Training in progress, epoch 1

logs/events.out.tfevents.1709445144.49ae8f4e8e7b.1647.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ccf3c3df004d7109733f8d8a5930298f24ca6f30c810aa07ff3d746980ff300
-size 5714
+oid sha256:2844c97e236f9bd45eb2514384cec96d7b4f418f3f18fabca0feca4e7f708ca9
+size 9806

logs/events.out.tfevents.1709446975.49ae8f4e8e7b.1647.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9b0b460172aac58ca10098a051eaf5c937d0ab5cf6675f6c8c6ded80d7e4ab1
+size 5180

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80f844ee9967441b288ef24fa1167260a7fb93ad526dacb0671a7c4b4ca13fed
+oid sha256:d86de785f326de5dff3e11e88c4aab157dd2b03e1e78e06e6e4af1771b96592e
 size 17549312

run-3/checkpoint-4216/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-3/checkpoint-4216/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6e0986c6211999fa326cc83f9a6272e2e829dd90c196d020f008eae521ddb24
+size 17549312

run-3/checkpoint-4216/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6e5f141ce51ee52566d7c10bcdc7d8d8cd76e5c725e1ced625f73df40151e0a
+size 35123898

run-3/checkpoint-4216/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a2719006b61f28d7e37d68afe179a1c4b2eedc673365947492e106cb79f976c
+size 14308

run-3/checkpoint-4216/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf04b24c61faa898e2f395c5d2a190405d789e3f56f0389c35e9fd21cfab436d
+size 1064

run-3/checkpoint-4216/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-4216/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-4216/trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": 0.8245412844036697,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-4216",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 4216,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.104732990264893,
+      "learning_rate": 2.9453688815098063e-05,
+      "loss": 1.6038,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7752293577981652,
+      "eval_loss": 1.2298829555511475,
+      "eval_runtime": 2.8117,
+      "eval_samples_per_second": 310.129,
+      "eval_steps_per_second": 2.49,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": Infinity,
+      "learning_rate": 2.5778963882284596e-05,
+      "loss": 1.0293,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8084862385321101,
+      "eval_loss": 1.0575315952301025,
+      "eval_runtime": 2.8112,
+      "eval_samples_per_second": 310.184,
+      "eval_steps_per_second": 2.49,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 26.63373565673828,
+      "learning_rate": 2.209725278039734e-05,
+      "loss": 0.814,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8004587155963303,
+      "eval_loss": 1.0314538478851318,
+      "eval_runtime": 2.813,
+      "eval_samples_per_second": 309.985,
+      "eval_steps_per_second": 2.488,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 14.250652313232422,
+      "learning_rate": 1.841554167851008e-05,
+      "loss": 0.6947,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8165137614678899,
+      "eval_loss": 0.9996209740638733,
+      "eval_runtime": 2.826,
+      "eval_samples_per_second": 308.569,
+      "eval_steps_per_second": 2.477,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 9.728443145751953,
+      "learning_rate": 1.4733830576622822e-05,
+      "loss": 0.6281,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8188073394495413,
+      "eval_loss": 0.9810827374458313,
+      "eval_runtime": 2.8344,
+      "eval_samples_per_second": 307.654,
+      "eval_steps_per_second": 2.47,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 33.9716911315918,
+      "learning_rate": 1.1052119474735564e-05,
+      "loss": 0.5753,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8188073394495413,
+      "eval_loss": 1.0152171850204468,
+      "eval_runtime": 2.8231,
+      "eval_samples_per_second": 308.876,
+      "eval_steps_per_second": 2.48,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 38.60210418701172,
+      "learning_rate": 7.370408372848306e-06,
+      "loss": 0.5522,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8222477064220184,
+      "eval_loss": 1.008946418762207,
+      "eval_runtime": 2.8157,
+      "eval_samples_per_second": 309.697,
+      "eval_steps_per_second": 2.486,
+      "step": 3689
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 33.359806060791016,
+      "learning_rate": 3.6886972709610482e-06,
+      "loss": 0.5295,
+      "step": 4216
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8245412844036697,
+      "eval_loss": 1.0115498304367065,
+      "eval_runtime": 2.8207,
+      "eval_samples_per_second": 309.143,
+      "eval_steps_per_second": 2.482,
+      "step": 4216
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 64687167744780.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.698062417678107,
+    "learning_rate": 3.3135399916985324e-05,
+    "num_train_epochs": 9,
+    "temperature": 29
+  }
+}

run-3/checkpoint-4216/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:791de1df6153e255740932c98a2614366ac91b450f70a12d225a6a28e058b4d5
+size 4984

run-3/checkpoint-4743/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-3/checkpoint-4743/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c47a84f1c47d9b3d78bb2cfbfcd1925f3cc3effe286e34ef7f30471d0938aa9a
+size 17549312

run-3/checkpoint-4743/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c8a8a5575a75dcc7b5b36b388f8dd29adb26ad891d90b18a39e00c89411093
+size 35123898

run-3/checkpoint-4743/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e885d27ff12c2d8e7f8a71b358892ece6c7eb3e93a62ecf472a32cfaceabd844
+size 14308

run-3/checkpoint-4743/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fb8a3601291fa0d8c7c1ebd4d58c6c50b8d329d0543992e5d3c7e6209043d30
+size 1064

run-3/checkpoint-4743/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-4743/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-4743/trainer_state.json

@@ -0,0 +1,170 @@
+{
+  "best_metric": 0.8245412844036697,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-4216",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 4743,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.104732990264893,
+      "learning_rate": 2.9453688815098063e-05,
+      "loss": 1.6038,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7752293577981652,
+      "eval_loss": 1.2298829555511475,
+      "eval_runtime": 2.8117,
+      "eval_samples_per_second": 310.129,
+      "eval_steps_per_second": 2.49,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": Infinity,
+      "learning_rate": 2.5778963882284596e-05,
+      "loss": 1.0293,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8084862385321101,
+      "eval_loss": 1.0575315952301025,
+      "eval_runtime": 2.8112,
+      "eval_samples_per_second": 310.184,
+      "eval_steps_per_second": 2.49,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 26.63373565673828,
+      "learning_rate": 2.209725278039734e-05,
+      "loss": 0.814,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8004587155963303,
+      "eval_loss": 1.0314538478851318,
+      "eval_runtime": 2.813,
+      "eval_samples_per_second": 309.985,
+      "eval_steps_per_second": 2.488,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 14.250652313232422,
+      "learning_rate": 1.841554167851008e-05,
+      "loss": 0.6947,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8165137614678899,
+      "eval_loss": 0.9996209740638733,
+      "eval_runtime": 2.826,
+      "eval_samples_per_second": 308.569,
+      "eval_steps_per_second": 2.477,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 9.728443145751953,
+      "learning_rate": 1.4733830576622822e-05,
+      "loss": 0.6281,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8188073394495413,
+      "eval_loss": 0.9810827374458313,
+      "eval_runtime": 2.8344,
+      "eval_samples_per_second": 307.654,
+      "eval_steps_per_second": 2.47,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 33.9716911315918,
+      "learning_rate": 1.1052119474735564e-05,
+      "loss": 0.5753,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8188073394495413,
+      "eval_loss": 1.0152171850204468,
+      "eval_runtime": 2.8231,
+      "eval_samples_per_second": 308.876,
+      "eval_steps_per_second": 2.48,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 38.60210418701172,
+      "learning_rate": 7.370408372848306e-06,
+      "loss": 0.5522,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8222477064220184,
+      "eval_loss": 1.008946418762207,
+      "eval_runtime": 2.8157,
+      "eval_samples_per_second": 309.697,
+      "eval_steps_per_second": 2.486,
+      "step": 3689
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 33.359806060791016,
+      "learning_rate": 3.6886972709610482e-06,
+      "loss": 0.5295,
+      "step": 4216
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8245412844036697,
+      "eval_loss": 1.0115498304367065,
+      "eval_runtime": 2.8207,
+      "eval_samples_per_second": 309.143,
+      "eval_steps_per_second": 2.482,
+      "step": 4216
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 9.716737747192383,
+      "learning_rate": 6.986169073789864e-09,
+      "loss": 0.5209,
+      "step": 4743
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8245412844036697,
+      "eval_loss": 1.00905442237854,
+      "eval_runtime": 2.8042,
+      "eval_samples_per_second": 310.967,
+      "eval_steps_per_second": 2.496,
+      "step": 4743
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 72758802681960.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.698062417678107,
+    "learning_rate": 3.3135399916985324e-05,
+    "num_train_epochs": 9,
+    "temperature": 29
+  }
+}

run-3/checkpoint-4743/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:791de1df6153e255740932c98a2614366ac91b450f70a12d225a6a28e058b4d5
+size 4984

run-4/checkpoint-527/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-4/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d86de785f326de5dff3e11e88c4aab157dd2b03e1e78e06e6e4af1771b96592e
+size 17549312

run-4/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6206b577fd9e48c85957e477a2192e1ae282880e83551150a46777c80bb59019
+size 35123898

run-4/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a32291cb0c1329fbb9596dcc47c5d9b0d1f71ecc09dad1791e0b193314659e4
+size 14308

run-4/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a6c83b8248554da9df55604b792e0cc3e97d6562e147841d0422e80cad5529
+size 1064

run-4/checkpoint-527/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-4/checkpoint-527/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-4/checkpoint-527/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.7717889908256881,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/checkpoint-527",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 527,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.212067127227783,
+      "learning_rate": 1.7783082729779372e-05,
+      "loss": 1.8496,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7717889908256881,
+      "eval_loss": 1.3957021236419678,
+      "eval_runtime": 2.8127,
+      "eval_samples_per_second": 310.024,
+      "eval_steps_per_second": 2.489,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3162,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 8057768762220.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6704103438400755,
+    "learning_rate": 2.1339699275735247e-05,
+    "num_train_epochs": 6,
+    "temperature": 15
+  }
+}

run-4/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dec3ce0eb673efb51820a99208f5385b27f4812a3c302cc6766ad0dc61097ba1
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:791de1df6153e255740932c98a2614366ac91b450f70a12d225a6a28e058b4d5
+oid sha256:dec3ce0eb673efb51820a99208f5385b27f4812a3c302cc6766ad0dc61097ba1
 size 4984