Training in progress, epoch 1

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0316611c4503c75489f46368494e8c43c9093f031501ced7097d79b8c54051ff
-size 6432
+oid sha256:42d95767feb7e3c3fb4746429e91a4206d48706dfed347c705bac97195194aae
+size 11136

logs/events.out.tfevents.1721964285.98acc6742512.15262.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:579146e213c74f2e9dfe4a9ade7d3a8bc246ac8d6feca02f515a476b29c9681f
+size 5708

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80586fa2bf21ee8f8f6cc04b98c10247a622a87795a4cce5c5e3569d67e1356b
+oid sha256:e6bf85f6c98e71aa9127c0c1d4c10efd98d59ce3243c71f646479e86c33664b2
 size 17549312

run-12/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-12/checkpoint-1204/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8151f01ed93e213c40594fa0b0b762f18ccd8fbfef92e9f4f7d5939a63e5f1ac
+size 17549312

run-12/checkpoint-1204/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0433bbc5831185dc44c21bd56695f732660cfb5df5f2d60fe95f97345953a1c
+size 35123898

run-12/checkpoint-1204/rng_state.pth

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

run-12/checkpoint-1204/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a65aefcab3b13bfc6ac43eb208c108bebe148e6a8c37b4a4c4334f7043d385f5
+size 1064

run-12/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-12/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-12/checkpoint-1204/trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_metric": 0.8186666666666667,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-12/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": 1.1232905387878418,
+      "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
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.4932422637939453,
+      "learning_rate": 0.00020929627746953138,
+      "loss": 0.5544,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8558471111111111,
+      "eval_BAC": 0.7973333333333333,
+      "eval_MCC": 0.611346783233452,
+      "eval_PR_AUC": 0.7974856134881959,
+      "eval_accuracy": 0.7973333333333333,
+      "eval_loss": 0.48413094878196716,
+      "eval_runtime": 6.2441,
+      "eval_samples_per_second": 240.225,
+      "eval_steps_per_second": 7.527,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.206993579864502,
+      "learning_rate": 0.00017441356455794282,
+      "loss": 0.5269,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.869047111111111,
+      "eval_BAC": 0.8073333333333333,
+      "eval_MCC": 0.6186526320925123,
+      "eval_PR_AUC": 0.8255089698845253,
+      "eval_accuracy": 0.8073333333333333,
+      "eval_loss": 0.462238073348999,
+      "eval_runtime": 6.1857,
+      "eval_samples_per_second": 242.494,
+      "eval_steps_per_second": 7.598,
+      "step": 516
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.8272817134857178,
+      "learning_rate": 0.00013953085164635426,
+      "loss": 0.5091,
+      "step": 688
+    },
+    {
+      "epoch": 4.0,
+      "eval_AUC": 0.8710062222222221,
+      "eval_BAC": 0.8073333333333333,
+      "eval_MCC": 0.6192417370132357,
+      "eval_PR_AUC": 0.8309641091365022,
+      "eval_accuracy": 0.8073333333333333,
+      "eval_loss": 0.4574926793575287,
+      "eval_runtime": 6.2565,
+      "eval_samples_per_second": 239.749,
+      "eval_steps_per_second": 7.512,
+      "step": 688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.853664875030518,
+      "learning_rate": 0.00010464813873476569,
+      "loss": 0.4963,
+      "step": 860
+    },
+    {
+      "epoch": 5.0,
+      "eval_AUC": 0.8805848888888889,
+      "eval_BAC": 0.8160000000000001,
+      "eval_MCC": 0.6374654004896197,
+      "eval_PR_AUC": 0.8421704428541694,
+      "eval_accuracy": 0.816,
+      "eval_loss": 0.4484695494174957,
+      "eval_runtime": 6.2529,
+      "eval_samples_per_second": 239.89,
+      "eval_steps_per_second": 7.517,
+      "step": 860
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 7.934250831604004,
+      "learning_rate": 6.976542582317713e-05,
+      "loss": 0.4847,
+      "step": 1032
+    },
+    {
+      "epoch": 6.0,
+      "eval_AUC": 0.8876497777777779,
+      "eval_BAC": 0.812,
+      "eval_MCC": 0.6287483531185474,
+      "eval_PR_AUC": 0.8583715628947348,
+      "eval_accuracy": 0.812,
+      "eval_loss": 0.4442266523838043,
+      "eval_runtime": 6.248,
+      "eval_samples_per_second": 240.075,
+      "eval_steps_per_second": 7.522,
+      "step": 1032
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.736802101135254,
+      "learning_rate": 3.4882712911588564e-05,
+      "loss": 0.4798,
+      "step": 1204
+    },
+    {
+      "epoch": 7.0,
+      "eval_AUC": 0.8849973333333332,
+      "eval_BAC": 0.8186666666666667,
+      "eval_MCC": 0.6409902876192075,
+      "eval_PR_AUC": 0.853489275135159,
+      "eval_accuracy": 0.8186666666666667,
+      "eval_loss": 0.44571828842163086,
+      "eval_runtime": 6.2276,
+      "eval_samples_per_second": 240.864,
+      "eval_steps_per_second": 7.547,
+      "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": 0.9633802106648812,
+    "learning_rate": 0.0002790617032927085,
+    "num_train_epochs": 8,
+    "temperature": 2
+  }
+}

run-12/checkpoint-1204/training_args.bin

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

run-12/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-12/checkpoint-1376/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:173082c452974a7b1983267fd57bdb0ae829e8a79d4f007ef086f7130c91175c
+size 17549312

run-12/checkpoint-1376/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb122467e19583516d8bbaa074871bd0ac898e013e8f7fa2d3674662ead30f09
+size 35123898

run-12/checkpoint-1376/rng_state.pth

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

run-12/checkpoint-1376/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:752a0543acd8df33f67128f8201e54afdc5003b672ee869bd38504bb03f65603
+size 1064

run-12/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-12/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-12/checkpoint-1376/trainer_state.json

@@ -0,0 +1,198 @@
+{
+  "best_metric": 0.82,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-12/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": 1.1232905387878418,
+      "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
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.4932422637939453,
+      "learning_rate": 0.00020929627746953138,
+      "loss": 0.5544,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8558471111111111,
+      "eval_BAC": 0.7973333333333333,
+      "eval_MCC": 0.611346783233452,
+      "eval_PR_AUC": 0.7974856134881959,
+      "eval_accuracy": 0.7973333333333333,
+      "eval_loss": 0.48413094878196716,
+      "eval_runtime": 6.2441,
+      "eval_samples_per_second": 240.225,
+      "eval_steps_per_second": 7.527,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.206993579864502,
+      "learning_rate": 0.00017441356455794282,
+      "loss": 0.5269,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.869047111111111,
+      "eval_BAC": 0.8073333333333333,
+      "eval_MCC": 0.6186526320925123,
+      "eval_PR_AUC": 0.8255089698845253,
+      "eval_accuracy": 0.8073333333333333,
+      "eval_loss": 0.462238073348999,
+      "eval_runtime": 6.1857,
+      "eval_samples_per_second": 242.494,
+      "eval_steps_per_second": 7.598,
+      "step": 516
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.8272817134857178,
+      "learning_rate": 0.00013953085164635426,
+      "loss": 0.5091,
+      "step": 688
+    },
+    {
+      "epoch": 4.0,
+      "eval_AUC": 0.8710062222222221,
+      "eval_BAC": 0.8073333333333333,
+      "eval_MCC": 0.6192417370132357,
+      "eval_PR_AUC": 0.8309641091365022,
+      "eval_accuracy": 0.8073333333333333,
+      "eval_loss": 0.4574926793575287,
+      "eval_runtime": 6.2565,
+      "eval_samples_per_second": 239.749,
+      "eval_steps_per_second": 7.512,
+      "step": 688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.853664875030518,
+      "learning_rate": 0.00010464813873476569,
+      "loss": 0.4963,
+      "step": 860
+    },
+    {
+      "epoch": 5.0,
+      "eval_AUC": 0.8805848888888889,
+      "eval_BAC": 0.8160000000000001,
+      "eval_MCC": 0.6374654004896197,
+      "eval_PR_AUC": 0.8421704428541694,
+      "eval_accuracy": 0.816,
+      "eval_loss": 0.4484695494174957,
+      "eval_runtime": 6.2529,
+      "eval_samples_per_second": 239.89,
+      "eval_steps_per_second": 7.517,
+      "step": 860
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 7.934250831604004,
+      "learning_rate": 6.976542582317713e-05,
+      "loss": 0.4847,
+      "step": 1032
+    },
+    {
+      "epoch": 6.0,
+      "eval_AUC": 0.8876497777777779,
+      "eval_BAC": 0.812,
+      "eval_MCC": 0.6287483531185474,
+      "eval_PR_AUC": 0.8583715628947348,
+      "eval_accuracy": 0.812,
+      "eval_loss": 0.4442266523838043,
+      "eval_runtime": 6.248,
+      "eval_samples_per_second": 240.075,
+      "eval_steps_per_second": 7.522,
+      "step": 1032
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.736802101135254,
+      "learning_rate": 3.4882712911588564e-05,
+      "loss": 0.4798,
+      "step": 1204
+    },
+    {
+      "epoch": 7.0,
+      "eval_AUC": 0.8849973333333332,
+      "eval_BAC": 0.8186666666666667,
+      "eval_MCC": 0.6409902876192075,
+      "eval_PR_AUC": 0.853489275135159,
+      "eval_accuracy": 0.8186666666666667,
+      "eval_loss": 0.44571828842163086,
+      "eval_runtime": 6.2276,
+      "eval_samples_per_second": 240.864,
+      "eval_steps_per_second": 7.547,
+      "step": 1204
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.6544547080993652,
+      "learning_rate": 0.0,
+      "loss": 0.4764,
+      "step": 1376
+    },
+    {
+      "epoch": 8.0,
+      "eval_AUC": 0.8864657777777778,
+      "eval_BAC": 0.8200000000000001,
+      "eval_MCC": 0.6428059008066962,
+      "eval_PR_AUC": 0.8583912197964987,
+      "eval_accuracy": 0.82,
+      "eval_loss": 0.4388044774532318,
+      "eval_runtime": 6.2323,
+      "eval_samples_per_second": 240.68,
+      "eval_steps_per_second": 7.541,
+      "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": 0.9633802106648812,
+    "learning_rate": 0.0002790617032927085,
+    "num_train_epochs": 8,
+    "temperature": 2
+  }
+}

run-12/checkpoint-1376/training_args.bin

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

run-13/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-13/checkpoint-172/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6bf85f6c98e71aa9127c0c1d4c10efd98d59ce3243c71f646479e86c33664b2
+size 17549312

run-13/checkpoint-172/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a23103e0ed847d60d6a8dfba0a8b3d152520e26495b17f0a59c1c82c67347b
+size 35123898

run-13/checkpoint-172/rng_state.pth

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

run-13/checkpoint-172/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9ad743a8cbba1c7374abc1d35a0d0145e169aa4f057d45ae0a50de32ed9bbfc
+size 1064

run-13/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-13/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-13/checkpoint-172/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.738,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-13/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": 1.6519217491149902,
+      "learning_rate": 0.0003489409909619128,
+      "loss": 0.6241,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8201937777777778,
+      "eval_BAC": 0.738,
+      "eval_MCC": 0.4761528166708038,
+      "eval_PR_AUC": 0.7788333782261532,
+      "eval_accuracy": 0.738,
+      "eval_loss": 0.5376982688903809,
+      "eval_runtime": 6.2979,
+      "eval_samples_per_second": 238.174,
+      "eval_steps_per_second": 7.463,
+      "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": 0.9793694957428477,
+    "learning_rate": 0.0003877122121799031,
+    "num_train_epochs": 10,
+    "temperature": 8
+  }
+}

run-13/checkpoint-172/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5f5a036df1b03e4a4ba9a6e0ee0d631925c8ae6af2604af8ddb074e8926e2a8
+size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d50e4f7ab6447df633273fe08e7e11f04b1d23b2e8a33c7570cd79f5951df51
+oid sha256:d5f5a036df1b03e4a4ba9a6e0ee0d631925c8ae6af2604af8ddb074e8926e2a8
 size 5240