Training in progress, epoch 1

logs/events.out.tfevents.1721962568.98acc6742512.15262.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:046ce3c9d615e9e499d90cc3b73bf6c22fb2c53d514b9fb5d80936b903ca0f4b
-size 6433
+oid sha256:6a6b63ce669785bc1963ea93a96c9b98e2584680c9a3da8d064eab525f47cc48
+size 12587

logs/events.out.tfevents.1721962879.98acc6742512.15262.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69aaa85072b5b48c1dc58cea6a0528f2fb55af9e67d2d6f9581633f7f3aa028d
+size 5707

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7db7573c7d58fccae5f4330b8c3198c712b008c25e4a2949b105294dc6d14851
+oid sha256:b3495e8233722ea9d7d383500a9885a5eb0d2109ab47d55bfc5540a43af54e46
 size 17549312

run-2/checkpoint-1548/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-2/checkpoint-1548/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b993a69647f4da2ddefbac3afa394d1242a6d3a98848dbe6840c416d09fd0310
+size 17549312

run-2/checkpoint-1548/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e2c364be10143ba6576de1138c89971ff43694d9fe0cb5dc7069bd015ea6fa3
+size 35123898

run-2/checkpoint-1548/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56ddbbc87b36b5871313fc71dae1a22c3ede13ff5a31af8b745553ca14ae3bba
+size 14308

run-2/checkpoint-1548/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ed3774676d30c8778f81492662674301fe444a2bf18f6077e0c63b85ea07a7
+size 1064

run-2/checkpoint-1548/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-1548/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-2/checkpoint-1548/trainer_state.json

@@ -0,0 +1,218 @@
+{
+  "best_metric": 0.79,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-2/checkpoint-1548",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 1548,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.39246517419815063,
+      "learning_rate": 4.639522353304605e-05,
+      "loss": 0.2489,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.786481777777778,
+      "eval_BAC": 0.6966666666666667,
+      "eval_MCC": 0.4004741770824115,
+      "eval_PR_AUC": 0.7486102682312443,
+      "eval_accuracy": 0.6966666666666667,
+      "eval_loss": 0.23812349140644073,
+      "eval_runtime": 6.2157,
+      "eval_samples_per_second": 241.324,
+      "eval_steps_per_second": 7.561,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.45007961988449097,
+      "learning_rate": 4.1240198696040935e-05,
+      "loss": 0.2402,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8126222222222222,
+      "eval_BAC": 0.7553333333333334,
+      "eval_MCC": 0.5408380051918336,
+      "eval_PR_AUC": 0.7628286445519327,
+      "eval_accuracy": 0.7553333333333333,
+      "eval_loss": 0.23252661526203156,
+      "eval_runtime": 6.2733,
+      "eval_samples_per_second": 239.107,
+      "eval_steps_per_second": 7.492,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5242908596992493,
+      "learning_rate": 3.608517385903581e-05,
+      "loss": 0.2384,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.8210719999999999,
+      "eval_BAC": 0.754,
+      "eval_MCC": 0.5442085309980096,
+      "eval_PR_AUC": 0.7771659186047205,
+      "eval_accuracy": 0.754,
+      "eval_loss": 0.23356583714485168,
+      "eval_runtime": 6.2379,
+      "eval_samples_per_second": 240.465,
+      "eval_steps_per_second": 7.535,
+      "step": 516
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.7818685173988342,
+      "learning_rate": 3.0930149022030695e-05,
+      "loss": 0.237,
+      "step": 688
+    },
+    {
+      "epoch": 4.0,
+      "eval_AUC": 0.8297351111111111,
+      "eval_BAC": 0.7686666666666666,
+      "eval_MCC": 0.5525864831739952,
+      "eval_PR_AUC": 0.7854176937233266,
+      "eval_accuracy": 0.7686666666666667,
+      "eval_loss": 0.2301863133907318,
+      "eval_runtime": 6.2464,
+      "eval_samples_per_second": 240.136,
+      "eval_steps_per_second": 7.524,
+      "step": 688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.7255853414535522,
+      "learning_rate": 2.577512418502558e-05,
+      "loss": 0.2362,
+      "step": 860
+    },
+    {
+      "epoch": 5.0,
+      "eval_AUC": 0.836256,
+      "eval_BAC": 0.7666666666666666,
+      "eval_MCC": 0.5542293013644021,
+      "eval_PR_AUC": 0.7972297123276614,
+      "eval_accuracy": 0.7666666666666667,
+      "eval_loss": 0.22993715107440948,
+      "eval_runtime": 6.2748,
+      "eval_samples_per_second": 239.051,
+      "eval_steps_per_second": 7.49,
+      "step": 860
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.7448613047599792,
+      "learning_rate": 2.0620099348020468e-05,
+      "loss": 0.235,
+      "step": 1032
+    },
+    {
+      "epoch": 6.0,
+      "eval_AUC": 0.8438133333333333,
+      "eval_BAC": 0.778,
+      "eval_MCC": 0.5714092913131209,
+      "eval_PR_AUC": 0.8061543385382132,
+      "eval_accuracy": 0.778,
+      "eval_loss": 0.22893689572811127,
+      "eval_runtime": 6.2414,
+      "eval_samples_per_second": 240.331,
+      "eval_steps_per_second": 7.53,
+      "step": 1032
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.7925253510475159,
+      "learning_rate": 1.5465074511015347e-05,
+      "loss": 0.2345,
+      "step": 1204
+    },
+    {
+      "epoch": 7.0,
+      "eval_AUC": 0.8473991111111112,
+      "eval_BAC": 0.782,
+      "eval_MCC": 0.5792569729386494,
+      "eval_PR_AUC": 0.8108360182006333,
+      "eval_accuracy": 0.782,
+      "eval_loss": 0.2287604957818985,
+      "eval_runtime": 6.2713,
+      "eval_samples_per_second": 239.186,
+      "eval_steps_per_second": 7.494,
+      "step": 1204
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.35333141684532166,
+      "learning_rate": 1.0310049674010234e-05,
+      "loss": 0.234,
+      "step": 1376
+    },
+    {
+      "epoch": 8.0,
+      "eval_AUC": 0.8490613333333333,
+      "eval_BAC": 0.788,
+      "eval_MCC": 0.5830155950947427,
+      "eval_PR_AUC": 0.8120541754208705,
+      "eval_accuracy": 0.788,
+      "eval_loss": 0.2279704362154007,
+      "eval_runtime": 6.2416,
+      "eval_samples_per_second": 240.322,
+      "eval_steps_per_second": 7.53,
+      "step": 1376
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.44008931517601013,
+      "learning_rate": 5.155024837005117e-06,
+      "loss": 0.2331,
+      "step": 1548
+    },
+    {
+      "epoch": 9.0,
+      "eval_AUC": 0.8531626666666667,
+      "eval_BAC": 0.79,
+      "eval_MCC": 0.5917962039710227,
+      "eval_PR_AUC": 0.81588940138238,
+      "eval_accuracy": 0.79,
+      "eval_loss": 0.22790811955928802,
+      "eval_runtime": 6.2673,
+      "eval_samples_per_second": 239.338,
+      "eval_steps_per_second": 7.499,
+      "step": 1548
+    }
+  ],
+  "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": 4053399570000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.3558486326039224,
+    "learning_rate": 5.155024837005116e-05,
+    "num_train_epochs": 10,
+    "temperature": 4
+  }
+}

run-2/checkpoint-1548/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9bd69b3929a44bec8f4cb67348238146f431e97b360ab6f0d8fff3cfab94f36
+size 5240

run-2/checkpoint-1720/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-2/checkpoint-1720/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3e0b5eecfba82e96ce61c64cb38b8b7b70a6b98fa441860533b1b7ab9eae566
+size 17549312

run-2/checkpoint-1720/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84db242a46e69f4820ae45fca69a588201a74f6cf1d866606ffd30b8c1c550c7
+size 35123898

run-2/checkpoint-1720/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:906d505cd404ce212b8a0134eeccb5432e576aeee31e498d90e98c607a797df0
+size 14308

run-2/checkpoint-1720/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dda1c5ae369a9bf33460356500caa574117b7ce71e8f5aecdda5eac2138f43dc
+size 1064

run-2/checkpoint-1720/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-1720/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-2/checkpoint-1720/trainer_state.json

@@ -0,0 +1,238 @@
+{
+  "best_metric": 0.7926666666666666,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-2/checkpoint-1720",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 1720,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.39246517419815063,
+      "learning_rate": 4.639522353304605e-05,
+      "loss": 0.2489,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.786481777777778,
+      "eval_BAC": 0.6966666666666667,
+      "eval_MCC": 0.4004741770824115,
+      "eval_PR_AUC": 0.7486102682312443,
+      "eval_accuracy": 0.6966666666666667,
+      "eval_loss": 0.23812349140644073,
+      "eval_runtime": 6.2157,
+      "eval_samples_per_second": 241.324,
+      "eval_steps_per_second": 7.561,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.45007961988449097,
+      "learning_rate": 4.1240198696040935e-05,
+      "loss": 0.2402,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8126222222222222,
+      "eval_BAC": 0.7553333333333334,
+      "eval_MCC": 0.5408380051918336,
+      "eval_PR_AUC": 0.7628286445519327,
+      "eval_accuracy": 0.7553333333333333,
+      "eval_loss": 0.23252661526203156,
+      "eval_runtime": 6.2733,
+      "eval_samples_per_second": 239.107,
+      "eval_steps_per_second": 7.492,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5242908596992493,
+      "learning_rate": 3.608517385903581e-05,
+      "loss": 0.2384,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.8210719999999999,
+      "eval_BAC": 0.754,
+      "eval_MCC": 0.5442085309980096,
+      "eval_PR_AUC": 0.7771659186047205,
+      "eval_accuracy": 0.754,
+      "eval_loss": 0.23356583714485168,
+      "eval_runtime": 6.2379,
+      "eval_samples_per_second": 240.465,
+      "eval_steps_per_second": 7.535,
+      "step": 516
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.7818685173988342,
+      "learning_rate": 3.0930149022030695e-05,
+      "loss": 0.237,
+      "step": 688
+    },
+    {
+      "epoch": 4.0,
+      "eval_AUC": 0.8297351111111111,
+      "eval_BAC": 0.7686666666666666,
+      "eval_MCC": 0.5525864831739952,
+      "eval_PR_AUC": 0.7854176937233266,
+      "eval_accuracy": 0.7686666666666667,
+      "eval_loss": 0.2301863133907318,
+      "eval_runtime": 6.2464,
+      "eval_samples_per_second": 240.136,
+      "eval_steps_per_second": 7.524,
+      "step": 688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.7255853414535522,
+      "learning_rate": 2.577512418502558e-05,
+      "loss": 0.2362,
+      "step": 860
+    },
+    {
+      "epoch": 5.0,
+      "eval_AUC": 0.836256,
+      "eval_BAC": 0.7666666666666666,
+      "eval_MCC": 0.5542293013644021,
+      "eval_PR_AUC": 0.7972297123276614,
+      "eval_accuracy": 0.7666666666666667,
+      "eval_loss": 0.22993715107440948,
+      "eval_runtime": 6.2748,
+      "eval_samples_per_second": 239.051,
+      "eval_steps_per_second": 7.49,
+      "step": 860
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.7448613047599792,
+      "learning_rate": 2.0620099348020468e-05,
+      "loss": 0.235,
+      "step": 1032
+    },
+    {
+      "epoch": 6.0,
+      "eval_AUC": 0.8438133333333333,
+      "eval_BAC": 0.778,
+      "eval_MCC": 0.5714092913131209,
+      "eval_PR_AUC": 0.8061543385382132,
+      "eval_accuracy": 0.778,
+      "eval_loss": 0.22893689572811127,
+      "eval_runtime": 6.2414,
+      "eval_samples_per_second": 240.331,
+      "eval_steps_per_second": 7.53,
+      "step": 1032
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.7925253510475159,
+      "learning_rate": 1.5465074511015347e-05,
+      "loss": 0.2345,
+      "step": 1204
+    },
+    {
+      "epoch": 7.0,
+      "eval_AUC": 0.8473991111111112,
+      "eval_BAC": 0.782,
+      "eval_MCC": 0.5792569729386494,
+      "eval_PR_AUC": 0.8108360182006333,
+      "eval_accuracy": 0.782,
+      "eval_loss": 0.2287604957818985,
+      "eval_runtime": 6.2713,
+      "eval_samples_per_second": 239.186,
+      "eval_steps_per_second": 7.494,
+      "step": 1204
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.35333141684532166,
+      "learning_rate": 1.0310049674010234e-05,
+      "loss": 0.234,
+      "step": 1376
+    },
+    {
+      "epoch": 8.0,
+      "eval_AUC": 0.8490613333333333,
+      "eval_BAC": 0.788,
+      "eval_MCC": 0.5830155950947427,
+      "eval_PR_AUC": 0.8120541754208705,
+      "eval_accuracy": 0.788,
+      "eval_loss": 0.2279704362154007,
+      "eval_runtime": 6.2416,
+      "eval_samples_per_second": 240.322,
+      "eval_steps_per_second": 7.53,
+      "step": 1376
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.44008931517601013,
+      "learning_rate": 5.155024837005117e-06,
+      "loss": 0.2331,
+      "step": 1548
+    },
+    {
+      "epoch": 9.0,
+      "eval_AUC": 0.8531626666666667,
+      "eval_BAC": 0.79,
+      "eval_MCC": 0.5917962039710227,
+      "eval_PR_AUC": 0.81588940138238,
+      "eval_accuracy": 0.79,
+      "eval_loss": 0.22790811955928802,
+      "eval_runtime": 6.2673,
+      "eval_samples_per_second": 239.338,
+      "eval_steps_per_second": 7.499,
+      "step": 1548
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.5285153388977051,
+      "learning_rate": 0.0,
+      "loss": 0.2334,
+      "step": 1720
+    },
+    {
+      "epoch": 10.0,
+      "eval_AUC": 0.8541422222222221,
+      "eval_BAC": 0.7926666666666666,
+      "eval_MCC": 0.5969110830375018,
+      "eval_PR_AUC": 0.8163240976491174,
+      "eval_accuracy": 0.7926666666666666,
+      "eval_loss": 0.22778959572315216,
+      "eval_runtime": 6.2536,
+      "eval_samples_per_second": 239.861,
+      "eval_steps_per_second": 7.516,
+      "step": 1720
+    }
+  ],
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4503777300000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.3558486326039224,
+    "learning_rate": 5.155024837005116e-05,
+    "num_train_epochs": 10,
+    "temperature": 4
+  }
+}

run-2/checkpoint-1720/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9bd69b3929a44bec8f4cb67348238146f431e97b360ab6f0d8fff3cfab94f36
+size 5240

run-3/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-3/checkpoint-172/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3495e8233722ea9d7d383500a9885a5eb0d2109ab47d55bfc5540a43af54e46
+size 17549312

run-3/checkpoint-172/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1303c775d21d38e5c71ed40c51ed7ca99d15c3b7697999c48aaae77492d605c6
+size 35123898

run-3/checkpoint-172/rng_state.pth

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

run-3/checkpoint-172/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2bb1d4b5e2791068c8926802d6cab96c136572ea664c036db3c50400d9f9f4f
+size 1064

run-3/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-3/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-3/checkpoint-172/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.5333333333333333,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-3/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": 0.06025523692369461,
+      "learning_rate": 1.750045443660438e-05,
+      "loss": 0.0574,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.6860142222222222,
+      "eval_BAC": 0.5333333333333333,
+      "eval_MCC": 0.14834770727423166,
+      "eval_PR_AUC": 0.6557725052787473,
+      "eval_accuracy": 0.5333333333333333,
+      "eval_loss": 0.05601842328906059,
+      "eval_runtime": 6.3117,
+      "eval_samples_per_second": 237.654,
+      "eval_steps_per_second": 7.446,
+      "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": 0.07282268127135982,
+    "learning_rate": 2.333393924880584e-05,
+    "num_train_epochs": 4,
+    "temperature": 19
+  }
+}

run-3/checkpoint-172/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac229c98c6bdd9f587e559a419af2e54959e4f4e987fa74451dc16869d3838c
+size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9bd69b3929a44bec8f4cb67348238146f431e97b360ab6f0d8fff3cfab94f36
+oid sha256:3ac229c98c6bdd9f587e559a419af2e54959e4f4e987fa74451dc16869d3838c
 size 5240