Training in progress, epoch 2

logs/events.out.tfevents.1721964555.98acc6742512.15262.18

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46def65befbaf433c34b1c2418fa897bf44342531090ef50c02472b7a12a5767
-size 5707
+oid sha256:35035dd5e5826c98646b29a95cd082d849ac7b00339c904af19267cd8bce551f
+size 6432

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83ad5a42d1a87f9ff44ac4c538922639bbebb0a4f46e1dd72be25000c75d6e33
+oid sha256:c9002842abaa30fd7980a94769d9f8368bd6462e1864e29e9b20967422d4c9b1
 size 17549312

run-17/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-17/checkpoint-344/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9002842abaa30fd7980a94769d9f8368bd6462e1864e29e9b20967422d4c9b1
+size 17549312

run-17/checkpoint-344/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21ffaed2f5fe5261e4e2c49a2298f5b3f428e02c55177c41a200e3ced8f7ab29
+size 35123898

run-17/checkpoint-344/rng_state.pth

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

run-17/checkpoint-344/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99a65d28eb8a66bbced98efc90a764e8bfdc1073192d702cfca44474770fa1c2
+size 1064

run-17/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-17/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-17/checkpoint-344/trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": 0.7453333333333333,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-17/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": 0.8996825218200684,
+      "learning_rate": 0.00018817928905452526,
+      "loss": 0.4453,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8236924444444444,
+      "eval_BAC": 0.7266666666666667,
+      "eval_MCC": 0.4600832969449537,
+      "eval_PR_AUC": 0.7804386215311028,
+      "eval_accuracy": 0.7266666666666667,
+      "eval_loss": 0.41169798374176025,
+      "eval_runtime": 6.2662,
+      "eval_samples_per_second": 239.379,
+      "eval_steps_per_second": 7.501,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0351688861846924,
+      "learning_rate": 0.0001646568779227096,
+      "loss": 0.4213,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8474275555555556,
+      "eval_BAC": 0.7453333333333334,
+      "eval_MCC": 0.5440525853779636,
+      "eval_PR_AUC": 0.8071261622681414,
+      "eval_accuracy": 0.7453333333333333,
+      "eval_loss": 0.41122254729270935,
+      "eval_runtime": 6.2642,
+      "eval_samples_per_second": 239.457,
+      "eval_steps_per_second": 7.503,
+      "step": 344
+    }
+  ],
+  "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": 900755460000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6759429935635236,
+    "learning_rate": 0.0002117017001863409,
+    "num_train_epochs": 9,
+    "temperature": 2
+  }
+}

run-17/checkpoint-344/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1ed1dad67690c5cbd37fff621da38a10e7851a2ef3b92dd81c6e2cf929ac29a
+size 5240