eacead7a61af7af64dd6d142aa63a40fd3101
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_34-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab7f6366643c9e2e0cf7b763e2780111944633e2999ddc8d2ea1c89b719d0867
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_35-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_35-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..84df52686f711637b31e554d677075607fb78652
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_35-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b9ee2873b74c3497ba1e978255fb4522d8d2ca83706367916982d4819a3962f
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_35-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_35-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a330959976f940d36efd10f953c4a648bb10ebe7
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_35-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:352de0621dd8bd844dc999fe4a1c6287fc73bdcad29589a12154a2da83e1863b
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_36-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_36-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..46e580d4ce8d8b10f48af4815d511b4e27a37747
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_36-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:853706c553d14a1cf3f3af88a9538b695b389dbdf51da5d673643522d981f0dd
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_36-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_36-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e1bb8726fdc0fa38c7094c969099b01fa8541ace
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_36-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20fec5e801ac15bb4a346b5b5fefaf8e7914cb7ea12e03b9984cca5bbc4e7302
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_37-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_37-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..af15af08f9d930a3ea0eb2f82121d267c2c89845
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_37-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f13611c5b83f520eeab78fcb346867809050d82a034a04a7b4ec76518662640e
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_37-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_37-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f76a0eb2d6ce5a8748b5f220da2dba26f6a5b38d
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_37-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:152ccfe286a39578d4a8c54326744c3ce4c32344d3c3cf1fdc3da1d5ecdafed4
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_38-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_38-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d767146f56e4cb7eda5daf11843eb108bd9744d7
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_38-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab4b39313535b00703105a4afa6b1e40b85bdd8961cd5aaa7a466df03d447c52
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_38-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_38-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e4cdda4c0f9d961c7255445b8bee8f25ab6ed113
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_38-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c179267062cd2dd16bd7e8c9f4c0529c9feeb4a9d7fc8bd0a430de0d7be2b03
+size 113308931
diff --git a/4b284b84b20c4py/global_step80108/layer_40-model_00-model_states.pt b/4b284b84b20c4py/global_step80108/layer_40-model_00-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9cc32e8515f75ff855f860c4d8bf0fcc8b0c0726
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_40-model_00-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0232695eaf8f87c445927f8c0c876035f7d4623c3a6f00da4b2c850b40899eb0
+size 13507
diff --git a/4b284b84b20c4py/global_step80108/layer_40-model_01-model_states.pt b/4b284b84b20c4py/global_step80108/layer_40-model_01-model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ad3f574b5228cba0b8bd5543d27233a683d4cdfc
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/layer_40-model_01-model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:119e823fd5cec9d3f6d432b439282fd4cb631fa9e8c2ca63485e8b28ed3432fe
+size 13507
diff --git a/4b284b84b20c4py/global_step80108/mp_rank_00_model_states.pt b/4b284b84b20c4py/global_step80108/mp_rank_00_model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1c5c1f833d48eda82d184ab58894e476b17423a2
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/mp_rank_00_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a557df9727a829e4321318f110db9fdd41793f98565b61a33280f7a490dfd14
+size 51827
diff --git a/4b284b84b20c4py/global_step80108/mp_rank_01_model_states.pt b/4b284b84b20c4py/global_step80108/mp_rank_01_model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2ab519809a3cd406ae67fded5c2b51e1b700e1b8
--- /dev/null
+++ b/4b284b84b20c4py/global_step80108/mp_rank_01_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:251ec8c13ff265f84833edb292af62d69018f779b5d0ab19368bc18266a14d0e
+size 51827
diff --git a/4b284b84b20c4py/transformers/config.json b/4b284b84b20c4py/transformers/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..df814c3a71ee49044410636b5eeb4f43611690ba
--- /dev/null
+++ b/4b284b84b20c4py/transformers/config.json
@@ -0,0 +1 @@
+{"vocab_size": 50432, "n_positions": 2048, "n_embd": 3072, "n_layer": 36, "n_head": 24, "n_inner": 12288, "activation_function": "gelu", "resid_pdrop": 0.1, "embd_pdrop": 0.1, "attn_pdrop": 0.1, "layer_norm_epsilon": 1e-05, "initializer_range": 0.02, "summary_type": "cls_index", "summary_use_proj": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "scale_attn_weights": true, "use_cache": true, "scale_attn_by_inverse_layer_idx": false, "reorder_and_upcast_attn": false, "bos_token_id": 50256, "eos_token_id": 50256, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "chunk_size_feed_forward": 0, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": ["GPT2LMHeadModel"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "pad_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "transformers_version": "4.25.0.dev0", "n_ctx": 1024, "gradient_checkpointing": false, "model_type": "gpt2"}
\ No newline at end of file
diff --git a/4b284b84b20c4py/transformers/pytorch_model.bin b/4b284b84b20c4py/transformers/pytorch_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..610be2960fadfc4095657aadd340b5d309d24f47
--- /dev/null
+++ b/4b284b84b20c4py/transformers/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06594533ebdbdb251028ff58d96e5bbb0b9502db0f74eb80f649ab3fd6555547
+size 8781203669
diff --git a/4b284b84b20c4py/transformers/tokenizer.json b/4b284b84b20c4py/transformers/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..0e99b0c1456fad7cbb09e6545c77cd19dc04f25e
--- /dev/null
+++ b/4b284b84b20c4py/transformers/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8414cab924d8b9b33013f0d221c5862f365ee9be39c5c2bfae8a5a9e970478a6
+size 1355256
diff --git a/4b284b84b20c4py/transformers/vocab.json b/4b284b84b20c4py/transformers/vocab.json
new file mode 100644
index 0000000000000000000000000000000000000000..27c8a6dc955d9c5dd9d6fe5afb9a3d2d17865485
--- /dev/null
+++ b/4b284b84b20c4py/transformers/vocab.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:196139668be63f3b5d6574427317ae82f612a97c5d1cdaf36ed2256dbf636783
+size 1042301