Training in progress, epoch 4

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e952d3bf32f90719f8140b1294a0102d7ef93042f456c48e352094b9bfb42f5a
-size 7158
+oid sha256:7fb84cda5d6629ebc492e2a655c02d283f10d662e2c5126929a2aa1bc78aa5ea
+size 7883

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b6dea94a6789bc99fa2901770681b255888724709fffb783d14a373dbfd7e09
+oid sha256:38738511cb1dd96d18cbac3440b22782c3d30c7f6db97d333d3be9530d28d12f
 size 17549312

run-44/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-44/checkpoint-688/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38738511cb1dd96d18cbac3440b22782c3d30c7f6db97d333d3be9530d28d12f
+size 17549312

run-44/checkpoint-688/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4087901c8a7dd1980fe3e6fb13889e79423e5819d804368fd4a35d638c57f21f
+size 35123898

run-44/checkpoint-688/rng_state.pth

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

run-44/checkpoint-688/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff7b111ead27290cc9c10933fa470888447157951cfd41258d3c65bb1cdac844
+size 1064

run-44/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-44/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-44/checkpoint-688/trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_metric": 0.8133333333333334,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-44/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": 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
+    }
+  ],
+  "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": 0.8802632296149603,
+    "learning_rate": 0.00026390380931815027,
+    "num_train_epochs": 9,
+    "temperature": 3
+  }
+}

run-44/checkpoint-688/training_args.bin

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