Add model and its dependencies

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.3651696443557739,
+    "eval_matthews_correlation": 0.692877466292272,
+    "eval_runtime": 4.135,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 252.237,
+    "eval_steps_per_second": 31.681,
+    "train_loss": 0.14064713289488606,
+    "train_runtime": 1047.1976,
+    "train_samples": 8551,
+    "train_samples_per_second": 81.656,
+    "train_steps_per_second": 2.559
+}

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": 0.3651696443557739,
+    "eval_matthews_correlation": 0.692877466292272,
+    "eval_runtime": 4.135,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 252.237,
+    "eval_steps_per_second": 31.681
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0a9f478fa752b2aa346dbaec12994232dcd893708923226c2422f8b85cd5b3c
+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": 0.14064713289488606,
+    "train_runtime": 1047.1976,
+    "train_samples": 8551,
+    "train_samples_per_second": 81.656,
+    "train_steps_per_second": 2.559
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.692877466292272,
+  "best_model_checkpoint": "./bert-base-uncased/fine_tuned_models/checkpoint-804",
+  "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": 0.5011,
+      "step": 268
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4567939043045044,
+      "eval_matthews_correlation": 0.5596416792460465,
+      "eval_runtime": 3.9522,
+      "eval_samples_per_second": 263.901,
+      "eval_steps_per_second": 33.146,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.3012,
+      "step": 536
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.3901456594467163,
+      "eval_matthews_correlation": 0.6344790083826756,
+      "eval_runtime": 4.0613,
+      "eval_samples_per_second": 256.815,
+      "eval_steps_per_second": 32.256,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.1956,
+      "step": 804
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.3651696443557739,
+      "eval_matthews_correlation": 0.692877466292272,
+      "eval_runtime": 4.1382,
+      "eval_samples_per_second": 252.045,
+      "eval_steps_per_second": 31.657,
+      "step": 804
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.1256,
+      "step": 1072
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.4441858232021332,
+      "eval_matthews_correlation": 0.6795352314031174,
+      "eval_runtime": 4.1536,
+      "eval_samples_per_second": 251.106,
+      "eval_steps_per_second": 31.539,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.0857,
+      "step": 1340
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6312969923019409,
+      "eval_matthews_correlation": 0.6730043803348406,
+      "eval_runtime": 4.1902,
+      "eval_samples_per_second": 248.916,
+      "eval_steps_per_second": 31.264,
+      "step": 1340
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.0671,
+      "step": 1608
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.6144707202911377,
+      "eval_matthews_correlation": 0.6870534352093987,
+      "eval_runtime": 4.1742,
+      "eval_samples_per_second": 249.87,
+      "eval_steps_per_second": 31.383,
+      "step": 1608
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.0491,
+      "step": 1876
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.6602195501327515,
+      "eval_matthews_correlation": 0.6923970453235757,
+      "eval_runtime": 4.1609,
+      "eval_samples_per_second": 250.666,
+      "eval_steps_per_second": 31.484,
+      "step": 1876
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.0302,
+      "step": 2144
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.736823320388794,
+      "eval_matthews_correlation": 0.6918731340886707,
+      "eval_runtime": 4.1639,
+      "eval_samples_per_second": 250.489,
+      "eval_steps_per_second": 31.461,
+      "step": 2144
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.0285,
+      "step": 2412
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.75467848777771,
+      "eval_matthews_correlation": 0.6870314619595771,
+      "eval_runtime": 4.1797,
+      "eval_samples_per_second": 249.539,
+      "eval_steps_per_second": 31.342,
+      "step": 2412
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0223,
+      "step": 2680
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.7401058673858643,
+      "eval_matthews_correlation": 0.6918731340886707,
+      "eval_runtime": 4.1828,
+      "eval_samples_per_second": 249.355,
+      "eval_steps_per_second": 31.319,
+      "step": 2680
+    },
+    {
+      "epoch": 10.0,
+      "step": 2680,
+      "total_flos": 3594991817003520.0,
+      "train_loss": 0.14064713289488606,
+      "train_runtime": 1047.1976,
+      "train_samples_per_second": 81.656,
+      "train_steps_per_second": 2.559
+    }
+  ],
+  "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 sha256:719fdcfc239818ee4305683550f23db32fe982d1bf55acb087b84b8b4b109268
+size 2671