Training in progress, epoch 2

logs/events.out.tfevents.1710434095.4cb0d5d7fb51.5918.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6069c9e5a9b4359ed272f493fd7287f36234da848f0a440570550e6871b20b7
-size 5712
+oid sha256:f99e79f49aac7be485ce6ca0787854b12c56803cd6649738a20da1f29767c8d6
+size 7134

logs/events.out.tfevents.1710438645.4cb0d5d7fb51.5918.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ec2183b8366d709c35a2c586501424d21a94efd56083dee2c938a05f81f056d
+size 5713

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:344b138dc88029e26487137bf04ab764bfd8c50b0c4e250209570c66a7a6e72a
+oid sha256:2a34257cdefdb738166aa4e1ad581f8c6a1664abe6077c96e1def4caf447a693
 size 17549312

run-1/checkpoint-1188/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-1/checkpoint-1188/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7965872f00ba3af3f37f869daacda6fc1f0381c34c1a715b4fdbaf9634bebe2f
+size 17549312

run-1/checkpoint-1188/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b439439dc54abaf1deda8534898e1f960f7e657f21941dc4800551e4d0e91166
+size 35122746

run-1/checkpoint-1188/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2417e175c9bd2e8cf2015d5a061a7249afeb461256703dc578cd33b9158529fc
+size 14054

run-1/checkpoint-1188/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44e6930556b45cb96692d66d8edaa590b3a717f302de7c4f6225093d361b88b5
+size 1064

run-1/checkpoint-1188/special_tokens_map.json

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

run-1/checkpoint-1188/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-1/checkpoint-1188/trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": 0.6653465346534654,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-1188",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1188,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.3426679372787476,
+      "learning_rate": 0.0003560526201910554,
+      "loss": 0.6371,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5841584158415841,
+      "eval_loss": 0.637409508228302,
+      "eval_runtime": 56.7978,
+      "eval_samples_per_second": 8.891,
+      "eval_steps_per_second": 0.282,
+      "step": 297
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.018396258354187,
+      "learning_rate": 0.0002373684134607036,
+      "loss": 0.603,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6277227722772277,
+      "eval_loss": 0.6017976403236389,
+      "eval_runtime": 55.6441,
+      "eval_samples_per_second": 9.076,
+      "eval_steps_per_second": 0.288,
+      "step": 594
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.4982593059539795,
+      "learning_rate": 0.0001186842067303518,
+      "loss": 0.588,
+      "step": 891
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6495049504950495,
+      "eval_loss": 0.5974766612052917,
+      "eval_runtime": 55.1255,
+      "eval_samples_per_second": 9.161,
+      "eval_steps_per_second": 0.29,
+      "step": 891
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.6116485595703125,
+      "learning_rate": 0.0,
+      "loss": 0.5769,
+      "step": 1188
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6653465346534654,
+      "eval_loss": 0.5864288806915283,
+      "eval_runtime": 56.8255,
+      "eval_samples_per_second": 8.887,
+      "eval_steps_per_second": 0.282,
+      "step": 1188
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1188,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 3111373132560.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.900582717199523,
+    "learning_rate": 0.0004747368269214072,
+    "num_train_epochs": 4,
+    "temperature": 18
+  }
+}

run-1/checkpoint-1188/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6f636dbab8b5e516bcd85051f9f0732a28727ed1675f1d1f3076c7baf2be402
+size 4984

run-1/checkpoint-891/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-1/checkpoint-891/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dad2c00079bf827d9e719db18d4c86aa796e128a9e02878962ed25adb3bcd1b
+size 17549312

run-1/checkpoint-891/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f743eb06051cc7a52c530b8568ca77b298b705e7ad276b49dc748f0572f28ee2
+size 35122746

run-1/checkpoint-891/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8825af3ee3a915f6774d349057db9cb8bcc74ea981ae299e1cb35993773495a5
+size 14054

run-1/checkpoint-891/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48269bd025e4a2a9251c6dba3b071353cc95ee138f476ea609464c3d7a8e9248
+size 1064

run-1/checkpoint-891/special_tokens_map.json

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

run-1/checkpoint-891/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-1/checkpoint-891/trainer_state.json

@@ -0,0 +1,74 @@
+{
+  "best_metric": 0.6495049504950495,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-891",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 891,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.3426679372787476,
+      "learning_rate": 0.0003560526201910554,
+      "loss": 0.6371,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5841584158415841,
+      "eval_loss": 0.637409508228302,
+      "eval_runtime": 56.7978,
+      "eval_samples_per_second": 8.891,
+      "eval_steps_per_second": 0.282,
+      "step": 297
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.018396258354187,
+      "learning_rate": 0.0002373684134607036,
+      "loss": 0.603,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6277227722772277,
+      "eval_loss": 0.6017976403236389,
+      "eval_runtime": 55.6441,
+      "eval_samples_per_second": 9.076,
+      "eval_steps_per_second": 0.288,
+      "step": 594
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.4982593059539795,
+      "learning_rate": 0.0001186842067303518,
+      "loss": 0.588,
+      "step": 891
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6495049504950495,
+      "eval_loss": 0.5974766612052917,
+      "eval_runtime": 55.1255,
+      "eval_samples_per_second": 9.161,
+      "eval_steps_per_second": 0.29,
+      "step": 891
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1188,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 2333529849420.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.900582717199523,
+    "learning_rate": 0.0004747368269214072,
+    "num_train_epochs": 4,
+    "temperature": 18
+  }
+}

run-1/checkpoint-891/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6f636dbab8b5e516bcd85051f9f0732a28727ed1675f1d1f3076c7baf2be402
+size 4984

run-2/checkpoint-297/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-2/checkpoint-297/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:858a8a1dab1ef5869328e1a71270ea538b6456e395636227e7050b939a40f362
+size 17549312

run-2/checkpoint-297/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0f8425164eef3bdefee196513eccc61644a3e47ff8a0c0efc849d5b1236c0ab
+size 35122746

run-2/checkpoint-297/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f414017d19e8a66d09e6a16c0bca909eff6c9e5541f54da3f0dba2607378e04d
+size 14054

run-2/checkpoint-297/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63d104cf5cc677e05d6c0d95aeea0ad14a5fcfd11dfd68081ad69d9a3757dc17
+size 1064

run-2/checkpoint-297/special_tokens_map.json

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

run-2/checkpoint-297/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-2/checkpoint-297/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.5089108910891089,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-297",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 297,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6225994825363159,
+      "learning_rate": 0.0001586738890732749,
+      "loss": 0.0237,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5089108910891089,
+      "eval_loss": 0.015105457045137882,
+      "eval_runtime": 57.753,
+      "eval_samples_per_second": 8.744,
+      "eval_steps_per_second": 0.277,
+      "step": 297
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 891,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 777843283140.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.007640219223822298,
+    "learning_rate": 0.00023801083360991236,
+    "num_train_epochs": 3,
+    "temperature": 6
+  }
+}

run-2/checkpoint-297/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6eb122098f8367495c5db394e8b3e852a429d4206a286ab0525ac7e92410bcf
+size 4984

run-2/checkpoint-594/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07ac356b8b2a20268b7ebcf811e6e76fb50d0907cebd76b4b97951d03a7883a2
+oid sha256:2a34257cdefdb738166aa4e1ad581f8c6a1664abe6077c96e1def4caf447a693
 size 17549312

run-2/checkpoint-594/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0a000da5dfae4ecc03bdcd0560ad40eca3b2a9776151e2114fb2776bb98c342
+oid sha256:322f8f3c31135d614ffb17055c6eb349e96af827401385fbf7fa0303f9090a1b
 size 35122746

run-2/checkpoint-594/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9593aa7b268a99b44b1c4305fd3c5fb8820f0dfb804b9c95c1c1b40dbaeb2963
+oid sha256:df6866d0dff400085edf68783c4718d94e08dcfa8f0d23f9d94ad3e230de2def
 size 14054

run-2/checkpoint-594/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9833b67d53cb68178f11d0e83e382bfc933a82bfeb6c8b386345826d25703649
+oid sha256:98b1c3e6ca1a73777b9d2abe0a489345000ab460318de113f2fff450a1f5e46c
 size 1064

run-2/checkpoint-594/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.5148514851485149,
-  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-594",
-  "epoch": 1.0,
+  "best_metric": 0.5089108910891089,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-297",
+  "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 594,
   "is_hyper_param_search": true,
@@ -10,37 +10,49 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.7887440323829651,
-      "learning_rate": 0.00015586356006012654,
-      "loss": 0.3246,
-      "step": 594
+      "grad_norm": 0.6225994825363159,
+      "learning_rate": 0.0001586738890732749,
+      "loss": 0.0237,
+      "step": 297
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5148514851485149,
-      "eval_f1": 0.16382252559726962,
-      "eval_loss": 0.3221835792064667,
-      "eval_precision": 0.5853658536585366,
-      "eval_recall": 0.09523809523809523,
-      "eval_runtime": 15.4228,
-      "eval_samples_per_second": 32.744,
-      "eval_steps_per_second": 1.037,
+      "eval_accuracy": 0.5089108910891089,
+      "eval_loss": 0.015105457045137882,
+      "eval_runtime": 57.753,
+      "eval_samples_per_second": 8.744,
+      "eval_steps_per_second": 0.277,
+      "step": 297
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.24433593451976776,
+      "learning_rate": 7.933694453663745e-05,
+      "loss": 0.0161,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.504950495049505,
+      "eval_loss": 0.014346625655889511,
+      "eval_runtime": 56.8115,
+      "eval_samples_per_second": 8.889,
+      "eval_steps_per_second": 0.282,
       "step": 594
     }
   ],
   "logging_steps": 500,
-  "max_steps": 5940,
+  "max_steps": 891,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
+  "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 777843283140.0,
-  "train_batch_size": 16,
+  "total_flos": 1555686566280.0,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.39860510957002215,
-    "learning_rate": 0.0001731817334001406,
-    "num_train_epochs": 10,
-    "per_device_train_batch_size": 16,
-    "temperature": 4
+    "alpha": 0.007640219223822298,
+    "learning_rate": 0.00023801083360991236,
+    "num_train_epochs": 3,
+    "temperature": 6
   }
 }

run-2/checkpoint-594/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8767ee43a8087c968cdc0eed2d700fdcfad08ca8672daf6f805917fe63cbe37
-size 4920
+oid sha256:b6eb122098f8367495c5db394e8b3e852a429d4206a286ab0525ac7e92410bcf
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6f636dbab8b5e516bcd85051f9f0732a28727ed1675f1d1f3076c7baf2be402
+oid sha256:b6eb122098f8367495c5db394e8b3e852a429d4206a286ab0525ac7e92410bcf
 size 4984