Training in progress, epoch 1

logs/events.out.tfevents.1721968062.98acc6742512.15262.45

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c29151ecb76277d4336fc52ab25f5dfbf706301d13db9e5b11cf7725025c6e0
-size 10783
+oid sha256:132b9035c1ddc9e2f90b2dec28224a3fbdf63b27fec123d4732cfa2693059615
+size 11862

logs/events.out.tfevents.1721968347.98acc6742512.15262.46

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cbbac6dd520f8ccd0eb129031efa6fafebf7209bec62f0242984ff981334e57
+size 5708

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c63dee6cfd5452301cca8d603c8e2991e92c3d325d62aceec7dc26c5595fa22c
+oid sha256:871c07ee71aee93c7f778c32d1667213f47a93bf6326b5b431d3d508338a5f65
 size 17549312

run-44/checkpoint-1548/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-44/checkpoint-1548/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8e09c6fe2c9553e2e7c5cb8b9d9ce668531fe74ae021ea8915db4895d874cdd
+size 17549312

run-44/checkpoint-1548/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1400013af2a4a2878b6c3fb43a8f84fbe5ed66de97a3a049aed6070ffe1ed992
+size 35123898

run-44/checkpoint-1548/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56ddbbc87b36b5871313fc71dae1a22c3ede13ff5a31af8b745553ca14ae3bba
+size 14308

run-44/checkpoint-1548/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdbd9497c3bd86bba1448656a403953b2f4dc19ce65c05669735e4f5870bc177
+size 1064

run-44/checkpoint-1548/special_tokens_map.json

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

run-44/checkpoint-1548/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-44/checkpoint-1548/trainer_state.json

@@ -0,0 +1,218 @@
+{
+  "best_metric": 0.8233333333333334,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-44/checkpoint-1376",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 1548,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0291366577148438,
+      "learning_rate": 0.0002345811638383558,
+      "loss": 0.5634,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8257493333333332,
+      "eval_BAC": 0.7493333333333334,
+      "eval_MCC": 0.4988440649884173,
+      "eval_PR_AUC": 0.7792588674864735,
+      "eval_accuracy": 0.7493333333333333,
+      "eval_loss": 0.5015578866004944,
+      "eval_runtime": 6.2231,
+      "eval_samples_per_second": 241.036,
+      "eval_steps_per_second": 7.552,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.020493507385254,
+      "learning_rate": 0.00020525851835856133,
+      "loss": 0.5193,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8491928888888889,
+      "eval_BAC": 0.782,
+      "eval_MCC": 0.5912326479111619,
+      "eval_PR_AUC": 0.8017644489241138,
+      "eval_accuracy": 0.782,
+      "eval_loss": 0.4762227237224579,
+      "eval_runtime": 6.2111,
+      "eval_samples_per_second": 241.504,
+      "eval_steps_per_second": 7.567,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.424774169921875,
+      "learning_rate": 0.00017593587287876683,
+      "loss": 0.4966,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.8737475555555555,
+      "eval_BAC": 0.8033333333333333,
+      "eval_MCC": 0.6091019874205584,
+      "eval_PR_AUC": 0.8433535637379812,
+      "eval_accuracy": 0.8033333333333333,
+      "eval_loss": 0.4474146366119385,
+      "eval_runtime": 6.1822,
+      "eval_samples_per_second": 242.634,
+      "eval_steps_per_second": 7.603,
+      "step": 516
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.390772342681885,
+      "learning_rate": 0.00014661322739897237,
+      "loss": 0.482,
+      "step": 688
+    },
+    {
+      "epoch": 4.0,
+      "eval_AUC": 0.8785333333333334,
+      "eval_BAC": 0.8133333333333334,
+      "eval_MCC": 0.631647403064903,
+      "eval_PR_AUC": 0.8486385119641844,
+      "eval_accuracy": 0.8133333333333334,
+      "eval_loss": 0.43625757098197937,
+      "eval_runtime": 6.2122,
+      "eval_samples_per_second": 241.458,
+      "eval_steps_per_second": 7.566,
+      "step": 688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.0998780727386475,
+      "learning_rate": 0.0001172905819191779,
+      "loss": 0.4692,
+      "step": 860
+    },
+    {
+      "epoch": 5.0,
+      "eval_AUC": 0.8852177777777779,
+      "eval_BAC": 0.8140000000000001,
+      "eval_MCC": 0.6360574434142463,
+      "eval_PR_AUC": 0.8613878408756617,
+      "eval_accuracy": 0.814,
+      "eval_loss": 0.4329131245613098,
+      "eval_runtime": 6.2417,
+      "eval_samples_per_second": 240.318,
+      "eval_steps_per_second": 7.53,
+      "step": 860
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.9871363639831543,
+      "learning_rate": 8.796793643938341e-05,
+      "loss": 0.4632,
+      "step": 1032
+    },
+    {
+      "epoch": 6.0,
+      "eval_AUC": 0.8855964444444443,
+      "eval_BAC": 0.8140000000000001,
+      "eval_MCC": 0.6363360194066445,
+      "eval_PR_AUC": 0.8667558509315602,
+      "eval_accuracy": 0.814,
+      "eval_loss": 0.4344085156917572,
+      "eval_runtime": 6.2717,
+      "eval_samples_per_second": 239.169,
+      "eval_steps_per_second": 7.494,
+      "step": 1032
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.6520533561706543,
+      "learning_rate": 5.864529095958895e-05,
+      "loss": 0.4528,
+      "step": 1204
+    },
+    {
+      "epoch": 7.0,
+      "eval_AUC": 0.8894951111111111,
+      "eval_BAC": 0.8186666666666667,
+      "eval_MCC": 0.6450959593872383,
+      "eval_PR_AUC": 0.8623100347407953,
+      "eval_accuracy": 0.8186666666666667,
+      "eval_loss": 0.4306567311286926,
+      "eval_runtime": 6.2587,
+      "eval_samples_per_second": 239.666,
+      "eval_steps_per_second": 7.51,
+      "step": 1204
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.8377232551574707,
+      "learning_rate": 2.9322645479794473e-05,
+      "loss": 0.4517,
+      "step": 1376
+    },
+    {
+      "epoch": 8.0,
+      "eval_AUC": 0.8932595555555556,
+      "eval_BAC": 0.8233333333333333,
+      "eval_MCC": 0.6488162231573837,
+      "eval_PR_AUC": 0.868740379494128,
+      "eval_accuracy": 0.8233333333333334,
+      "eval_loss": 0.4159427881240845,
+      "eval_runtime": 6.2307,
+      "eval_samples_per_second": 240.743,
+      "eval_steps_per_second": 7.543,
+      "step": 1376
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 2.067809581756592,
+      "learning_rate": 0.0,
+      "loss": 0.4496,
+      "step": 1548
+    },
+    {
+      "epoch": 9.0,
+      "eval_AUC": 0.8937137777777778,
+      "eval_BAC": 0.8206666666666667,
+      "eval_MCC": 0.6482156016668791,
+      "eval_PR_AUC": 0.868625867981939,
+      "eval_accuracy": 0.8206666666666667,
+      "eval_loss": 0.42660513520240784,
+      "eval_runtime": 6.2138,
+      "eval_samples_per_second": 241.397,
+      "eval_steps_per_second": 7.564,
+      "step": 1548
+    }
+  ],
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4053399570000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8802632296149603,
+    "learning_rate": 0.00026390380931815027,
+    "num_train_epochs": 9,
+    "temperature": 3
+  }
+}

run-44/checkpoint-1548/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f63f506b94a2aa0779057c338dd289bcd70e250aaed1bf57094a633cce39e96
+size 5240

run-45/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-45/checkpoint-172/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:871c07ee71aee93c7f778c32d1667213f47a93bf6326b5b431d3d508338a5f65
+size 17549312

run-45/checkpoint-172/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e2f1cb707f29497eb73763f37569101c7c9edd2d3011788b1ccc6f4bdbd5464
+size 35123898

run-45/checkpoint-172/rng_state.pth

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

run-45/checkpoint-172/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b1d98cd394d65065596ecb0c9690923590d69b57a9108c7d7e4caf8e6a9d512
+size 1064

run-45/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-45/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-45/checkpoint-172/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.7406666666666667,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-45/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": 0.85662442445755,
+      "learning_rate": 0.00016620474751591354,
+      "loss": 0.5008,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8249404444444444,
+      "eval_BAC": 0.7406666666666666,
+      "eval_MCC": 0.4841652673133511,
+      "eval_PR_AUC": 0.7765196206273925,
+      "eval_accuracy": 0.7406666666666667,
+      "eval_loss": 0.4507910907268524,
+      "eval_runtime": 6.198,
+      "eval_samples_per_second": 242.014,
+      "eval_steps_per_second": 7.583,
+      "step": 172
+    }
+  ],
+  "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": 450377730000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7655139424580379,
+    "learning_rate": 0.00018698034095540275,
+    "num_train_epochs": 9,
+    "temperature": 3
+  }
+}

run-45/checkpoint-172/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2054525f4e15172bda8bfeaff2389aa9e0e577d6dbdc69f9c0d0d12d94e873c1
+size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f63f506b94a2aa0779057c338dd289bcd70e250aaed1bf57094a633cce39e96
+oid sha256:2054525f4e15172bda8bfeaff2389aa9e0e577d6dbdc69f9c0d0d12d94e873c1
 size 5240