Training in progress, epoch 5

logs/events.out.tfevents.1721966499.98acc6742512.15262.34

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4c0c3c5a43e51fa280f4af7dba7d66d09583411d3cf7108a6c591784516428
-size 7883
+oid sha256:c98cef215038cfd29efe0b0fb0adca05f1236d492e9b67046bfbff3c92d43ef7
+size 8608

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f2aaf13e0f54340f5be104a4a36018386cda6c3a368325e40f73bf9c45ab624
+oid sha256:b5007782a4d485ceba771f331fdbfa5d9ec20460c37b7534840f187dd94a5413
 size 17549312

run-33/checkpoint-860/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-33/checkpoint-860/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5007782a4d485ceba771f331fdbfa5d9ec20460c37b7534840f187dd94a5413
+size 17549312

run-33/checkpoint-860/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a841c94ac9f3274fb954ad82ec6dc711d58eca6382e48e5429e0f406c84a0da
+size 35123898

run-33/checkpoint-860/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9f0bc35f961ba3eec992b81bac90971267fe149efd92cea3c10af23980c570
+size 14308

run-33/checkpoint-860/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3406f6b4586c0c3cf193f4f54189a43050ed99fed7eff0791dae8bb196a90251
+size 1064

run-33/checkpoint-860/special_tokens_map.json

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

run-33/checkpoint-860/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-33/checkpoint-860/trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_metric": 0.8166666666666667,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-33/checkpoint-860",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 860,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8714374899864197,
+      "learning_rate": 0.0001496514315519773,
+      "loss": 0.4869,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8238275555555555,
+      "eval_BAC": 0.7426666666666666,
+      "eval_MCC": 0.48550598838444897,
+      "eval_PR_AUC": 0.7856295371225543,
+      "eval_accuracy": 0.7426666666666667,
+      "eval_loss": 0.44039902091026306,
+      "eval_runtime": 6.2687,
+      "eval_samples_per_second": 239.283,
+      "eval_steps_per_second": 7.498,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.5228420495986938,
+      "learning_rate": 0.00012827265561598055,
+      "loss": 0.4538,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8575324444444444,
+      "eval_BAC": 0.7833333333333333,
+      "eval_MCC": 0.5945533134180191,
+      "eval_PR_AUC": 0.8074672778987287,
+      "eval_accuracy": 0.7833333333333333,
+      "eval_loss": 0.4205223023891449,
+      "eval_runtime": 6.2791,
+      "eval_samples_per_second": 238.889,
+      "eval_steps_per_second": 7.485,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.2492823600769043,
+      "learning_rate": 0.00010689387967998379,
+      "loss": 0.4415,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.8663128888888889,
+      "eval_BAC": 0.8046666666666666,
+      "eval_MCC": 0.6114945050025467,
+      "eval_PR_AUC": 0.8316399526656422,
+      "eval_accuracy": 0.8046666666666666,
+      "eval_loss": 0.40513432025909424,
+      "eval_runtime": 6.2792,
+      "eval_samples_per_second": 238.886,
+      "eval_steps_per_second": 7.485,
+      "step": 516
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.7223961353302,
+      "learning_rate": 8.551510374398703e-05,
+      "loss": 0.4324,
+      "step": 688
+    },
+    {
+      "epoch": 4.0,
+      "eval_AUC": 0.8720817777777777,
+      "eval_BAC": 0.8026666666666666,
+      "eval_MCC": 0.6129675036984655,
+      "eval_PR_AUC": 0.8433174330584201,
+      "eval_accuracy": 0.8026666666666666,
+      "eval_loss": 0.40090322494506836,
+      "eval_runtime": 6.223,
+      "eval_samples_per_second": 241.04,
+      "eval_steps_per_second": 7.553,
+      "step": 688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.3804311752319336,
+      "learning_rate": 6.413632780799028e-05,
+      "loss": 0.4243,
+      "step": 860
+    },
+    {
+      "epoch": 5.0,
+      "eval_AUC": 0.8757084444444445,
+      "eval_BAC": 0.8166666666666667,
+      "eval_MCC": 0.6384760414061431,
+      "eval_PR_AUC": 0.841910429701927,
+      "eval_accuracy": 0.8166666666666667,
+      "eval_loss": 0.3949587345123291,
+      "eval_runtime": 6.2206,
+      "eval_samples_per_second": 241.134,
+      "eval_steps_per_second": 7.556,
+      "step": 860
+    }
+  ],
+  "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": 2251888650000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7463444212571515,
+    "learning_rate": 0.00017103020748797406,
+    "num_train_epochs": 8,
+    "temperature": 2
+  }
+}

run-33/checkpoint-860/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a2b26670da698e8514ad2208f41ef0e2631c0fcee2f8b2bba3cebe4576add4e
+size 5240