Training in progress, epoch 4

logs/events.out.tfevents.1721967054.98acc6742512.15262.37

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa6dff8f886b951ee60fc18cc9c4f3926ecc22785af4dc278bf3c807b6b0f009
-size 7158
+oid sha256:a06bc1275045baa01265dba962ecdbe3c72960fc4609752c853bcc4fc01d59f3
+size 7883

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f222229b09333d65ca1e6c3c3c290f1df7ff8266342c9f4c59e7fade695cda6
+oid sha256:78a9d5811fa96bb8fa079bc53d4cfd9f749839bbb05fc1af3ac3c939f5805275
 size 17549312

run-36/checkpoint-688/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-36/checkpoint-688/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78a9d5811fa96bb8fa079bc53d4cfd9f749839bbb05fc1af3ac3c939f5805275
+size 17549312

run-36/checkpoint-688/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2cc9db6b8a557c6ae44b772a8dd7c85ab04fac8584092baf39dc6815aa49ea6
+size 35123898

run-36/checkpoint-688/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1b1fea9cda5ce8cfa36db49d92878d70e7ecc73c289b2b17c8c4949a715ba6e
+size 14308

run-36/checkpoint-688/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1fdc32722c92e7f9f3dc45e9a8077498784df3826ea001fbb35f12b0defe42
+size 1064

run-36/checkpoint-688/special_tokens_map.json

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

run-36/checkpoint-688/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-36/checkpoint-688/trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_metric": 0.8006666666666666,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-36/checkpoint-516",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 688,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.308287262916565,
+      "learning_rate": 0.0002879869507236685,
+      "loss": 0.5678,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8217386666666667,
+      "eval_BAC": 0.736,
+      "eval_MCC": 0.4730523981849912,
+      "eval_PR_AUC": 0.7761665019542776,
+      "eval_accuracy": 0.736,
+      "eval_loss": 0.5004285573959351,
+      "eval_runtime": 6.1912,
+      "eval_samples_per_second": 242.279,
+      "eval_steps_per_second": 7.591,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.256314754486084,
+      "learning_rate": 0.0002559884006432609,
+      "loss": 0.5202,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8523057777777777,
+      "eval_BAC": 0.7726666666666666,
+      "eval_MCC": 0.5737217012378742,
+      "eval_PR_AUC": 0.8091641314211763,
+      "eval_accuracy": 0.7726666666666666,
+      "eval_loss": 0.4866323173046112,
+      "eval_runtime": 6.27,
+      "eval_samples_per_second": 239.234,
+      "eval_steps_per_second": 7.496,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.7342841625213623,
+      "learning_rate": 0.00022398985056285326,
+      "loss": 0.5001,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.8681244444444443,
+      "eval_BAC": 0.8006666666666666,
+      "eval_MCC": 0.6014536360920308,
+      "eval_PR_AUC": 0.837440734968566,
+      "eval_accuracy": 0.8006666666666666,
+      "eval_loss": 0.4462110102176666,
+      "eval_runtime": 6.2929,
+      "eval_samples_per_second": 238.364,
+      "eval_steps_per_second": 7.469,
+      "step": 516
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.1570067405700684,
+      "learning_rate": 0.00019199130048244567,
+      "loss": 0.4831,
+      "step": 688
+    },
+    {
+      "epoch": 4.0,
+      "eval_AUC": 0.8736213333333334,
+      "eval_BAC": 0.7993333333333333,
+      "eval_MCC": 0.6012164213074452,
+      "eval_PR_AUC": 0.8490695424383705,
+      "eval_accuracy": 0.7993333333333333,
+      "eval_loss": 0.4456213116645813,
+      "eval_runtime": 6.2861,
+      "eval_samples_per_second": 238.622,
+      "eval_steps_per_second": 7.477,
+      "step": 688
+    }
+  ],
+  "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": 1801510920000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8849078880407933,
+    "learning_rate": 0.0003199855008040761,
+    "num_train_epochs": 10,
+    "temperature": 6
+  }
+}

run-36/checkpoint-688/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd64e600de3bd562cb09ae8610fd4eb38a5b7e030bbab378ba613b44c0de5fa
+size 5240