Add model and its dependencies

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.6460844874382019,
+    "eval_matthews_correlation": 0.6894950485304671,
+    "eval_runtime": 4.2956,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 242.805,
+    "eval_steps_per_second": 30.496,
+    "train_loss": 0.14144750192983827,
+    "train_runtime": 1118.7624,
+    "train_samples": 8551,
+    "train_samples_per_second": 76.433,
+    "train_steps_per_second": 2.396
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "google/electra-base-discriminator",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "embedding_size": 768,
+  "finetuning_task": "cola",
+  "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": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "transformers_version": "4.9.0.dev0",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.6460844874382019,
+    "eval_matthews_correlation": 0.6894950485304671,
+    "eval_runtime": 4.2956,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 242.805,
+    "eval_steps_per_second": 30.496
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4959f2d8072a8ce9ef6884d5244d93f93bb8debb079d71a9f687cd923b13a0ea
+size 438020461

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": "google/electra-base-discriminator", "tokenizer_class": "ElectraTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.14144750192983827,
+    "train_runtime": 1118.7624,
+    "train_samples": 8551,
+    "train_samples_per_second": 76.433,
+    "train_steps_per_second": 2.396
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.6894950485304671,
+  "best_model_checkpoint": "./bert-base-uncased/fine_tuned_models/checkpoint-1876",
+  "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": 0.512,
+      "step": 268
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.444403737783432,
+      "eval_matthews_correlation": 0.5528800923802824,
+      "eval_runtime": 4.3492,
+      "eval_samples_per_second": 239.817,
+      "eval_steps_per_second": 30.121,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.3063,
+      "step": 536
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.39591822028160095,
+      "eval_matthews_correlation": 0.6504142235366493,
+      "eval_runtime": 4.378,
+      "eval_samples_per_second": 238.237,
+      "eval_steps_per_second": 29.922,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.1914,
+      "step": 804
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.4600050151348114,
+      "eval_matthews_correlation": 0.6457236074037789,
+      "eval_runtime": 4.3895,
+      "eval_samples_per_second": 237.612,
+      "eval_steps_per_second": 29.844,
+      "step": 804
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.1246,
+      "step": 1072
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.4485293924808502,
+      "eval_matthews_correlation": 0.6792126156603279,
+      "eval_runtime": 4.4001,
+      "eval_samples_per_second": 237.042,
+      "eval_steps_per_second": 29.772,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.087,
+      "step": 1340
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5688888430595398,
+      "eval_matthews_correlation": 0.664145461224172,
+      "eval_runtime": 4.3944,
+      "eval_samples_per_second": 237.345,
+      "eval_steps_per_second": 29.81,
+      "step": 1340
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.0632,
+      "step": 1608
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.6831964254379272,
+      "eval_matthews_correlation": 0.6480399678091215,
+      "eval_runtime": 4.3831,
+      "eval_samples_per_second": 237.959,
+      "eval_steps_per_second": 29.887,
+      "step": 1608
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.0472,
+      "step": 1876
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.6460844874382019,
+      "eval_matthews_correlation": 0.6894950485304671,
+      "eval_runtime": 4.3978,
+      "eval_samples_per_second": 237.167,
+      "eval_steps_per_second": 29.788,
+      "step": 1876
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.0369,
+      "step": 2144
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.6897103786468506,
+      "eval_matthews_correlation": 0.6657078975506158,
+      "eval_runtime": 4.3815,
+      "eval_samples_per_second": 238.046,
+      "eval_steps_per_second": 29.898,
+      "step": 2144
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.024,
+      "step": 2412
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.7450592517852783,
+      "eval_matthews_correlation": 0.6728260482046828,
+      "eval_runtime": 4.3905,
+      "eval_samples_per_second": 237.56,
+      "eval_steps_per_second": 29.837,
+      "step": 2412
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0219,
+      "step": 2680
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.7519025802612305,
+      "eval_matthews_correlation": 0.6707864369052745,
+      "eval_runtime": 4.3943,
+      "eval_samples_per_second": 237.353,
+      "eval_steps_per_second": 29.811,
+      "step": 2680
+    },
+    {
+      "epoch": 10.0,
+      "step": 2680,
+      "total_flos": 3594991817003520.0,
+      "train_loss": 0.14144750192983827,
+      "train_runtime": 1118.7624,
+      "train_samples_per_second": 76.433,
+      "train_steps_per_second": 2.396
+    }
+  ],
+  "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:d4a1aac7d61d49f846228a12fa6411ee72d7d623b0d08cf5b0e318ea1a341b3f
+size 2671