Add model and its dependencies

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.9316096901893616,
+    "eval_matthews_correlation": 0.6006236595789939,
+    "eval_runtime": 4.3316,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 240.791,
+    "eval_steps_per_second": 30.243,
+    "train_loss": 0.15299048690653558,
+    "train_runtime": 1102.1141,
+    "train_samples": 8551,
+    "train_samples_per_second": 77.587,
+    "train_steps_per_second": 2.432
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "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": 30522
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.9316096901893616,
+    "eval_matthews_correlation": 0.6006236595789939,
+    "eval_runtime": 4.3316,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 240.791,
+    "eval_steps_per_second": 30.243
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17fe53d46747357fb6ad213f3c06a6b3f15d29e525e48de194523d426d8e5012
+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": 0.15299048690653558,
+    "train_runtime": 1102.1141,
+    "train_samples": 8551,
+    "train_samples_per_second": 77.587,
+    "train_steps_per_second": 2.432
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.6006236595789939,
+  "best_model_checkpoint": "./bert-base-uncased/fine_tuned_models/checkpoint-2144",
+  "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,
+      "learning_rate": 2e-05,
+      "loss": 0.5218,
+      "step": 268
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.44753605127334595,
+      "eval_matthews_correlation": 0.5206026837066519,
+      "eval_runtime": 4.3233,
+      "eval_samples_per_second": 241.252,
+      "eval_steps_per_second": 30.301,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.354,
+      "step": 536
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5026671886444092,
+      "eval_matthews_correlation": 0.5041499193143336,
+      "eval_runtime": 4.4396,
+      "eval_samples_per_second": 234.933,
+      "eval_steps_per_second": 29.507,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.2161,
+      "step": 804
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.4919278025627136,
+      "eval_matthews_correlation": 0.5677601756676588,
+      "eval_runtime": 4.4161,
+      "eval_samples_per_second": 236.18,
+      "eval_steps_per_second": 29.664,
+      "step": 804
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.1417,
+      "step": 1072
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6432674527168274,
+      "eval_matthews_correlation": 0.5807484475986369,
+      "eval_runtime": 4.4083,
+      "eval_samples_per_second": 236.601,
+      "eval_steps_per_second": 29.717,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.0991,
+      "step": 1340
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.7236476540565491,
+      "eval_matthews_correlation": 0.5704260999182836,
+      "eval_runtime": 4.4163,
+      "eval_samples_per_second": 236.173,
+      "eval_steps_per_second": 29.663,
+      "step": 1340
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.0691,
+      "step": 1608
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.815778911113739,
+      "eval_matthews_correlation": 0.5779841591999347,
+      "eval_runtime": 4.3921,
+      "eval_samples_per_second": 237.473,
+      "eval_steps_per_second": 29.826,
+      "step": 1608
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.0476,
+      "step": 1876
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.9046832323074341,
+      "eval_matthews_correlation": 0.5882977917441249,
+      "eval_runtime": 4.406,
+      "eval_samples_per_second": 236.724,
+      "eval_steps_per_second": 29.732,
+      "step": 1876
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.0359,
+      "step": 2144
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.9316096901893616,
+      "eval_matthews_correlation": 0.6006236595789939,
+      "eval_runtime": 4.418,
+      "eval_samples_per_second": 236.082,
+      "eval_steps_per_second": 29.652,
+      "step": 2144
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.0272,
+      "step": 2412
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.9396897554397583,
+      "eval_matthews_correlation": 0.5858661515147512,
+      "eval_runtime": 4.4274,
+      "eval_samples_per_second": 235.576,
+      "eval_steps_per_second": 29.588,
+      "step": 2412
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0173,
+      "step": 2680
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.0013642311096191,
+      "eval_matthews_correlation": 0.5932024506783026,
+      "eval_runtime": 4.4,
+      "eval_samples_per_second": 237.046,
+      "eval_steps_per_second": 29.773,
+      "step": 2680
+    },
+    {
+      "epoch": 10.0,
+      "step": 2680,
+      "total_flos": 3594991817003520.0,
+      "train_loss": 0.15299048690653558,
+      "train_runtime": 1102.1141,
+      "train_samples_per_second": 77.587,
+      "train_steps_per_second": 2.432
+    }
+  ],
+  "max_steps": 2680,
+  "num_train_epochs": 10,
+  "total_flos": 3594991817003520.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:850ffa8374bae244ca85c588712da309c1021de5142723d9bd768e236fa4ea7c
+size 2671