Add model and its dependencies

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.9931675791740417,
+    "eval_matthews_correlation": 0.5817890663339899,
+    "eval_runtime": 4.3164,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 241.634,
+    "eval_steps_per_second": 30.349,
+    "train_loss": 0.1556472381549095,
+    "train_runtime": 1086.1404,
+    "train_samples": 8551,
+    "train_samples_per_second": 78.728,
+    "train_steps_per_second": 2.467
+}

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": 0.9931675791740417,
+    "eval_matthews_correlation": 0.5817890663339899,
+    "eval_runtime": 4.3164,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 241.634,
+    "eval_steps_per_second": 30.349
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c131fa9baee310a9df7ab75064d25252cf142764a03454985af1a690a3c5ec8
+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": 0.1556472381549095,
+    "train_runtime": 1086.1404,
+    "train_samples": 8551,
+    "train_samples_per_second": 78.728,
+    "train_steps_per_second": 2.467
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.5817890663339899,
+  "best_model_checkpoint": "./bert-base-uncased/fine_tuned_models/checkpoint-2412",
+  "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": 0.5423,
+      "step": 268
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5171352028846741,
+      "eval_matthews_correlation": 0.4578310517092636,
+      "eval_runtime": 4.251,
+      "eval_samples_per_second": 245.355,
+      "eval_steps_per_second": 30.816,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.3611,
+      "step": 536
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4953174293041229,
+      "eval_matthews_correlation": 0.5397228199543882,
+      "eval_runtime": 4.3098,
+      "eval_samples_per_second": 242.005,
+      "eval_steps_per_second": 30.396,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.2184,
+      "step": 804
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5253208875656128,
+      "eval_matthews_correlation": 0.537552563011597,
+      "eval_runtime": 4.3068,
+      "eval_samples_per_second": 242.175,
+      "eval_steps_per_second": 30.417,
+      "step": 804
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.1415,
+      "step": 1072
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5971294641494751,
+      "eval_matthews_correlation": 0.5703054933279827,
+      "eval_runtime": 4.3161,
+      "eval_samples_per_second": 241.653,
+      "eval_steps_per_second": 30.351,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.101,
+      "step": 1340
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6834197044372559,
+      "eval_matthews_correlation": 0.5730766020227869,
+      "eval_runtime": 4.3032,
+      "eval_samples_per_second": 242.379,
+      "eval_steps_per_second": 30.443,
+      "step": 1340
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.0647,
+      "step": 1608
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.8203297853469849,
+      "eval_matthews_correlation": 0.5680628967969402,
+      "eval_runtime": 4.3072,
+      "eval_samples_per_second": 242.153,
+      "eval_steps_per_second": 30.414,
+      "step": 1608
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.0478,
+      "step": 1876
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.9401350617408752,
+      "eval_matthews_correlation": 0.5784786967005595,
+      "eval_runtime": 4.3076,
+      "eval_samples_per_second": 242.128,
+      "eval_steps_per_second": 30.411,
+      "step": 1876
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.0315,
+      "step": 2144
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.0027819871902466,
+      "eval_matthews_correlation": 0.5729657494988228,
+      "eval_runtime": 4.2929,
+      "eval_samples_per_second": 242.958,
+      "eval_steps_per_second": 30.515,
+      "step": 2144
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.0256,
+      "step": 2412
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.9931675791740417,
+      "eval_matthews_correlation": 0.5817890663339899,
+      "eval_runtime": 4.2926,
+      "eval_samples_per_second": 242.975,
+      "eval_steps_per_second": 30.517,
+      "step": 2412
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0225,
+      "step": 2680
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.0250993967056274,
+      "eval_matthews_correlation": 0.5759158430027601,
+      "eval_runtime": 4.2922,
+      "eval_samples_per_second": 242.998,
+      "eval_steps_per_second": 30.52,
+      "step": 2680
+    },
+    {
+      "epoch": 10.0,
+      "step": 2680,
+      "total_flos": 3594991817003520.0,
+      "train_loss": 0.1556472381549095,
+      "train_runtime": 1086.1404,
+      "train_samples_per_second": 78.728,
+      "train_steps_per_second": 2.467
+    }
+  ],
+  "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 sha256:4bfa9990cd1a5b14c39cdb0b9ba55eb7d3314ec04ff34fa7cb65f0e66c5c3c63
+size 2671