Training in progress, epoch 2

logs/events.out.tfevents.1721967385.98acc6742512.15262.40

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:311649b77c8ccbbd8b4d86abcd1d307ae8883f58f5cd35e9a906b498d33f6076
-size 5708
+oid sha256:38f2fc42cfaedddfe181e99076eba131e92ff07915a3d69c3c244b1ab08efabb
+size 6433

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a658b8887425c704be28377138ba6e6e6af3f312057e3e54c52484e709266079
+oid sha256:aece714db1ad88f374468affe7d78ad2c676b47a3f859854fdaa2e9e4263e9b2
 size 17549312

run-39/checkpoint-344/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-39/checkpoint-344/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aece714db1ad88f374468affe7d78ad2c676b47a3f859854fdaa2e9e4263e9b2
+size 17549312

run-39/checkpoint-344/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d180e9b28d524508519bc08e35caa83dbc9f963e8794021e18695a6fe78760f
+size 35123898

run-39/checkpoint-344/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2379c4b3c857cec440f9d16a9c9688b7d4e4a6884412fa1520c2361c4ae0b74c
+size 14308

run-39/checkpoint-344/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f6ab029a6eb3ad5bff947c70a412f720ca753b648339a31da1a43f108a3de83
+size 1064

run-39/checkpoint-344/special_tokens_map.json

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

run-39/checkpoint-344/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-39/checkpoint-344/trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": 0.7726666666666666,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-39/checkpoint-344",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 344,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.055269718170166,
+      "learning_rate": 0.00025163261729188927,
+      "loss": 0.5433,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8219448888888888,
+      "eval_BAC": 0.7506666666666666,
+      "eval_MCC": 0.5016348507579017,
+      "eval_PR_AUC": 0.7707998025613563,
+      "eval_accuracy": 0.7506666666666667,
+      "eval_loss": 0.4826282262802124,
+      "eval_runtime": 6.2248,
+      "eval_samples_per_second": 240.97,
+      "eval_steps_per_second": 7.55,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.3906846046447754,
+      "learning_rate": 0.0002156851005359051,
+      "loss": 0.5027,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8551982222222222,
+      "eval_BAC": 0.7726666666666666,
+      "eval_MCC": 0.5656065138044973,
+      "eval_PR_AUC": 0.8199811588475655,
+      "eval_accuracy": 0.7726666666666666,
+      "eval_loss": 0.46273502707481384,
+      "eval_runtime": 6.2303,
+      "eval_samples_per_second": 240.758,
+      "eval_steps_per_second": 7.544,
+      "step": 344
+    }
+  ],
+  "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": 900755460000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.842702461956624,
+    "learning_rate": 0.00028758013404787345,
+    "num_train_epochs": 8,
+    "temperature": 6
+  }
+}

run-39/checkpoint-344/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e8a1be64d362b369012eed476baffc2d06787e5ee79078bb527d723978136e8
+size 5240