Training in progress, epoch 1

logs/events.out.tfevents.1721965439.98acc6742512.15262.25

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcbbb28bb3e38581c12dc9bb2af61c29b767c02fe82351d0e8f172ea7a03b306
-size 6434
+oid sha256:4c9937e1d573c304efe45d9d1736f4436a7b5f9797e4fd4b890fd06c2d6ee51d
+size 8609

logs/events.out.tfevents.1721965588.98acc6742512.15262.26

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37ad6698a68647e75f4a0ae679fabd88a9fa06ce936470c667d33cf07bc196d9
+size 5707

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:286aac835ad64dde2fcda8a7cb22333261662dcac84e95cd7fdad3e83a516117
+oid sha256:8213352dae50cc3d57ccecacdd43708a479e7c2a90ef60b2d454c41f70088f34
 size 17549312

run-24/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-24/checkpoint-516/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:487b3e2faa13fa88b9035fdb66b34aae3900483994b43e87c1e3c63f8a5eeaba
+size 17549312

run-24/checkpoint-516/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ab166851499e567368aff902ead1bcc14a527bd4e9b4b4c4ec2ea8469eb5a50
+size 35123898

run-24/checkpoint-516/rng_state.pth

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

run-24/checkpoint-516/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75538528aad8bbe80fa7cbd01a9fd872acdcce4c9c529222c28ac5b2e9afc68f
+size 1064

run-24/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-24/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-24/checkpoint-516/trainer_state.json

@@ -0,0 +1,98 @@
+{
+  "best_metric": 0.804,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-24/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": 0.6114831566810608,
+      "learning_rate": 0.00012438553278352026,
+      "loss": 0.4032,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.812864,
+      "eval_BAC": 0.736,
+      "eval_MCC": 0.47260700716368276,
+      "eval_PR_AUC": 0.7744742146180674,
+      "eval_accuracy": 0.736,
+      "eval_loss": 0.3765888214111328,
+      "eval_runtime": 6.2583,
+      "eval_samples_per_second": 239.681,
+      "eval_steps_per_second": 7.51,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8825994729995728,
+      "learning_rate": 0.00011056491802979578,
+      "loss": 0.3836,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.834104888888889,
+      "eval_BAC": 0.7606666666666666,
+      "eval_MCC": 0.5584922194756476,
+      "eval_PR_AUC": 0.7802314251570694,
+      "eval_accuracy": 0.7606666666666667,
+      "eval_loss": 0.36870983242988586,
+      "eval_runtime": 6.277,
+      "eval_samples_per_second": 238.968,
+      "eval_steps_per_second": 7.488,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.0203838348388672,
+      "learning_rate": 9.67443032760713e-05,
+      "loss": 0.3769,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.8587253333333335,
+      "eval_BAC": 0.804,
+      "eval_MCC": 0.6132578536355836,
+      "eval_PR_AUC": 0.8153312043691034,
+      "eval_accuracy": 0.804,
+      "eval_loss": 0.35289254784584045,
+      "eval_runtime": 6.2324,
+      "eval_samples_per_second": 240.677,
+      "eval_steps_per_second": 7.541,
+      "step": 516
+    }
+  ],
+  "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": 1351133190000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.605164320881552,
+    "learning_rate": 0.00013820614753724472,
+    "num_train_epochs": 10,
+    "temperature": 9
+  }
+}

run-24/checkpoint-516/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db080950555f1448b25c4e51afe1a086f8b409b2841b40874bfcb82bde4dd4fe
+size 5240

run-24/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-24/checkpoint-688/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cd88e55a4ad598aeedf3f4280a390f9784cf880a857c6e4d81f9cf21b4aa022
+size 17549312

run-24/checkpoint-688/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c044b32ef437069b4b6b2b1d1e757646e944ccb01a280067d98dbff9a83653fd
+size 35123898

run-24/checkpoint-688/rng_state.pth

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

run-24/checkpoint-688/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30b2b90006e3a2c253a37647a01130cb18ff999440ac3da1261bd3f1029cb923
+size 1064

run-24/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-24/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-24/checkpoint-688/trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_metric": 0.81,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-24/checkpoint-688",
+  "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": 0.6114831566810608,
+      "learning_rate": 0.00012438553278352026,
+      "loss": 0.4032,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.812864,
+      "eval_BAC": 0.736,
+      "eval_MCC": 0.47260700716368276,
+      "eval_PR_AUC": 0.7744742146180674,
+      "eval_accuracy": 0.736,
+      "eval_loss": 0.3765888214111328,
+      "eval_runtime": 6.2583,
+      "eval_samples_per_second": 239.681,
+      "eval_steps_per_second": 7.51,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8825994729995728,
+      "learning_rate": 0.00011056491802979578,
+      "loss": 0.3836,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.834104888888889,
+      "eval_BAC": 0.7606666666666666,
+      "eval_MCC": 0.5584922194756476,
+      "eval_PR_AUC": 0.7802314251570694,
+      "eval_accuracy": 0.7606666666666667,
+      "eval_loss": 0.36870983242988586,
+      "eval_runtime": 6.277,
+      "eval_samples_per_second": 238.968,
+      "eval_steps_per_second": 7.488,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.0203838348388672,
+      "learning_rate": 9.67443032760713e-05,
+      "loss": 0.3769,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.8587253333333335,
+      "eval_BAC": 0.804,
+      "eval_MCC": 0.6132578536355836,
+      "eval_PR_AUC": 0.8153312043691034,
+      "eval_accuracy": 0.804,
+      "eval_loss": 0.35289254784584045,
+      "eval_runtime": 6.2324,
+      "eval_samples_per_second": 240.677,
+      "eval_steps_per_second": 7.541,
+      "step": 516
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.1677234172821045,
+      "learning_rate": 8.292368852234684e-05,
+      "loss": 0.3677,
+      "step": 688
+    },
+    {
+      "epoch": 4.0,
+      "eval_AUC": 0.8672444444444444,
+      "eval_BAC": 0.81,
+      "eval_MCC": 0.6290847145741534,
+      "eval_PR_AUC": 0.8293327638808494,
+      "eval_accuracy": 0.81,
+      "eval_loss": 0.3481285870075226,
+      "eval_runtime": 6.2093,
+      "eval_samples_per_second": 241.573,
+      "eval_steps_per_second": 7.569,
+      "step": 688
+    }
+  ],
+  "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": 1801510920000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.605164320881552,
+    "learning_rate": 0.00013820614753724472,
+    "num_train_epochs": 10,
+    "temperature": 9
+  }
+}

run-24/checkpoint-688/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db080950555f1448b25c4e51afe1a086f8b409b2841b40874bfcb82bde4dd4fe
+size 5240

run-25/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-25/checkpoint-172/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8213352dae50cc3d57ccecacdd43708a479e7c2a90ef60b2d454c41f70088f34
+size 17549312

run-25/checkpoint-172/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e0e9c065f0b95e48906d4d640da8a2723ca4a00e40b2e8f468aae67984dcfa0
+size 35123898

run-25/checkpoint-172/rng_state.pth

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

run-25/checkpoint-172/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc1cbbc90dd196a984a862d2e56b8e356ce5cb2b72c88db207315d8f1d36e14b
+size 1064

run-25/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-25/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-25/checkpoint-172/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.7413333333333333,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-25/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": 0.8690188527107239,
+      "learning_rate": 0.0001732793884765621,
+      "loss": 0.484,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8223413333333331,
+      "eval_BAC": 0.7413333333333333,
+      "eval_MCC": 0.48280573474696187,
+      "eval_PR_AUC": 0.7777897109751378,
+      "eval_accuracy": 0.7413333333333333,
+      "eval_loss": 0.43229565024375916,
+      "eval_runtime": 6.2362,
+      "eval_samples_per_second": 240.531,
+      "eval_steps_per_second": 7.537,
+      "step": 172
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 344,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 0.7425109383729434,
+    "learning_rate": 0.0003465587769531242,
+    "num_train_epochs": 2,
+    "temperature": 5
+  }
+}

run-25/checkpoint-172/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55a7265c224cfadd9cbeae7323bf17185f780b87c258a3ceb7edb6382228834d
+size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db080950555f1448b25c4e51afe1a086f8b409b2841b40874bfcb82bde4dd4fe
+oid sha256:55a7265c224cfadd9cbeae7323bf17185f780b87c258a3ceb7edb6382228834d
 size 5240