Training in progress, epoch 1

logs/events.out.tfevents.1713587314.1376c752d37a.9760.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1fab29a37d387457397e9217c93cabdf0556a2be7be85d273b266c377a53ff4
-size 6213
+oid sha256:b0ceb876d0b7f2bbf5a6d7a0eaa25dcc1110806adc2859dd1cb7612b4713333f
+size 10217

logs/events.out.tfevents.1713587431.1376c752d37a.9760.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dd224660c062d25664140e29cbe3f1b449a639071b5e6213118d6cf292e3c44
+size 5482

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:891b297a2bf21326fb8271332e48c1cd97b14c1666c823c54122fc0a840e4bd8
+oid sha256:414d4511bde49e77d270d8cee18cf5c6445777bf6858ddfc4e543aa88ea7a7d9
 size 17549312

run-4/checkpoint-1498/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-4/checkpoint-1498/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba01923c799b46a7174d339dd398cafe6b179d6b17a96ddff06994309014549a
+size 17549312

run-4/checkpoint-1498/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3e4889077d18d5ff51d6bcce5786246b006960b6a5047307469cc7d3b2bbd38
+size 35123898

run-4/checkpoint-1498/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec7baa77763623ab6f5c0a3afb24b20f15950a2841a41419e9c31b1269a80a7
+size 14308

run-4/checkpoint-1498/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b421233205628458448619fb2c1d6825c21951ecbfc8c0468a6df366479b891
+size 1064

run-4/checkpoint-1498/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-1498/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-1498/trainer_state.json

@@ -0,0 +1,166 @@
+{
+  "best_metric": 0.7065026362038664,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/checkpoint-856",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 1498,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.794419765472412,
+      "learning_rate": 3.974483565917368e-05,
+      "loss": 0.5313,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6666666666666666,
+      "eval_f1": 0.0035026269702276708,
+      "eval_loss": 0.49643149971961975,
+      "eval_mcc": 0.01210898699241207,
+      "eval_precision": 0.5,
+      "eval_recall": 0.0017574692442882249,
+      "eval_runtime": 3.1332,
+      "eval_samples_per_second": 544.813,
+      "eval_steps_per_second": 17.235,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.522770643234253,
+      "learning_rate": 3.3120696382644734e-05,
+      "loss": 0.493,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7047451669595782,
+      "eval_f1": 0.48884381338742394,
+      "eval_loss": 0.48239898681640625,
+      "eval_mcc": 0.2950146249100624,
+      "eval_precision": 0.5779376498800959,
+      "eval_recall": 0.4235500878734622,
+      "eval_runtime": 3.1182,
+      "eval_samples_per_second": 547.428,
+      "eval_steps_per_second": 17.318,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.776003122329712,
+      "learning_rate": 2.6496557106115785e-05,
+      "loss": 0.4796,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7012302284710018,
+      "eval_f1": 0.45278969957081544,
+      "eval_loss": 0.47861993312835693,
+      "eval_mcc": 0.2733353610467977,
+      "eval_precision": 0.581267217630854,
+      "eval_recall": 0.37082601054481545,
+      "eval_runtime": 3.1521,
+      "eval_samples_per_second": 541.541,
+      "eval_steps_per_second": 17.131,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.881204843521118,
+      "learning_rate": 1.987241782958684e-05,
+      "loss": 0.4758,
+      "step": 856
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7065026362038664,
+      "eval_f1": 0.47318611987381703,
+      "eval_loss": 0.47547900676727295,
+      "eval_mcc": 0.29121450441681707,
+      "eval_precision": 0.5890052356020943,
+      "eval_recall": 0.3954305799648506,
+      "eval_runtime": 3.1289,
+      "eval_samples_per_second": 545.555,
+      "eval_steps_per_second": 17.258,
+      "step": 856
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.075852394104004,
+      "learning_rate": 1.3248278553057892e-05,
+      "loss": 0.4712,
+      "step": 1070
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7047451669595782,
+      "eval_f1": 0.4603854389721628,
+      "eval_loss": 0.4729969799518585,
+      "eval_mcc": 0.2828917897972719,
+      "eval_precision": 0.589041095890411,
+      "eval_recall": 0.37785588752196836,
+      "eval_runtime": 3.133,
+      "eval_samples_per_second": 544.843,
+      "eval_steps_per_second": 17.236,
+      "step": 1070
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.4645376205444336,
+      "learning_rate": 6.624139276528946e-06,
+      "loss": 0.4692,
+      "step": 1284
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.70298769771529,
+      "eval_f1": 0.44224422442244227,
+      "eval_loss": 0.47236910462379456,
+      "eval_mcc": 0.27278283262063535,
+      "eval_precision": 0.5911764705882353,
+      "eval_recall": 0.3532513181019332,
+      "eval_runtime": 3.1425,
+      "eval_samples_per_second": 543.202,
+      "eval_steps_per_second": 17.184,
+      "step": 1284
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.018095016479492,
+      "learning_rate": 0.0,
+      "loss": 0.4675,
+      "step": 1498
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7065026362038664,
+      "eval_f1": 0.4653148345784418,
+      "eval_loss": 0.4719870388507843,
+      "eval_mcc": 0.28809574061746357,
+      "eval_precision": 0.592391304347826,
+      "eval_recall": 0.38312829525483305,
+      "eval_runtime": 3.1194,
+      "eval_samples_per_second": 547.227,
+      "eval_steps_per_second": 17.311,
+      "step": 1498
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1498,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 3673429651080.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8274705871724447,
+    "learning_rate": 4.6368974935702624e-05,
+    "num_train_epochs": 7,
+    "temperature": 26
+  }
+}

run-4/checkpoint-1498/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a66c3611aaa8b227e5b872f0aa4e2f90b172c191cd1eb23826a153b2caba18a
+size 5048

run-4/checkpoint-856/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-4/checkpoint-856/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cb56a22a7aeac753cd5a0aaa8b01daec8386c531a33d1381cda7cdf6f254bf9
+size 17549312

run-4/checkpoint-856/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:838ed95de8bf8193e0a072004a0c55592d534bc623b3ceb4ceef8fc8376ca957
+size 35123898

run-4/checkpoint-856/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057111bfbb4d541cc190a3ed4fcfe228e7425a50e4a06afd33224d43272b1a59
+size 14308

run-4/checkpoint-856/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e6e9e878273ea2e32422fe9c8c467b72705eaa0f6f2b187924e58384dfd4ebd
+size 1064

run-4/checkpoint-856/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-856/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-856/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.7065026362038664,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/checkpoint-856",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 856,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.794419765472412,
+      "learning_rate": 3.974483565917368e-05,
+      "loss": 0.5313,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6666666666666666,
+      "eval_f1": 0.0035026269702276708,
+      "eval_loss": 0.49643149971961975,
+      "eval_mcc": 0.01210898699241207,
+      "eval_precision": 0.5,
+      "eval_recall": 0.0017574692442882249,
+      "eval_runtime": 3.1332,
+      "eval_samples_per_second": 544.813,
+      "eval_steps_per_second": 17.235,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.522770643234253,
+      "learning_rate": 3.3120696382644734e-05,
+      "loss": 0.493,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7047451669595782,
+      "eval_f1": 0.48884381338742394,
+      "eval_loss": 0.48239898681640625,
+      "eval_mcc": 0.2950146249100624,
+      "eval_precision": 0.5779376498800959,
+      "eval_recall": 0.4235500878734622,
+      "eval_runtime": 3.1182,
+      "eval_samples_per_second": 547.428,
+      "eval_steps_per_second": 17.318,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.776003122329712,
+      "learning_rate": 2.6496557106115785e-05,
+      "loss": 0.4796,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7012302284710018,
+      "eval_f1": 0.45278969957081544,
+      "eval_loss": 0.47861993312835693,
+      "eval_mcc": 0.2733353610467977,
+      "eval_precision": 0.581267217630854,
+      "eval_recall": 0.37082601054481545,
+      "eval_runtime": 3.1521,
+      "eval_samples_per_second": 541.541,
+      "eval_steps_per_second": 17.131,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.881204843521118,
+      "learning_rate": 1.987241782958684e-05,
+      "loss": 0.4758,
+      "step": 856
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7065026362038664,
+      "eval_f1": 0.47318611987381703,
+      "eval_loss": 0.47547900676727295,
+      "eval_mcc": 0.29121450441681707,
+      "eval_precision": 0.5890052356020943,
+      "eval_recall": 0.3954305799648506,
+      "eval_runtime": 3.1289,
+      "eval_samples_per_second": 545.555,
+      "eval_steps_per_second": 17.258,
+      "step": 856
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1498,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 2099102657760.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8274705871724447,
+    "learning_rate": 4.6368974935702624e-05,
+    "num_train_epochs": 7,
+    "temperature": 26
+  }
+}

run-4/checkpoint-856/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a66c3611aaa8b227e5b872f0aa4e2f90b172c191cd1eb23826a153b2caba18a
+size 5048

run-5/checkpoint-214/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-5/checkpoint-214/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:414d4511bde49e77d270d8cee18cf5c6445777bf6858ddfc4e543aa88ea7a7d9
+size 17549312

run-5/checkpoint-214/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f0ef1bfc381dac85573d917c0ba317a9931ee02263b52a4559b12f74d484700
+size 35123898

run-5/checkpoint-214/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc7e492e6768bc7c3c01ac823da5a8177cf34fc1b175dd727fa3be969661a151
+size 14308

run-5/checkpoint-214/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6f2962f08ce57257ceee4f9d80cbef2473f4afbfdfe23b8792790502b23fc3
+size 1064

run-5/checkpoint-214/special_tokens_map.json

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

run-5/checkpoint-214/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-5/checkpoint-214/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.6666666666666666,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-5/checkpoint-214",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 214,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.334259033203125,
+      "learning_rate": 0.0007289392500735427,
+      "loss": 0.5536,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6666666666666666,
+      "eval_f1": 0.0,
+      "eval_loss": 0.5510665774345398,
+      "eval_mcc": 0.0,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 3.1386,
+      "eval_samples_per_second": 543.88,
+      "eval_steps_per_second": 17.205,
+      "step": 214
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1498,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 524775664440.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8578412183256148,
+    "learning_rate": 0.0008504291250857999,
+    "num_train_epochs": 7,
+    "temperature": 7
+  }
+}

run-5/checkpoint-214/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a105efa06002e83e7f7f9728fd07b6e3ab16420601aa1ff3b5c7d3c74b026e
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a66c3611aaa8b227e5b872f0aa4e2f90b172c191cd1eb23826a153b2caba18a
+oid sha256:19a105efa06002e83e7f7f9728fd07b6e3ab16420601aa1ff3b5c7d3c74b026e
 size 5048