Training in progress, epoch 3

logs/events.out.tfevents.1721966078.98acc6742512.15262.32

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:048bc937c7896679c3a4e5b395fc885baa4a0dc037567389f458a097a4d582d5
-size 6432
+oid sha256:6f552b78219c4e8ad625fcb808d74213bb243bbf6bb8db7a0d5905307c539c0b
+size 7157

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32499d2ea0fe0191c38413f18270c5694094390864424a0775775c3e50f49b14
+oid sha256:0704d4e6666646eabcfb0e136e1343bb112f939efd62ac231ee351af2951adef
 size 17549312

run-31/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-31/checkpoint-516/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0704d4e6666646eabcfb0e136e1343bb112f939efd62ac231ee351af2951adef
+size 17549312

run-31/checkpoint-516/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4196a843292a0e1e626a78c0b137a29757cec16b6d4af8187a47c704e9c59426
+size 35123898

run-31/checkpoint-516/rng_state.pth

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

run-31/checkpoint-516/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:006df4b6d87766d435229e22caf8cb08387b241417bfb3abfafdddb6fa5449cc
+size 1064

run-31/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-31/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-31/checkpoint-516/trainer_state.json

@@ -0,0 +1,98 @@
+{
+  "best_metric": 0.7986666666666666,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-31/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": 0.9708962440490723,
+      "learning_rate": 0.00018007353154788933,
+      "loss": 0.5186,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8338702222222223,
+      "eval_BAC": 0.758,
+      "eval_MCC": 0.5164413442563544,
+      "eval_PR_AUC": 0.7903470719520844,
+      "eval_accuracy": 0.758,
+      "eval_loss": 0.45808151364326477,
+      "eval_runtime": 6.2856,
+      "eval_samples_per_second": 238.642,
+      "eval_steps_per_second": 7.477,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.5569114685058594,
+      "learning_rate": 0.0001543487413267623,
+      "loss": 0.4771,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8571271111111111,
+      "eval_BAC": 0.7793333333333333,
+      "eval_MCC": 0.591094330111451,
+      "eval_PR_AUC": 0.8037547287750328,
+      "eval_accuracy": 0.7793333333333333,
+      "eval_loss": 0.4492648243904114,
+      "eval_runtime": 6.2364,
+      "eval_samples_per_second": 240.525,
+      "eval_steps_per_second": 7.536,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.398871898651123,
+      "learning_rate": 0.00012862395110563524,
+      "loss": 0.4628,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.8642417777777778,
+      "eval_BAC": 0.7986666666666666,
+      "eval_MCC": 0.5973864367101849,
+      "eval_PR_AUC": 0.8284732954100074,
+      "eval_accuracy": 0.7986666666666666,
+      "eval_loss": 0.425106942653656,
+      "eval_runtime": 6.229,
+      "eval_samples_per_second": 240.809,
+      "eval_steps_per_second": 7.545,
+      "step": 516
+    }
+  ],
+  "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": 1351133190000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8022374115576867,
+    "learning_rate": 0.0002057983217690164,
+    "num_train_epochs": 8,
+    "temperature": 4
+  }
+}

run-31/checkpoint-516/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78fd7203d5f23c69c697c8238f9f591b290847593ab65c957256295adf31d75f
+size 5240