Training in progress, epoch 3, checkpoint

checkpoint-690/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "mrpc",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "equivalent": 1,
+    "not_equivalent": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-690/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37015ad72a3f43bda22ab00f49ab1e8dbe97f37f8a621c44de95738488f3e493
+size 437958648

checkpoint-690/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bf09ab8992cbe1a6f39ddacdb46317d15e9f89c240434309e2aab7e343dd313
+size 876038394

checkpoint-690/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b36ff4bc10db765620ff5148e229a4b42e12fef951f2de2dc0adec862027db
+size 14244

checkpoint-690/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60e78b2d2abd625bd2ee6a67339539e56371d47ad1241e7fb4f9f17200ffea2b
+size 1064

checkpoint-690/special_tokens_map.json

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

checkpoint-690/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]"
+}

checkpoint-690/trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 690,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.811136722564697,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.5401,
+      "step": 230
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8357843137254902,
+      "eval_combined_score": 0.8583894925643437,
+      "eval_f1": 0.8809946714031972,
+      "eval_loss": 0.39578330516815186,
+      "eval_runtime": 1.2728,
+      "eval_samples_per_second": 320.554,
+      "eval_steps_per_second": 40.069,
+      "step": 230
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 14.35599136352539,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.3312,
+      "step": 460
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8431372549019608,
+      "eval_combined_score": 0.8662053056516724,
+      "eval_f1": 0.889273356401384,
+      "eval_loss": 0.3634483516216278,
+      "eval_runtime": 1.2981,
+      "eval_samples_per_second": 314.298,
+      "eval_steps_per_second": 39.287,
+      "step": 460
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.680626153945923,
+      "learning_rate": 0.0,
+      "loss": 0.1913,
+      "step": 690
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8529411764705882,
+      "eval_combined_score": 0.8743872549019608,
+      "eval_f1": 0.8958333333333334,
+      "eval_loss": 0.43215397000312805,
+      "eval_runtime": 1.3921,
+      "eval_samples_per_second": 293.088,
+      "eval_steps_per_second": 36.636,
+      "step": 690
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2895274053181440.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-690/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c52f5d1a218b3c5ecf59503e1501b1ae50f8b6b6380fc2eff4c96d750f6e3a5b
+size 5176