Training in progress, epoch 1

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56aefbf84c601f77f8b20c125aee6d628dde6b1706f4275822432c594010dc48
-size 6432
+oid sha256:3024554ce80166e5a3aa67ccdb6c3d2bb4747fef8a0a86374faa2951b04a62a8
+size 8236

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6cb732fec6b5056570aa54443129f3e03d3257ba9750ef74f7a4c6cbe44234
+size 5708

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d8b88377cd56d5eb922bb194d6c19eb82349353a1543f11a3d7458e56d9897e
+oid sha256:1af612a7f664f810b37e8f8d7fe7ce92d45527d343d7b701c8085caded0fa603
 size 17549312

run-1/checkpoint-516/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-516/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdd8af782175ee631b889f95e37381418065aa689d291323e07349506aa1b268
+size 17549312

run-1/checkpoint-516/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:749ebfea1d5609c34b035032762726a3c2b2bd9ea5958b92ab3098b58af24339
+size 35123898

run-1/checkpoint-516/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e559bd010dfad806644ec9950fc1246348c344f69faad3d9fcd91973ca8dae1e
+size 14308

run-1/checkpoint-516/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55c2128f9137c1f9de6173f0232dceb1bd4fb80938a5f625e5ff881d01b31fbc
+size 1064

run-1/checkpoint-516/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-516/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-516/trainer_state.json

@@ -0,0 +1,98 @@
+{
+  "best_metric": 0.7086666666666667,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-1/checkpoint-516",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 516,
+  "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
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.061181988567113876,
+      "learning_rate": 0.00031317844283151793,
+      "loss": 0.0486,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8169422222222222,
+      "eval_BAC": 0.6066666666666667,
+      "eval_MCC": 0.34181792192366234,
+      "eval_PR_AUC": 0.7733898212292494,
+      "eval_accuracy": 0.6066666666666667,
+      "eval_loss": 0.04842817783355713,
+      "eval_runtime": 6.2071,
+      "eval_samples_per_second": 241.657,
+      "eval_steps_per_second": 7.572,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.035214055329561234,
+      "learning_rate": 0.00015658922141575897,
+      "loss": 0.0484,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.7751502222222222,
+      "eval_BAC": 0.7086666666666667,
+      "eval_MCC": 0.47074801855813936,
+      "eval_PR_AUC": 0.718076635825553,
+      "eval_accuracy": 0.7086666666666667,
+      "eval_loss": 0.048104096204042435,
+      "eval_runtime": 6.2731,
+      "eval_samples_per_second": 239.115,
+      "eval_steps_per_second": 7.492,
+      "step": 516
+    }
+  ],
+  "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": 1351133190000.0,
+  "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-516/training_args.bin

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

run-1/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-1/checkpoint-688/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05f2e53cca223b521271e54b265d0f50be12bbcc30b495fd472d3680aab7d798
+size 17549312

run-1/checkpoint-688/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8695e21af44c9b0d4d3b0dfa84bcdc92de443023bba347ec8f0901643dd66956
+size 35123898

run-1/checkpoint-688/rng_state.pth

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

run-1/checkpoint-688/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bed76c770e34ec7ed846c66d1d97ef39c9e6544624cff7fe4ff4557af799276
+size 1064

run-1/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-1/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-1/checkpoint-688/trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_metric": 0.7086666666666667,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-1/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": 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
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.061181988567113876,
+      "learning_rate": 0.00031317844283151793,
+      "loss": 0.0486,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8169422222222222,
+      "eval_BAC": 0.6066666666666667,
+      "eval_MCC": 0.34181792192366234,
+      "eval_PR_AUC": 0.7733898212292494,
+      "eval_accuracy": 0.6066666666666667,
+      "eval_loss": 0.04842817783355713,
+      "eval_runtime": 6.2071,
+      "eval_samples_per_second": 241.657,
+      "eval_steps_per_second": 7.572,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.035214055329561234,
+      "learning_rate": 0.00015658922141575897,
+      "loss": 0.0484,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.7751502222222222,
+      "eval_BAC": 0.7086666666666667,
+      "eval_MCC": 0.47074801855813936,
+      "eval_PR_AUC": 0.718076635825553,
+      "eval_accuracy": 0.7086666666666667,
+      "eval_loss": 0.048104096204042435,
+      "eval_runtime": 6.2731,
+      "eval_samples_per_second": 239.115,
+      "eval_steps_per_second": 7.492,
+      "step": 516
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.08540869504213333,
+      "learning_rate": 0.0,
+      "loss": 0.0483,
+      "step": 688
+    },
+    {
+      "epoch": 4.0,
+      "eval_AUC": 0.7888142222222222,
+      "eval_BAC": 0.6553333333333333,
+      "eval_MCC": 0.41482262338943016,
+      "eval_PR_AUC": 0.7243356288592278,
+      "eval_accuracy": 0.6553333333333333,
+      "eval_loss": 0.04813617467880249,
+      "eval_runtime": 6.2684,
+      "eval_samples_per_second": 239.295,
+      "eval_steps_per_second": 7.498,
+      "step": 688
+    }
+  ],
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1801510920000.0,
+  "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-688/training_args.bin

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

run-2/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-2/checkpoint-172/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1af612a7f664f810b37e8f8d7fe7ce92d45527d343d7b701c8085caded0fa603
+size 17549312

run-2/checkpoint-172/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ef2a75fb52625dacf9421df2e7486e69640896586a8f6c38c2387af02cb4f13
+size 35123898

run-2/checkpoint-172/rng_state.pth

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

run-2/checkpoint-172/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b928f62439a633e541dcdfc2797ab5c91ac1d9bfd5ed6bc37aeb26ec367112d
+size 1064

run-2/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-2/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-2/checkpoint-172/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.6966666666666667,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-2/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": 0.39246517419815063,
+      "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
+    }
+  ],
+  "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": 0.3558486326039224,
+    "learning_rate": 5.155024837005116e-05,
+    "num_train_epochs": 10,
+    "temperature": 4
+  }
+}

run-2/checkpoint-172/training_args.bin

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fa2a37044ef6ce8c62252f894198b0ff65c98d3ddcbefc318c73358bb5c9023
+oid sha256:e9bd69b3929a44bec8f4cb67348238146f431e97b360ab6f0d8fff3cfab94f36
 size 5240