Training in progress, epoch 1

logs/events.out.tfevents.1721962255.98acc6742512.15262.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b1dc7a841b98377170505beaa1d0e38173e1a34c3a55799426edd2cd53dd2fd
-size 6433
+oid sha256:c250775ebf60f77fc9f9ccd155de966bc6c7fbdcd5a0d6da2ccaae6d11b395ea
+size 9687

logs/events.out.tfevents.1721962439.98acc6742512.15262.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8524fd8d9a602c0fda9c8936ed4305d683c79d6513ddad265e9eaac372138880
+size 5707

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a91e6aee508612edb5a342f53e0951e9747c9022981f584ca3c6e11311f61240
+oid sha256:481ef6f946a20ace36469d3759ab47132144bae42fb7955308b2bae4edba13ac
 size 17549312

run-0/checkpoint-1032/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-0/checkpoint-1032/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dccef483dac17f644b1e742c535ada9ceddd407fa617a188d3abc9eda286c44
+size 17549312

run-0/checkpoint-1032/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9cd74ddf548932e67ab1d0d4207b3ba5bfefc526efde9edb008b5ac00b03c99
+size 35123898

run-0/checkpoint-1032/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc1d950c7aa768cbb06bd21291e0e2d816cdf5332b230a560123681e0a9a3f44
+size 14308

run-0/checkpoint-1032/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94533e4e5c72a690cff92502ddc9a54d8a404a9cb758908bf9ee90bfd044d660
+size 1064

run-0/checkpoint-1032/special_tokens_map.json

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

run-0/checkpoint-1032/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-0/checkpoint-1032/trainer_state.json

@@ -0,0 +1,158 @@
+{
+  "best_metric": 0.802,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-0/checkpoint-1032",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 1032,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.40991276502609253,
+      "learning_rate": 0.00012592472624312588,
+      "loss": 0.3541,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8165582222222223,
+      "eval_BAC": 0.7313333333333334,
+      "eval_MCC": 0.4637400760214038,
+      "eval_PR_AUC": 0.7669251828483298,
+      "eval_accuracy": 0.7313333333333333,
+      "eval_loss": 0.33297714591026306,
+      "eval_runtime": 5.88,
+      "eval_samples_per_second": 255.102,
+      "eval_steps_per_second": 7.993,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7852521538734436,
+      "learning_rate": 0.0001007397809945007,
+      "loss": 0.3395,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8291591111111111,
+      "eval_BAC": 0.7453333333333334,
+      "eval_MCC": 0.5307731566207068,
+      "eval_PR_AUC": 0.7773307731479302,
+      "eval_accuracy": 0.7453333333333333,
+      "eval_loss": 0.32892802357673645,
+      "eval_runtime": 5.8962,
+      "eval_samples_per_second": 254.401,
+      "eval_steps_per_second": 7.971,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.8841129541397095,
+      "learning_rate": 7.555483574587553e-05,
+      "loss": 0.3354,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.8464124444444445,
+      "eval_BAC": 0.7846666666666666,
+      "eval_MCC": 0.585494859343166,
+      "eval_PR_AUC": 0.8098393230420249,
+      "eval_accuracy": 0.7846666666666666,
+      "eval_loss": 0.3203962743282318,
+      "eval_runtime": 6.0014,
+      "eval_samples_per_second": 249.942,
+      "eval_steps_per_second": 7.832,
+      "step": 516
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.4307535886764526,
+      "learning_rate": 5.036989049725035e-05,
+      "loss": 0.3283,
+      "step": 688
+    },
+    {
+      "epoch": 4.0,
+      "eval_AUC": 0.853079111111111,
+      "eval_BAC": 0.7986666666666666,
+      "eval_MCC": 0.6048666115791026,
+      "eval_PR_AUC": 0.8161612377554972,
+      "eval_accuracy": 0.7986666666666666,
+      "eval_loss": 0.3148361146450043,
+      "eval_runtime": 6.1071,
+      "eval_samples_per_second": 245.616,
+      "eval_steps_per_second": 7.696,
+      "step": 688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.2096748352050781,
+      "learning_rate": 2.5184945248625176e-05,
+      "loss": 0.3238,
+      "step": 860
+    },
+    {
+      "epoch": 5.0,
+      "eval_AUC": 0.8653653333333333,
+      "eval_BAC": 0.8013333333333333,
+      "eval_MCC": 0.6179940224891067,
+      "eval_PR_AUC": 0.8210118227054324,
+      "eval_accuracy": 0.8013333333333333,
+      "eval_loss": 0.31179723143577576,
+      "eval_runtime": 6.1725,
+      "eval_samples_per_second": 243.014,
+      "eval_steps_per_second": 7.614,
+      "step": 860
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.405503273010254,
+      "learning_rate": 0.0,
+      "loss": 0.3214,
+      "step": 1032
+    },
+    {
+      "epoch": 6.0,
+      "eval_AUC": 0.8693102222222221,
+      "eval_BAC": 0.802,
+      "eval_MCC": 0.6195541306150731,
+      "eval_PR_AUC": 0.8205258347742059,
+      "eval_accuracy": 0.802,
+      "eval_loss": 0.31147220730781555,
+      "eval_runtime": 6.2204,
+      "eval_samples_per_second": 241.144,
+      "eval_steps_per_second": 7.556,
+      "step": 1032
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1032,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 0.5274993372148938,
+    "learning_rate": 0.00015110967149175106,
+    "num_train_epochs": 6,
+    "temperature": 12
+  }
+}

run-0/checkpoint-1032/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e464c1afaeff5573aad80fae160b03b120959cad188d7058bdf60c851a35ea4
+size 5240

run-0/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-0/checkpoint-860/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907d9a2a8f574f302e4080f498821062126c7df1f1c6ba3584de09def9f655a7
+size 17549312

run-0/checkpoint-860/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0927bf29e2bb897ec0112194a11ba4ff6021db466a3589ba3ca178c444d0dc8
+size 35123898

run-0/checkpoint-860/rng_state.pth

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

run-0/checkpoint-860/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7145304de1c6a909fcb1f8966f7b3e581149508e9366c1b6db8b6ab4f9df5137
+size 1064

run-0/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-0/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-0/checkpoint-860/trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_metric": 0.8013333333333333,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-0/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": 0.40991276502609253,
+      "learning_rate": 0.00012592472624312588,
+      "loss": 0.3541,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8165582222222223,
+      "eval_BAC": 0.7313333333333334,
+      "eval_MCC": 0.4637400760214038,
+      "eval_PR_AUC": 0.7669251828483298,
+      "eval_accuracy": 0.7313333333333333,
+      "eval_loss": 0.33297714591026306,
+      "eval_runtime": 5.88,
+      "eval_samples_per_second": 255.102,
+      "eval_steps_per_second": 7.993,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7852521538734436,
+      "learning_rate": 0.0001007397809945007,
+      "loss": 0.3395,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8291591111111111,
+      "eval_BAC": 0.7453333333333334,
+      "eval_MCC": 0.5307731566207068,
+      "eval_PR_AUC": 0.7773307731479302,
+      "eval_accuracy": 0.7453333333333333,
+      "eval_loss": 0.32892802357673645,
+      "eval_runtime": 5.8962,
+      "eval_samples_per_second": 254.401,
+      "eval_steps_per_second": 7.971,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.8841129541397095,
+      "learning_rate": 7.555483574587553e-05,
+      "loss": 0.3354,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.8464124444444445,
+      "eval_BAC": 0.7846666666666666,
+      "eval_MCC": 0.585494859343166,
+      "eval_PR_AUC": 0.8098393230420249,
+      "eval_accuracy": 0.7846666666666666,
+      "eval_loss": 0.3203962743282318,
+      "eval_runtime": 6.0014,
+      "eval_samples_per_second": 249.942,
+      "eval_steps_per_second": 7.832,
+      "step": 516
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.4307535886764526,
+      "learning_rate": 5.036989049725035e-05,
+      "loss": 0.3283,
+      "step": 688
+    },
+    {
+      "epoch": 4.0,
+      "eval_AUC": 0.853079111111111,
+      "eval_BAC": 0.7986666666666666,
+      "eval_MCC": 0.6048666115791026,
+      "eval_PR_AUC": 0.8161612377554972,
+      "eval_accuracy": 0.7986666666666666,
+      "eval_loss": 0.3148361146450043,
+      "eval_runtime": 6.1071,
+      "eval_samples_per_second": 245.616,
+      "eval_steps_per_second": 7.696,
+      "step": 688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.2096748352050781,
+      "learning_rate": 2.5184945248625176e-05,
+      "loss": 0.3238,
+      "step": 860
+    },
+    {
+      "epoch": 5.0,
+      "eval_AUC": 0.8653653333333333,
+      "eval_BAC": 0.8013333333333333,
+      "eval_MCC": 0.6179940224891067,
+      "eval_PR_AUC": 0.8210118227054324,
+      "eval_accuracy": 0.8013333333333333,
+      "eval_loss": 0.31179723143577576,
+      "eval_runtime": 6.1725,
+      "eval_samples_per_second": 243.014,
+      "eval_steps_per_second": 7.614,
+      "step": 860
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1032,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 0.5274993372148938,
+    "learning_rate": 0.00015110967149175106,
+    "num_train_epochs": 6,
+    "temperature": 12
+  }
+}

run-0/checkpoint-860/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e464c1afaeff5573aad80fae160b03b120959cad188d7058bdf60c851a35ea4
+size 5240

run-1/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-1/checkpoint-172/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:481ef6f946a20ace36469d3759ab47132144bae42fb7955308b2bae4edba13ac
+size 17549312

run-1/checkpoint-172/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f8e231518631e02105169cacddd21c1c007ce76f7786852cbbd5b89bc54f65d
+size 35123898

run-1/checkpoint-172/rng_state.pth

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

run-1/checkpoint-172/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef5c99637887adfa8b1e9c90a6f87ffb1549d6b3570d5357c522ab30a7c78678
+size 1064

run-1/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-1/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-1/checkpoint-172/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.5,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-1/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": 0.10513057559728622,
+      "learning_rate": 0.0004697676642472769,
+      "loss": 0.0495,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8095893333333333,
+      "eval_BAC": 0.5,
+      "eval_MCC": 0.0,
+      "eval_PR_AUC": 0.7634102804324954,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.04859978333115578,
+      "eval_runtime": 6.131,
+      "eval_samples_per_second": 244.658,
+      "eval_steps_per_second": 7.666,
+      "step": 172
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 688,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 0.06190377563487581,
+    "learning_rate": 0.0006263568856630359,
+    "num_train_epochs": 4,
+    "temperature": 15
+  }
+}

run-1/checkpoint-172/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fa2a37044ef6ce8c62252f894198b0ff65c98d3ddcbefc318c73358bb5c9023
+size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e464c1afaeff5573aad80fae160b03b120959cad188d7058bdf60c851a35ea4
+oid sha256:0fa2a37044ef6ce8c62252f894198b0ff65c98d3ddcbefc318c73358bb5c9023
 size 5240