Training in progress, epoch 1

logs/events.out.tfevents.1721965230.98acc6742512.15262.24

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b10372f4196456e651d37fc2aa46af4235acce30f1efbeef45363a8119a8a10c
-size 6432
+oid sha256:51ee8cbba6bf39425ffdae4ae0d1bc7be11a3b88af9ffa54ec9071f515119ecc
+size 10057

logs/events.out.tfevents.1721965439.98acc6742512.15262.25

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9baf39669cf918c4027bde6caa207ddfdb682b9404e809d95bae78f7f55c130f
+size 5709

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d444cc5d5174d8ce3d0dbdf361090f75cbd8e47713c75ad24278ae96db15a68
+oid sha256:66920bab88d11c47d714a1386fd87c93335978fa565a6141d9be3a236a28ec25
 size 17549312

run-23/checkpoint-1204/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": "4.43.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-23/checkpoint-1204/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e7a67a6619023a42c9bb4c54dc59ab7e00cb3d42f9460b22d2bb0f2bdc20063
+size 17549312

run-23/checkpoint-1204/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ab6ebf30739ad48294c42f9188ce58a520391c2707a14febb8772af910a8ec
+size 35123898

run-23/checkpoint-1204/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:637a1606621bd80a6fdbff71a22ce14e8c8c6f93aa7e71464f67978f9e73d7a9
+size 14308

run-23/checkpoint-1204/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cff6b2f8575e5a499a683dea8885c1d912ee108a03f6fdc8db74cbd29100919
+size 1064

run-23/checkpoint-1204/special_tokens_map.json

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

run-23/checkpoint-1204/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-23/checkpoint-1204/trainer_state.json

@@ -0,0 +1,158 @@
+{
+  "best_metric": 0.8133333333333334,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-23/checkpoint-860",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 1204,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0031909942626953,
+      "learning_rate": 0.0002164041823853993,
+      "loss": 0.5574,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8248408888888888,
+      "eval_BAC": 0.736,
+      "eval_MCC": 0.4730523981849912,
+      "eval_PR_AUC": 0.781847757181041,
+      "eval_accuracy": 0.736,
+      "eval_loss": 0.49910596013069153,
+      "eval_runtime": 6.2575,
+      "eval_samples_per_second": 239.711,
+      "eval_steps_per_second": 7.511,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.0278003215789795,
+      "learning_rate": 0.00018033681865449943,
+      "loss": 0.5145,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8580764444444444,
+      "eval_BAC": 0.7773333333333333,
+      "eval_MCC": 0.582222053555848,
+      "eval_PR_AUC": 0.8188026202087335,
+      "eval_accuracy": 0.7773333333333333,
+      "eval_loss": 0.4729117155075073,
+      "eval_runtime": 6.2762,
+      "eval_samples_per_second": 238.996,
+      "eval_steps_per_second": 7.489,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.6290640830993652,
+      "learning_rate": 0.00014426945492359953,
+      "loss": 0.4941,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.8673866666666666,
+      "eval_BAC": 0.798,
+      "eval_MCC": 0.60126120615129,
+      "eval_PR_AUC": 0.8330993802459163,
+      "eval_accuracy": 0.798,
+      "eval_loss": 0.44955623149871826,
+      "eval_runtime": 6.2788,
+      "eval_samples_per_second": 238.898,
+      "eval_steps_per_second": 7.485,
+      "step": 516
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.129098892211914,
+      "learning_rate": 0.00010820209119269965,
+      "loss": 0.4805,
+      "step": 688
+    },
+    {
+      "epoch": 4.0,
+      "eval_AUC": 0.8743111111111109,
+      "eval_BAC": 0.8126666666666666,
+      "eval_MCC": 0.6313151141711845,
+      "eval_PR_AUC": 0.8435583937466524,
+      "eval_accuracy": 0.8126666666666666,
+      "eval_loss": 0.43168675899505615,
+      "eval_runtime": 6.2703,
+      "eval_samples_per_second": 239.222,
+      "eval_steps_per_second": 7.496,
+      "step": 688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.103851318359375,
+      "learning_rate": 7.213472746179977e-05,
+      "loss": 0.4677,
+      "step": 860
+    },
+    {
+      "epoch": 5.0,
+      "eval_AUC": 0.8835342222222222,
+      "eval_BAC": 0.8133333333333334,
+      "eval_MCC": 0.6345698826834335,
+      "eval_PR_AUC": 0.8645101312047581,
+      "eval_accuracy": 0.8133333333333334,
+      "eval_loss": 0.43117985129356384,
+      "eval_runtime": 6.2193,
+      "eval_samples_per_second": 241.185,
+      "eval_steps_per_second": 7.557,
+      "step": 860
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.7112812995910645,
+      "learning_rate": 3.6067363730899884e-05,
+      "loss": 0.4594,
+      "step": 1032
+    },
+    {
+      "epoch": 6.0,
+      "eval_AUC": 0.8841564444444445,
+      "eval_BAC": 0.8086666666666666,
+      "eval_MCC": 0.62420750531922,
+      "eval_PR_AUC": 0.8634245109180674,
+      "eval_accuracy": 0.8086666666666666,
+      "eval_loss": 0.43022820353507996,
+      "eval_runtime": 6.2078,
+      "eval_samples_per_second": 241.632,
+      "eval_steps_per_second": 7.571,
+      "step": 1032
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1204,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2702266380000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.868343761378926,
+    "learning_rate": 0.0002524715461162992,
+    "num_train_epochs": 7,
+    "temperature": 5
+  }
+}

run-23/checkpoint-1204/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75a0586eaedd6e814a7ef987ae0d99347c0d18ed4427cfb68a82d0f0ab94523c
+size 5240

run-23/checkpoint-860/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": "4.43.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-23/checkpoint-860/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a1b0c4e817bd7057a6022f0b6e579a57382c58208ed6139d57a32cd465de7f2
+size 17549312

run-23/checkpoint-860/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37676a025fe339feb9114a91fcd71510c21630ae07e0b3fd9fd3b5669b310566
+size 35123898

run-23/checkpoint-860/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9f0bc35f961ba3eec992b81bac90971267fe149efd92cea3c10af23980c570
+size 14308

run-23/checkpoint-860/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5799d0a84bdf308ab6463c0fe8281c4dfb3a4c645b829a22fc582af6782a831
+size 1064

run-23/checkpoint-860/special_tokens_map.json

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

run-23/checkpoint-860/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-23/checkpoint-860/trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_metric": 0.8133333333333334,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-23/checkpoint-860",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 860,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0031909942626953,
+      "learning_rate": 0.0002164041823853993,
+      "loss": 0.5574,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8248408888888888,
+      "eval_BAC": 0.736,
+      "eval_MCC": 0.4730523981849912,
+      "eval_PR_AUC": 0.781847757181041,
+      "eval_accuracy": 0.736,
+      "eval_loss": 0.49910596013069153,
+      "eval_runtime": 6.2575,
+      "eval_samples_per_second": 239.711,
+      "eval_steps_per_second": 7.511,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.0278003215789795,
+      "learning_rate": 0.00018033681865449943,
+      "loss": 0.5145,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8580764444444444,
+      "eval_BAC": 0.7773333333333333,
+      "eval_MCC": 0.582222053555848,
+      "eval_PR_AUC": 0.8188026202087335,
+      "eval_accuracy": 0.7773333333333333,
+      "eval_loss": 0.4729117155075073,
+      "eval_runtime": 6.2762,
+      "eval_samples_per_second": 238.996,
+      "eval_steps_per_second": 7.489,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.6290640830993652,
+      "learning_rate": 0.00014426945492359953,
+      "loss": 0.4941,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.8673866666666666,
+      "eval_BAC": 0.798,
+      "eval_MCC": 0.60126120615129,
+      "eval_PR_AUC": 0.8330993802459163,
+      "eval_accuracy": 0.798,
+      "eval_loss": 0.44955623149871826,
+      "eval_runtime": 6.2788,
+      "eval_samples_per_second": 238.898,
+      "eval_steps_per_second": 7.485,
+      "step": 516
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.129098892211914,
+      "learning_rate": 0.00010820209119269965,
+      "loss": 0.4805,
+      "step": 688
+    },
+    {
+      "epoch": 4.0,
+      "eval_AUC": 0.8743111111111109,
+      "eval_BAC": 0.8126666666666666,
+      "eval_MCC": 0.6313151141711845,
+      "eval_PR_AUC": 0.8435583937466524,
+      "eval_accuracy": 0.8126666666666666,
+      "eval_loss": 0.43168675899505615,
+      "eval_runtime": 6.2703,
+      "eval_samples_per_second": 239.222,
+      "eval_steps_per_second": 7.496,
+      "step": 688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.103851318359375,
+      "learning_rate": 7.213472746179977e-05,
+      "loss": 0.4677,
+      "step": 860
+    },
+    {
+      "epoch": 5.0,
+      "eval_AUC": 0.8835342222222222,
+      "eval_BAC": 0.8133333333333334,
+      "eval_MCC": 0.6345698826834335,
+      "eval_PR_AUC": 0.8645101312047581,
+      "eval_accuracy": 0.8133333333333334,
+      "eval_loss": 0.43117985129356384,
+      "eval_runtime": 6.2193,
+      "eval_samples_per_second": 241.185,
+      "eval_steps_per_second": 7.557,
+      "step": 860
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1204,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2251888650000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.868343761378926,
+    "learning_rate": 0.0002524715461162992,
+    "num_train_epochs": 7,
+    "temperature": 5
+  }
+}

run-23/checkpoint-860/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75a0586eaedd6e814a7ef987ae0d99347c0d18ed4427cfb68a82d0f0ab94523c
+size 5240

run-24/checkpoint-172/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": "4.43.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-24/checkpoint-172/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66920bab88d11c47d714a1386fd87c93335978fa565a6141d9be3a236a28ec25
+size 17549312

run-24/checkpoint-172/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46d081ba4eb12e31e213ebf63b5ca2f4d234cd2f8b350ee71715e3b43288a7c8
+size 35123898

run-24/checkpoint-172/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b99cb6263c36c5c191e9bbbef2d3167790018df547076ed69608752e2b4353d4
+size 14308

run-24/checkpoint-172/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:942ae2b001ade5a042f0f29b6dc46350a489ad70c0e38088044300565c19fea2
+size 1064

run-24/checkpoint-172/special_tokens_map.json

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

run-24/checkpoint-172/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-24/checkpoint-172/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.736,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-24/checkpoint-172",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 172,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6114831566810608,
+      "learning_rate": 0.00012438553278352026,
+      "loss": 0.4032,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.812864,
+      "eval_BAC": 0.736,
+      "eval_MCC": 0.47260700716368276,
+      "eval_PR_AUC": 0.7744742146180674,
+      "eval_accuracy": 0.736,
+      "eval_loss": 0.3765888214111328,
+      "eval_runtime": 6.2583,
+      "eval_samples_per_second": 239.681,
+      "eval_steps_per_second": 7.51,
+      "step": 172
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1720,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 450377730000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.605164320881552,
+    "learning_rate": 0.00013820614753724472,
+    "num_train_epochs": 10,
+    "temperature": 9
+  }
+}

run-24/checkpoint-172/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db080950555f1448b25c4e51afe1a086f8b409b2841b40874bfcb82bde4dd4fe
+size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75a0586eaedd6e814a7ef987ae0d99347c0d18ed4427cfb68a82d0f0ab94523c
+oid sha256:db080950555f1448b25c4e51afe1a086f8b409b2841b40874bfcb82bde4dd4fe
 size 5240