Training in progress, epoch 1

logs/events.out.tfevents.1721967656.98acc6742512.15262.43

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1646204136ab46da6092ab9c445782fe07d99d3b87e1e9e9fcb6dacac353931
-size 7883
+oid sha256:c447953a3c11e7e7c871da220840b9ab21242271193e34f504a82682e15f81c6
+size 8608

logs/events.out.tfevents.1721967807.98acc6742512.15262.44

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45972d0ef08211319783db8bdd8878d1ee5a248d0cd6d25193d1d47698c1a3c1
+size 5708

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:284ae1de6fe6156c2b821e4570b12baf145ff39487f1e155eadea6857adb6acd
+oid sha256:0706546970c53ef4e75b954e187a0658aa0fc0e8b5daeff72163ff6141e90577
 size 17549312

run-43/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-43/checkpoint-172/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0706546970c53ef4e75b954e187a0658aa0fc0e8b5daeff72163ff6141e90577
+size 17549312

run-43/checkpoint-172/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a772652660a72f8192ff0f069225b7fc67a51201055798f054f5bc175dd120f
+size 35123898

run-43/checkpoint-172/rng_state.pth

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

run-43/checkpoint-172/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f6f2e40018b797c5550339fce829b1beba6c48b1485fe8b4b6d884a716f43c9
+size 1064

run-43/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-43/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-43/checkpoint-172/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.7526666666666667,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-43/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": 0.9297363758087158,
+      "learning_rate": 0.00018220163554157572,
+      "loss": 0.5109,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8338702222222223,
+      "eval_BAC": 0.7526666666666666,
+      "eval_MCC": 0.5054631978951394,
+      "eval_PR_AUC": 0.7906860159456152,
+      "eval_accuracy": 0.7526666666666667,
+      "eval_loss": 0.45379385352134705,
+      "eval_runtime": 6.2406,
+      "eval_samples_per_second": 240.361,
+      "eval_steps_per_second": 7.531,
+      "step": 172
+    }
+  ],
+  "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": 450377730000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.788436760671977,
+    "learning_rate": 0.00020823044061894368,
+    "num_train_epochs": 8,
+    "temperature": 3
+  }
+}

run-43/checkpoint-172/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a92756ef89f8e47d74c8dbb99b95636b4c11a42f430916a18a4047589b3d76f
+size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49a69b9f95471c755661ba788d0f28bc3b9a005b3ef503c12409bca07c7ecbf3
+oid sha256:4a92756ef89f8e47d74c8dbb99b95636b4c11a42f430916a18a4047589b3d76f
 size 5240