Training in progress, epoch 1

logs/events.out.tfevents.1721965657.98acc6742512.15262.27

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:209a6aa6511a07803cabcf458b669ccdd12624d82049ee3aa7b0dab3c993da6b
-size 7158
+oid sha256:b784abbf0752af88734951e7bd940380965321f6b4184f81a141e2befc5de591
+size 8608

logs/events.out.tfevents.1721965807.98acc6742512.15262.28

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fa6602e63922e414ef00ba53f7d5d93aa14623b653210749c279a83b85d1a7b
+size 5707

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:195d39612fbbfad641911725252cdc92e48de9bb03d6b2b0151c2b10e7335188
+oid sha256:507e2ed80f7779bce039cb10a712a815967d5f7199a41ad0985044a2cce47617
 size 17549312

run-26/checkpoint-688/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-26/checkpoint-688/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9c1c961d132401f2799dd9f997505659cc8e463e1622ea996ecbe8307e4a713
+size 17549312

run-26/checkpoint-688/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b5ae1208a05aac2b90cfd54eacc597a5139cd263ea562213c6b2af16750854
+size 35123898

run-26/checkpoint-688/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1b1fea9cda5ce8cfa36db49d92878d70e7ecc73c289b2b17c8c4949a715ba6e
+size 14308

run-26/checkpoint-688/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5d0eea2ca9c15cfef379f04d45083752204b02c7d17e123dac9edf1ace38a6b
+size 1064

run-26/checkpoint-688/special_tokens_map.json

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

run-26/checkpoint-688/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-26/checkpoint-688/trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_metric": 0.802,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-26/checkpoint-516",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 688,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.019540548324585,
+      "learning_rate": 0.00010368996748543682,
+      "loss": 0.5941,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.819072,
+      "eval_BAC": 0.7366666666666667,
+      "eval_MCC": 0.47336741701441504,
+      "eval_PR_AUC": 0.7723271954821734,
+      "eval_accuracy": 0.7366666666666667,
+      "eval_loss": 0.5035012364387512,
+      "eval_runtime": 6.3714,
+      "eval_samples_per_second": 235.425,
+      "eval_steps_per_second": 7.377,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.5166783332824707,
+      "learning_rate": 9.072872154975722e-05,
+      "loss": 0.5442,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8454275555555554,
+      "eval_BAC": 0.7753333333333333,
+      "eval_MCC": 0.5820649492328364,
+      "eval_PR_AUC": 0.790134879283048,
+      "eval_accuracy": 0.7753333333333333,
+      "eval_loss": 0.4930420219898224,
+      "eval_runtime": 6.2243,
+      "eval_samples_per_second": 240.99,
+      "eval_steps_per_second": 7.551,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.6264541149139404,
+      "learning_rate": 7.776747561407761e-05,
+      "loss": 0.5232,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.8629688888888889,
+      "eval_BAC": 0.802,
+      "eval_MCC": 0.6107257017486105,
+      "eval_PR_AUC": 0.823189737884114,
+      "eval_accuracy": 0.802,
+      "eval_loss": 0.4630783796310425,
+      "eval_runtime": 6.2126,
+      "eval_samples_per_second": 241.445,
+      "eval_steps_per_second": 7.565,
+      "step": 516
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.5070528984069824,
+      "learning_rate": 6.480622967839802e-05,
+      "loss": 0.508,
+      "step": 688
+    },
+    {
+      "epoch": 4.0,
+      "eval_AUC": 0.8704533333333333,
+      "eval_BAC": 0.8013333333333332,
+      "eval_MCC": 0.6090140007758802,
+      "eval_PR_AUC": 0.8362687418122099,
+      "eval_accuracy": 0.8013333333333333,
+      "eval_loss": 0.4516940116882324,
+      "eval_runtime": 6.2633,
+      "eval_samples_per_second": 239.492,
+      "eval_steps_per_second": 7.504,
+      "step": 688
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1548,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "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": 1801510920000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9196094567227121,
+    "learning_rate": 0.00011665121342111642,
+    "num_train_epochs": 9,
+    "temperature": 22
+  }
+}

run-26/checkpoint-688/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d42d4503454c744ad29b146a95868f7aa17157675037f45e91972dc2de9576d5
+size 5240

run-27/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-27/checkpoint-172/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:507e2ed80f7779bce039cb10a712a815967d5f7199a41ad0985044a2cce47617
+size 17549312

run-27/checkpoint-172/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb0dbef203f507407d3375041c9e0f8fe54f9b962a6bd50a8a90d438c61ce8f
+size 35123898

run-27/checkpoint-172/rng_state.pth

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

run-27/checkpoint-172/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:017f2985713774d3e63fa2bdea09e035098c1a169b8ff6a3690e89228090f0fd
+size 1064

run-27/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-27/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-27/checkpoint-172/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.728,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-27/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": 0.47720852494239807,
+      "learning_rate": 0.0004943634319141483,
+      "loss": 0.2662,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8116800000000002,
+      "eval_BAC": 0.728,
+      "eval_MCC": 0.5123711940238413,
+      "eval_PR_AUC": 0.7608377598735417,
+      "eval_accuracy": 0.728,
+      "eval_loss": 0.25086572766304016,
+      "eval_runtime": 6.2262,
+      "eval_samples_per_second": 240.917,
+      "eval_steps_per_second": 7.549,
+      "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": 0.38379772759688324,
+    "learning_rate": 0.0005649867793304552,
+    "num_train_epochs": 8,
+    "temperature": 7
+  }
+}

run-27/checkpoint-172/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:172fde5e5d3589e7befbf9b642d485261863cd4e94a1de4ad47b4c5bfef5f722
+size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d42d4503454c744ad29b146a95868f7aa17157675037f45e91972dc2de9576d5
+oid sha256:172fde5e5d3589e7befbf9b642d485261863cd4e94a1de4ad47b4c5bfef5f722
 size 5240