Add model and its dependencies

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9125154588177096,
+    "eval_combined_score": 0.8974312649841467,
+    "eval_f1": 0.8823470711505838,
+    "eval_loss": 0.40157535672187805,
+    "eval_runtime": 184.8348,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 218.736,
+    "eval_steps_per_second": 27.343,
+    "train_loss": 0.16454659021579016,
+    "train_runtime": 22957.988,
+    "train_samples": 363846,
+    "train_samples_per_second": 79.242,
+    "train_steps_per_second": 2.476
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "qqp",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.9.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9125154588177096,
+    "eval_combined_score": 0.8974312649841467,
+    "eval_f1": 0.8823470711505838,
+    "eval_loss": 0.40157535672187805,
+    "eval_runtime": 184.8348,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 218.736,
+    "eval_steps_per_second": 27.343
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00b41d2d5c14a267a9b11007f6ade1fc740c2b06d73b21c898766648693c890f
+size 438019245

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.16454659021579016,
+    "train_runtime": 22957.988,
+    "train_samples": 363846,
+    "train_samples_per_second": 79.242,
+    "train_steps_per_second": 2.476
+}

trainer_state.json

@@ -0,0 +1,110 @@
+{
+  "best_metric": 0.9125154588177096,
+  "best_model_checkpoint": "./bert-base-uncased/fine_tuned_models/checkpoint-56855",
+  "epoch": 5.0,
+  "global_step": 56855,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.777760406488177e-05,
+      "loss": 0.3331,
+      "step": 11371
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8918872124659906,
+      "eval_combined_score": 0.8741442698553219,
+      "eval_f1": 0.8564013272446532,
+      "eval_loss": 0.25236421823501587,
+      "eval_runtime": 183.9392,
+      "eval_samples_per_second": 219.801,
+      "eval_steps_per_second": 27.476,
+      "step": 11371
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.3333203048661326e-05,
+      "loss": 0.2043,
+      "step": 22742
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.904699480583725,
+      "eval_combined_score": 0.8889967855745091,
+      "eval_f1": 0.8732940905652932,
+      "eval_loss": 0.23582789301872253,
+      "eval_runtime": 184.4786,
+      "eval_samples_per_second": 219.158,
+      "eval_steps_per_second": 27.396,
+      "step": 22742
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.888802032440885e-06,
+      "loss": 0.1327,
+      "step": 34113
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9093742270591145,
+      "eval_combined_score": 0.894668767310189,
+      "eval_f1": 0.8799633075612633,
+      "eval_loss": 0.25910505652427673,
+      "eval_runtime": 184.7125,
+      "eval_samples_per_second": 218.881,
+      "eval_steps_per_second": 27.361,
+      "step": 34113
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.4444010162204425e-06,
+      "loss": 0.0893,
+      "step": 45484
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9120702448676725,
+      "eval_combined_score": 0.8976971395660034,
+      "eval_f1": 0.8833240342643344,
+      "eval_loss": 0.3531641662120819,
+      "eval_runtime": 184.8553,
+      "eval_samples_per_second": 218.712,
+      "eval_steps_per_second": 27.34,
+      "step": 45484
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.0633,
+      "step": 56855
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9125154588177096,
+      "eval_combined_score": 0.8974312649841467,
+      "eval_f1": 0.8823470711505838,
+      "eval_loss": 0.40157535672187805,
+      "eval_runtime": 184.919,
+      "eval_samples_per_second": 218.636,
+      "eval_steps_per_second": 27.331,
+      "step": 56855
+    },
+    {
+      "epoch": 5.0,
+      "step": 56855,
+      "total_flos": 1.196648813106432e+17,
+      "train_loss": 0.16454659021579016,
+      "train_runtime": 22957.988,
+      "train_samples_per_second": 79.242,
+      "train_steps_per_second": 2.476
+    }
+  ],
+  "max_steps": 56855,
+  "num_train_epochs": 5,
+  "total_flos": 1.196648813106432e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cd5fe9e6a8763838afc4e6441b730d774504037647d9be07a897a4a37aff651
+size 2671