Add model and its dependencies

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.580573558807373,
+    "eval_matthews_correlation": 0.7068649074843276,
+    "eval_runtime": 4.2746,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 243.999,
+    "eval_steps_per_second": 30.646,
+    "train_loss": 0.14022661696619063,
+    "train_runtime": 1094.6693,
+    "train_samples": 8551,
+    "train_samples_per_second": 78.115,
+    "train_steps_per_second": 2.448
+}

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": 0.580573558807373,
+    "eval_matthews_correlation": 0.7068649074843276,
+    "eval_runtime": 4.2746,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 243.999,
+    "eval_steps_per_second": 30.646
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b96ed75763999e3da3bc26cc31a1644ba4dc99a37c00c595de4b8d7d729176ec
+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": 0.14022661696619063,
+    "train_runtime": 1094.6693,
+    "train_samples": 8551,
+    "train_samples_per_second": 78.115,
+    "train_steps_per_second": 2.448
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.7068649074843276,
+  "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": 0.4974,
+      "step": 268
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.3856096863746643,
+      "eval_matthews_correlation": 0.6039307167689609,
+      "eval_runtime": 4.0975,
+      "eval_samples_per_second": 254.544,
+      "eval_steps_per_second": 31.971,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.3024,
+      "step": 536
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.3309681713581085,
+      "eval_matthews_correlation": 0.6557131266546689,
+      "eval_runtime": 4.2881,
+      "eval_samples_per_second": 243.234,
+      "eval_steps_per_second": 30.55,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.1855,
+      "step": 804
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.3909442722797394,
+      "eval_matthews_correlation": 0.6679153499290561,
+      "eval_runtime": 4.2794,
+      "eval_samples_per_second": 243.728,
+      "eval_steps_per_second": 30.612,
+      "step": 804
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.1278,
+      "step": 1072
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.4562387764453888,
+      "eval_matthews_correlation": 0.6657078975506158,
+      "eval_runtime": 4.2964,
+      "eval_samples_per_second": 242.759,
+      "eval_steps_per_second": 30.49,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.094,
+      "step": 1340
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.634463906288147,
+      "eval_matthews_correlation": 0.6304318137769176,
+      "eval_runtime": 4.2802,
+      "eval_samples_per_second": 243.682,
+      "eval_steps_per_second": 30.606,
+      "step": 1340
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.0685,
+      "step": 1608
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.6211329698562622,
+      "eval_matthews_correlation": 0.6700089525749314,
+      "eval_runtime": 4.2939,
+      "eval_samples_per_second": 242.905,
+      "eval_steps_per_second": 30.509,
+      "step": 1608
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.048,
+      "step": 1876
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.580573558807373,
+      "eval_matthews_correlation": 0.7068649074843276,
+      "eval_runtime": 4.3122,
+      "eval_samples_per_second": 241.873,
+      "eval_steps_per_second": 30.379,
+      "step": 1876
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.0352,
+      "step": 2144
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.6809670329093933,
+      "eval_matthews_correlation": 0.6773861896003048,
+      "eval_runtime": 4.3021,
+      "eval_samples_per_second": 242.442,
+      "eval_steps_per_second": 30.451,
+      "step": 2144
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.0253,
+      "step": 2412
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.7312929034233093,
+      "eval_matthews_correlation": 0.6850707271866645,
+      "eval_runtime": 4.3106,
+      "eval_samples_per_second": 241.961,
+      "eval_steps_per_second": 30.39,
+      "step": 2412
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0181,
+      "step": 2680
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.7737548351287842,
+      "eval_matthews_correlation": 0.6578435355005723,
+      "eval_runtime": 4.3001,
+      "eval_samples_per_second": 242.555,
+      "eval_steps_per_second": 30.465,
+      "step": 2680
+    },
+    {
+      "epoch": 10.0,
+      "step": 2680,
+      "total_flos": 3594991817003520.0,
+      "train_loss": 0.14022661696619063,
+      "train_runtime": 1094.6693,
+      "train_samples_per_second": 78.115,
+      "train_steps_per_second": 2.448
+    }
+  ],
+  "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 sha256:52b669402b4faae05c5ca39940fe23587fed833d3b1039d55d55dac8f4a1748e
+size 2671