Add model and its dependencies

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.8578431372549019,
+    "eval_combined_score": 0.8790933899332929,
+    "eval_f1": 0.9003436426116839,
+    "eval_loss": 0.48073676228523254,
+    "eval_runtime": 1.1509,
+    "eval_samples": 408,
+    "eval_samples_per_second": 354.51,
+    "eval_steps_per_second": 44.314,
+    "train_loss": 0.17106628703034443,
+    "train_runtime": 327.4394,
+    "train_samples": 3668,
+    "train_samples_per_second": 112.021,
+    "train_steps_per_second": 3.512
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "mrpc",
+  "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": 10.0,
+    "eval_accuracy": 0.8578431372549019,
+    "eval_combined_score": 0.8790933899332929,
+    "eval_f1": 0.9003436426116839,
+    "eval_loss": 0.48073676228523254,
+    "eval_runtime": 1.1509,
+    "eval_samples": 408,
+    "eval_samples_per_second": 354.51,
+    "eval_steps_per_second": 44.314
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6bfeb9dc85b3366879f7c6e3f65b6bd9e714d49094131e06112c8eed58908cf
+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": 10.0,
+    "train_loss": 0.17106628703034443,
+    "train_runtime": 327.4394,
+    "train_samples": 3668,
+    "train_samples_per_second": 112.021,
+    "train_steps_per_second": 3.512
+}

trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 0.8578431372549019,
+  "best_model_checkpoint": "./bert-base-uncased/fine_tuned_models/checkpoint-460",
+  "epoch": 10.0,
+  "global_step": 1150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1e-05,
+      "loss": 0.6308,
+      "step": 115
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7058823529411765,
+      "eval_combined_score": 0.7639204049572351,
+      "eval_f1": 0.8219584569732937,
+      "eval_loss": 0.5484543442726135,
+      "eval_runtime": 1.1176,
+      "eval_samples_per_second": 365.063,
+      "eval_steps_per_second": 45.633,
+      "step": 115
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2e-05,
+      "loss": 0.488,
+      "step": 230
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7990196078431373,
+      "eval_combined_score": 0.8344304388422037,
+      "eval_f1": 0.86984126984127,
+      "eval_loss": 0.44723159074783325,
+      "eval_runtime": 1.121,
+      "eval_samples_per_second": 363.966,
+      "eval_steps_per_second": 45.496,
+      "step": 230
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 0.3019,
+      "step": 345
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8406862745098039,
+      "eval_combined_score": 0.8653515974917887,
+      "eval_f1": 0.8900169204737733,
+      "eval_loss": 0.3739049434661865,
+      "eval_runtime": 1.1236,
+      "eval_samples_per_second": 363.103,
+      "eval_steps_per_second": 45.388,
+      "step": 345
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.1395,
+      "step": 460
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8578431372549019,
+      "eval_combined_score": 0.8790933899332929,
+      "eval_f1": 0.9003436426116839,
+      "eval_loss": 0.48073676228523254,
+      "eval_runtime": 1.1302,
+      "eval_samples_per_second": 360.994,
+      "eval_steps_per_second": 45.124,
+      "step": 460
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.25e-05,
+      "loss": 0.0603,
+      "step": 575
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8357843137254902,
+      "eval_combined_score": 0.8594279334770557,
+      "eval_f1": 0.8830715532286212,
+      "eval_loss": 0.6254621148109436,
+      "eval_runtime": 1.1347,
+      "eval_samples_per_second": 359.579,
+      "eval_steps_per_second": 44.947,
+      "step": 575
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0356,
+      "step": 690
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8431372549019608,
+      "eval_combined_score": 0.8676965735789266,
+      "eval_f1": 0.8922558922558923,
+      "eval_loss": 0.8049449324607849,
+      "eval_runtime": 1.1199,
+      "eval_samples_per_second": 364.325,
+      "eval_steps_per_second": 45.541,
+      "step": 690
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.0267,
+      "step": 805
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8455882352941176,
+      "eval_combined_score": 0.8668438512172187,
+      "eval_f1": 0.8880994671403197,
+      "eval_loss": 0.7565263509750366,
+      "eval_runtime": 1.1371,
+      "eval_samples_per_second": 358.818,
+      "eval_steps_per_second": 44.852,
+      "step": 805
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 5e-06,
+      "loss": 0.0117,
+      "step": 920
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8382352941176471,
+      "eval_combined_score": 0.8622210953346856,
+      "eval_f1": 0.8862068965517241,
+      "eval_loss": 0.8377837538719177,
+      "eval_runtime": 1.1383,
+      "eval_samples_per_second": 358.436,
+      "eval_steps_per_second": 44.805,
+      "step": 920
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0086,
+      "step": 1035
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8382352941176471,
+      "eval_combined_score": 0.8614253393665159,
+      "eval_f1": 0.8846153846153846,
+      "eval_loss": 0.870381772518158,
+      "eval_runtime": 1.1281,
+      "eval_samples_per_second": 361.659,
+      "eval_steps_per_second": 45.207,
+      "step": 1035
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0075,
+      "step": 1150
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8406862745098039,
+      "eval_combined_score": 0.8640173140313319,
+      "eval_f1": 0.8873483535528597,
+      "eval_loss": 0.8665909171104431,
+      "eval_runtime": 1.1293,
+      "eval_samples_per_second": 361.28,
+      "eval_steps_per_second": 45.16,
+      "step": 1150
+    },
+    {
+      "epoch": 10.0,
+      "step": 1150,
+      "total_flos": 2412728377651200.0,
+      "train_loss": 0.17106628703034443,
+      "train_runtime": 327.4394,
+      "train_samples_per_second": 112.021,
+      "train_steps_per_second": 3.512
+    }
+  ],
+  "max_steps": 1150,
+  "num_train_epochs": 10,
+  "total_flos": 2412728377651200.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0456efef3913b90541d5850bdca4a25220c2f1241bfb896cf4767ef6570abcf4
+size 2671