Training in progress, epoch 2

logs/events.out.tfevents.1721964285.98acc6742512.15262.14

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:579146e213c74f2e9dfe4a9ade7d3a8bc246ac8d6feca02f515a476b29c9681f
-size 5708
+oid sha256:fee97e1784e852867cfe2c905a27945df9fe93b915c538fcbdb59c62f0a91ad4
+size 6433

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6bf85f6c98e71aa9127c0c1d4c10efd98d59ce3243c71f646479e86c33664b2
+oid sha256:6fb1b56226a28deec3e04a44d652d93ab1bfb44d77fc1588459d5f704fe33378
 size 17549312

run-13/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-13/checkpoint-344/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fb1b56226a28deec3e04a44d652d93ab1bfb44d77fc1588459d5f704fe33378
+size 17549312

run-13/checkpoint-344/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7db4c180d3146ccf6063547302f2c77ecb0eb6532fc4b7c85ac4496454e45e
+size 35123898

run-13/checkpoint-344/rng_state.pth

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

run-13/checkpoint-344/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9983cce8fe1c22e83731056a7b49d379629bb669e86ef1efccbf46708664368d
+size 1064

run-13/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-13/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-13/checkpoint-344/trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": 0.7846666666666666,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-13/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": 1.6519217491149902,
+      "learning_rate": 0.0003489409909619128,
+      "loss": 0.6241,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8201937777777778,
+      "eval_BAC": 0.738,
+      "eval_MCC": 0.4761528166708038,
+      "eval_PR_AUC": 0.7788333782261532,
+      "eval_accuracy": 0.738,
+      "eval_loss": 0.5376982688903809,
+      "eval_runtime": 6.2979,
+      "eval_samples_per_second": 238.174,
+      "eval_steps_per_second": 7.463,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.3186373710632324,
+      "learning_rate": 0.0003101697697439225,
+      "loss": 0.5634,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8520746666666666,
+      "eval_BAC": 0.7846666666666666,
+      "eval_MCC": 0.5843621161716221,
+      "eval_PR_AUC": 0.8014637687014566,
+      "eval_accuracy": 0.7846666666666666,
+      "eval_loss": 0.4982443153858185,
+      "eval_runtime": 6.2909,
+      "eval_samples_per_second": 238.439,
+      "eval_steps_per_second": 7.471,
+      "step": 344
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1720,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 0.9793694957428477,
+    "learning_rate": 0.0003877122121799031,
+    "num_train_epochs": 10,
+    "temperature": 8
+  }
+}

run-13/checkpoint-344/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5f5a036df1b03e4a4ba9a6e0ee0d631925c8ae6af2604af8ddb074e8926e2a8
+size 5240