Training in progress, epoch 2, checkpoint

checkpoint-45482/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": "qqp",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "duplicate": 1,
+    "not_duplicate": 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-45482/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98297b94193756fda67c260674e7145953722059b13f81971e7f70daff5a3299
+size 437958648

checkpoint-45482/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd7ea4f1ef1d2493cd9fd90e3ee2ae866e6cdfe03cb8199899d61bd26855e0c1
+size 876038394

checkpoint-45482/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90c8e6714402d088ebfa5befd5fd6769540bb7374245ce148b404f1cf4c9f781
+size 14244

checkpoint-45482/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92203300f8a43c6154fce87b01b184a633ea5ddc265b98d9b4a77abdf984002b
+size 1064

checkpoint-45482/special_tokens_map.json

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

checkpoint-45482/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-45482/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 45482,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.0593485832214355,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.2942,
+      "step": 22741
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9008656937917388,
+      "eval_combined_score": 0.8844814218975149,
+      "eval_f1": 0.868097150003291,
+      "eval_loss": 0.2476482093334198,
+      "eval_runtime": 125.5141,
+      "eval_samples_per_second": 322.115,
+      "eval_steps_per_second": 40.266,
+      "step": 22741
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 10.616366386413574,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1919,
+      "step": 45482
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9079643828839971,
+      "eval_combined_score": 0.892029542512559,
+      "eval_f1": 0.8760947021411208,
+      "eval_loss": 0.2705819010734558,
+      "eval_runtime": 126.0816,
+      "eval_samples_per_second": 320.665,
+      "eval_steps_per_second": 40.085,
+      "step": 45482
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 68223,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.9146381009702912e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-45482/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c852fffd18f3405f60cdefedf46f13897035c5a2d03e7f77b13eef7e7104405
+size 5176