Add model and its dependencies

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "cola",
+  "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",
+  "transformers_version": "4.9.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7de7dcd82ea4d86850a84e522425f2039960f23e3449db22eb0b0223ac431014
+size 433331373

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb02eb6dc935ca7a2b464620df60cb06a2220ea91d93d51d5c7cc4b16ff37bab
+size 14503

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": false, "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-cased", "tokenizer_class": "BertTokenizer"}

trainer_state.json

@@ -0,0 +1,126 @@
+{
+  "best_metric": 0.4796141982078552,
+  "best_model_checkpoint": "/content/output_dir/checkpoint-268",
+  "epoch": 10.0,
+  "global_step": 2680,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4796141982078552,
+      "eval_matthews_correlation": 0.5351033849356494,
+      "eval_runtime": 8.8067,
+      "eval_samples_per_second": 118.433,
+      "eval_steps_per_second": 14.875,
+      "step": 268,
+      "learning_rate": 1.8067415730337083e-05,
+      "loss": 0.4913
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5334435701370239,
+      "eval_matthews_correlation": 0.5178799252679331,
+      "eval_runtime": 8.9439,
+      "eval_samples_per_second": 116.616,
+      "eval_steps_per_second": 14.647,
+      "step": 536,
+      "learning_rate": 1.605992509363296e-05,
+      "loss": 0.2872
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5544090270996094,
+      "eval_matthews_correlation": 0.5649788851042796,
+      "eval_runtime": 8.9467,
+      "eval_samples_per_second": 116.58,
+      "eval_steps_per_second": 14.642,
+      "step": 804,
+      "learning_rate": 1.4052434456928841e-05,
+      "loss": 0.1777
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5754779577255249,
+      "eval_matthews_correlation": 0.6105374636148787,
+      "eval_runtime": 8.8982,
+      "eval_samples_per_second": 117.215,
+      "eval_steps_per_second": 14.722,
+      "step": 1072,
+      "learning_rate": 1.2044943820224718e-05,
+      "loss": 0.1263
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.7263916730880737,
+      "eval_matthews_correlation": 0.5807606001872874,
+      "eval_runtime": 8.9705,
+      "eval_samples_per_second": 116.27,
+      "eval_steps_per_second": 14.603,
+      "step": 1340,
+      "learning_rate": 1.0037453183520601e-05,
+      "loss": 0.0905
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.8121512532234192,
+      "eval_matthews_correlation": 0.5651092792103851,
+      "eval_runtime": 8.9924,
+      "eval_samples_per_second": 115.987,
+      "eval_steps_per_second": 14.568,
+      "step": 1608,
+      "learning_rate": 8.02996254681648e-06,
+      "loss": 0.0692
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.941014289855957,
+      "eval_matthews_correlation": 0.5632084517291658,
+      "eval_runtime": 8.9583,
+      "eval_samples_per_second": 116.428,
+      "eval_steps_per_second": 14.623,
+      "step": 1876,
+      "learning_rate": 6.022471910112359e-06,
+      "loss": 0.0413
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.0095174312591553,
+      "eval_matthews_correlation": 0.5856531698367675,
+      "eval_runtime": 9.0029,
+      "eval_samples_per_second": 115.851,
+      "eval_steps_per_second": 14.551,
+      "step": 2144,
+      "learning_rate": 4.01498127340824e-06,
+      "loss": 0.0327
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.0425965785980225,
+      "eval_matthews_correlation": 0.5941395545037332,
+      "eval_runtime": 8.9217,
+      "eval_samples_per_second": 116.906,
+      "eval_steps_per_second": 14.683,
+      "step": 2412,
+      "learning_rate": 2.00749063670412e-06,
+      "loss": 0.0202
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.0782166719436646,
+      "eval_matthews_correlation": 0.5956649094312695,
+      "eval_runtime": 8.9472,
+      "eval_samples_per_second": 116.572,
+      "eval_steps_per_second": 14.641,
+      "step": 2680,
+      "learning_rate": 0.0,
+      "loss": 0.0104
+    }
+  ],
+  "max_steps": 2680,
+  "num_train_epochs": 10,
+  "total_flos": 7113018526540800.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76db2190700e5b27c108fcfb9a9d9fd9fe0836736da2399f4fe25cd0916b7a8b
+size 2607