Training in progress, epoch 1

logs/events.out.tfevents.1721963780.98acc6742512.15262.12

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a9a4516fdd3b7e37246ab4b923aa374cdb7fb97b2a0455c42ad8e1375e1dcf7
-size 6433
+oid sha256:ac968270ab0b3253904bf2cf5bc4b1d1f044326b26c490a2b9e1ea79a20d9a7d
+size 11137

logs/events.out.tfevents.1721964033.98acc6742512.15262.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ecbe9df3a52c0c08856ff050181ca4544e71072e3a038564edc349883f645c9
+size 5707

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f98a237992fe2bb816274230d277cabcab5b3eae040c5eefa75ccca238d200ab
+oid sha256:14fdfcfe9061a09edda20b60e554d6b0c5ba3388e70cd83e25b1dfc70581121d
 size 17549312

run-11/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-11/checkpoint-1204/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bbf1fa380484480004f69a37e8a6ae198ad5837967aab480c39ec0c1113efcd
+size 17549312

run-11/checkpoint-1204/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35fd99c8c6868fcb79cf8ef08a908b9be520d8a3c67e92b1152f90c4cdf4ef66
+size 35123898

run-11/checkpoint-1204/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4404160742a334aa27fbb21c3241578919c1efefcab10b400b543b1d691ccc6d
+size 14308

run-11/checkpoint-1204/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b822515287f90b218d3a10f32a5156f4bc0a524ede8a86ca5445761d191a50b5
+size 1064

run-11/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-11/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-11/checkpoint-1204/trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_metric": 0.818,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-11/checkpoint-1204",
+  "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": 1.173068881034851,
+      "learning_rate": 0.00024337376165851695,
+      "loss": 0.6049,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8273706666666667,
+      "eval_BAC": 0.7413333333333333,
+      "eval_MCC": 0.4850333676414723,
+      "eval_PR_AUC": 0.7881657633117372,
+      "eval_accuracy": 0.7413333333333333,
+      "eval_loss": 0.5346564650535583,
+      "eval_runtime": 6.256,
+      "eval_samples_per_second": 239.768,
+      "eval_steps_per_second": 7.513,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.4093000888824463,
+      "learning_rate": 0.00020860608142158596,
+      "loss": 0.5475,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8532853333333333,
+      "eval_BAC": 0.7966666666666666,
+      "eval_MCC": 0.6114050721892912,
+      "eval_PR_AUC": 0.7888869116793986,
+      "eval_accuracy": 0.7966666666666666,
+      "eval_loss": 0.48248833417892456,
+      "eval_runtime": 6.2583,
+      "eval_samples_per_second": 239.682,
+      "eval_steps_per_second": 7.51,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.5168275833129883,
+      "learning_rate": 0.00017383840118465497,
+      "loss": 0.521,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.8562666666666667,
+      "eval_BAC": 0.798,
+      "eval_MCC": 0.5978527601704366,
+      "eval_PR_AUC": 0.8147153641772997,
+      "eval_accuracy": 0.798,
+      "eval_loss": 0.4632047414779663,
+      "eval_runtime": 6.2642,
+      "eval_samples_per_second": 239.455,
+      "eval_steps_per_second": 7.503,
+      "step": 516
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.0364439487457275,
+      "learning_rate": 0.00013907072094772397,
+      "loss": 0.5067,
+      "step": 688
+    },
+    {
+      "epoch": 4.0,
+      "eval_AUC": 0.8710017777777778,
+      "eval_BAC": 0.8026666666666666,
+      "eval_MCC": 0.6086337734330317,
+      "eval_PR_AUC": 0.8431966996463283,
+      "eval_accuracy": 0.8026666666666666,
+      "eval_loss": 0.4548323452472687,
+      "eval_runtime": 6.2602,
+      "eval_samples_per_second": 239.609,
+      "eval_steps_per_second": 7.508,
+      "step": 688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.948005199432373,
+      "learning_rate": 0.00010430304071079298,
+      "loss": 0.496,
+      "step": 860
+    },
+    {
+      "epoch": 5.0,
+      "eval_AUC": 0.8774115555555555,
+      "eval_BAC": 0.8133333333333332,
+      "eval_MCC": 0.6399469848044845,
+      "eval_PR_AUC": 0.8344867532038169,
+      "eval_accuracy": 0.8133333333333334,
+      "eval_loss": 0.45315295457839966,
+      "eval_runtime": 6.257,
+      "eval_samples_per_second": 239.731,
+      "eval_steps_per_second": 7.512,
+      "step": 860
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 7.4915666580200195,
+      "learning_rate": 6.953536047386199e-05,
+      "loss": 0.4845,
+      "step": 1032
+    },
+    {
+      "epoch": 6.0,
+      "eval_AUC": 0.8858737777777778,
+      "eval_BAC": 0.8113333333333332,
+      "eval_MCC": 0.6275096493938598,
+      "eval_PR_AUC": 0.8524215878184646,
+      "eval_accuracy": 0.8113333333333334,
+      "eval_loss": 0.44440844655036926,
+      "eval_runtime": 6.2656,
+      "eval_samples_per_second": 239.403,
+      "eval_steps_per_second": 7.501,
+      "step": 1032
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.649087905883789,
+      "learning_rate": 3.476768023693099e-05,
+      "loss": 0.4771,
+      "step": 1204
+    },
+    {
+      "epoch": 7.0,
+      "eval_AUC": 0.8873937777777777,
+      "eval_BAC": 0.8180000000000001,
+      "eval_MCC": 0.6409466868541137,
+      "eval_PR_AUC": 0.8535373088628392,
+      "eval_accuracy": 0.818,
+      "eval_loss": 0.43640071153640747,
+      "eval_runtime": 6.2505,
+      "eval_samples_per_second": 239.982,
+      "eval_steps_per_second": 7.519,
+      "step": 1204
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1376,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "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": 3152644110000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9508242983728342,
+    "learning_rate": 0.00027814144189544795,
+    "num_train_epochs": 8,
+    "temperature": 2
+  }
+}

run-11/checkpoint-1204/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c34daadb74657e0250649c99c809ed0c04f4fb815b36eb44644c8403fdf072
+size 5240

run-11/checkpoint-1376/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-11/checkpoint-1376/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce58bc99dcbd91e647d3b6b43a35473226e013935977d6667387f3f13b02b35d
+size 17549312

run-11/checkpoint-1376/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97c7860c5f9bc1c05615e5a8d43a3a058b3855b79a7b338438b17a158c4667f4
+size 35123898

run-11/checkpoint-1376/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edaf180ca6adccc71bbccb352ad77ce0fa3542e9d87badbbada21fe981422321
+size 14308

run-11/checkpoint-1376/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d47b980b0c8a7546fee8320406f9109930106684894695f32a7c9368b45850a
+size 1064

run-11/checkpoint-1376/special_tokens_map.json

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

run-11/checkpoint-1376/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-11/checkpoint-1376/trainer_state.json

@@ -0,0 +1,198 @@
+{
+  "best_metric": 0.824,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-11/checkpoint-1376",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 1376,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.173068881034851,
+      "learning_rate": 0.00024337376165851695,
+      "loss": 0.6049,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8273706666666667,
+      "eval_BAC": 0.7413333333333333,
+      "eval_MCC": 0.4850333676414723,
+      "eval_PR_AUC": 0.7881657633117372,
+      "eval_accuracy": 0.7413333333333333,
+      "eval_loss": 0.5346564650535583,
+      "eval_runtime": 6.256,
+      "eval_samples_per_second": 239.768,
+      "eval_steps_per_second": 7.513,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.4093000888824463,
+      "learning_rate": 0.00020860608142158596,
+      "loss": 0.5475,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8532853333333333,
+      "eval_BAC": 0.7966666666666666,
+      "eval_MCC": 0.6114050721892912,
+      "eval_PR_AUC": 0.7888869116793986,
+      "eval_accuracy": 0.7966666666666666,
+      "eval_loss": 0.48248833417892456,
+      "eval_runtime": 6.2583,
+      "eval_samples_per_second": 239.682,
+      "eval_steps_per_second": 7.51,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.5168275833129883,
+      "learning_rate": 0.00017383840118465497,
+      "loss": 0.521,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.8562666666666667,
+      "eval_BAC": 0.798,
+      "eval_MCC": 0.5978527601704366,
+      "eval_PR_AUC": 0.8147153641772997,
+      "eval_accuracy": 0.798,
+      "eval_loss": 0.4632047414779663,
+      "eval_runtime": 6.2642,
+      "eval_samples_per_second": 239.455,
+      "eval_steps_per_second": 7.503,
+      "step": 516
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.0364439487457275,
+      "learning_rate": 0.00013907072094772397,
+      "loss": 0.5067,
+      "step": 688
+    },
+    {
+      "epoch": 4.0,
+      "eval_AUC": 0.8710017777777778,
+      "eval_BAC": 0.8026666666666666,
+      "eval_MCC": 0.6086337734330317,
+      "eval_PR_AUC": 0.8431966996463283,
+      "eval_accuracy": 0.8026666666666666,
+      "eval_loss": 0.4548323452472687,
+      "eval_runtime": 6.2602,
+      "eval_samples_per_second": 239.609,
+      "eval_steps_per_second": 7.508,
+      "step": 688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.948005199432373,
+      "learning_rate": 0.00010430304071079298,
+      "loss": 0.496,
+      "step": 860
+    },
+    {
+      "epoch": 5.0,
+      "eval_AUC": 0.8774115555555555,
+      "eval_BAC": 0.8133333333333332,
+      "eval_MCC": 0.6399469848044845,
+      "eval_PR_AUC": 0.8344867532038169,
+      "eval_accuracy": 0.8133333333333334,
+      "eval_loss": 0.45315295457839966,
+      "eval_runtime": 6.257,
+      "eval_samples_per_second": 239.731,
+      "eval_steps_per_second": 7.512,
+      "step": 860
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 7.4915666580200195,
+      "learning_rate": 6.953536047386199e-05,
+      "loss": 0.4845,
+      "step": 1032
+    },
+    {
+      "epoch": 6.0,
+      "eval_AUC": 0.8858737777777778,
+      "eval_BAC": 0.8113333333333332,
+      "eval_MCC": 0.6275096493938598,
+      "eval_PR_AUC": 0.8524215878184646,
+      "eval_accuracy": 0.8113333333333334,
+      "eval_loss": 0.44440844655036926,
+      "eval_runtime": 6.2656,
+      "eval_samples_per_second": 239.403,
+      "eval_steps_per_second": 7.501,
+      "step": 1032
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.649087905883789,
+      "learning_rate": 3.476768023693099e-05,
+      "loss": 0.4771,
+      "step": 1204
+    },
+    {
+      "epoch": 7.0,
+      "eval_AUC": 0.8873937777777777,
+      "eval_BAC": 0.8180000000000001,
+      "eval_MCC": 0.6409466868541137,
+      "eval_PR_AUC": 0.8535373088628392,
+      "eval_accuracy": 0.818,
+      "eval_loss": 0.43640071153640747,
+      "eval_runtime": 6.2505,
+      "eval_samples_per_second": 239.982,
+      "eval_steps_per_second": 7.519,
+      "step": 1204
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.1959824562072754,
+      "learning_rate": 0.0,
+      "loss": 0.4739,
+      "step": 1376
+    },
+    {
+      "epoch": 8.0,
+      "eval_AUC": 0.8897351111111111,
+      "eval_BAC": 0.8240000000000001,
+      "eval_MCC": 0.651352819389177,
+      "eval_PR_AUC": 0.8590307681592729,
+      "eval_accuracy": 0.824,
+      "eval_loss": 0.4306699335575104,
+      "eval_runtime": 6.2445,
+      "eval_samples_per_second": 240.211,
+      "eval_steps_per_second": 7.527,
+      "step": 1376
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1376,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "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": 3603021840000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9508242983728342,
+    "learning_rate": 0.00027814144189544795,
+    "num_train_epochs": 8,
+    "temperature": 2
+  }
+}

run-11/checkpoint-1376/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c34daadb74657e0250649c99c809ed0c04f4fb815b36eb44644c8403fdf072
+size 5240

run-12/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-12/checkpoint-172/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14fdfcfe9061a09edda20b60e554d6b0c5ba3388e70cd83e25b1dfc70581121d
+size 17549312

run-12/checkpoint-172/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cd94b5122b763e8c6be7234547e47a50b0b840ce7389b11403e1ff133d4d8d2
+size 35123898

run-12/checkpoint-172/rng_state.pth

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

run-12/checkpoint-172/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:142f817588faa52be4f42af2594882b843b702be715b40fc13fcb9869af39976
+size 1064

run-12/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-12/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-12/checkpoint-172/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.7453333333333333,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-12/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": 1.1232905387878418,
+      "learning_rate": 0.00024417899038111995,
+      "loss": 0.6117,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8254151111111111,
+      "eval_BAC": 0.7453333333333334,
+      "eval_MCC": 0.4912976797633764,
+      "eval_PR_AUC": 0.786302392146851,
+      "eval_accuracy": 0.7453333333333333,
+      "eval_loss": 0.5350800156593323,
+      "eval_runtime": 6.3041,
+      "eval_samples_per_second": 237.94,
+      "eval_steps_per_second": 7.455,
+      "step": 172
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1376,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "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": 0.9633802106648812,
+    "learning_rate": 0.0002790617032927085,
+    "num_train_epochs": 8,
+    "temperature": 2
+  }
+}

run-12/checkpoint-172/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d50e4f7ab6447df633273fe08e7e11f04b1d23b2e8a33c7570cd79f5951df51
+size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00c34daadb74657e0250649c99c809ed0c04f4fb815b36eb44644c8403fdf072
+oid sha256:6d50e4f7ab6447df633273fe08e7e11f04b1d23b2e8a33c7570cd79f5951df51
 size 5240