Add model and its dependencies

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "google/electra-base-discriminator",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "embedding_size": 768,
+  "finetuning_task": "mnli",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03bc7060469f053a0e7015daafc20c7428cf675edf280a1dc3d97efb4eabd34d
+size 438023533

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"}

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.8860927152317881,
+  "best_model_checkpoint": "./outputs/electra-base-uncased/fine_tuned_models/checkpoint-36816",
+  "epoch": 5.0,
+  "global_step": 61360,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.7388593694651082e-05,
+      "loss": 0.4571,
+      "step": 12272
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8808965868568518,
+      "eval_loss": 0.3177725374698639,
+      "eval_runtime": 24.4511,
+      "eval_samples_per_second": 401.414,
+      "eval_steps_per_second": 50.182,
+      "step": 12272
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.3041445270988312e-05,
+      "loss": 0.2786,
+      "step": 24544
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8843606724401426,
+      "eval_loss": 0.3345130681991577,
+      "eval_runtime": 24.46,
+      "eval_samples_per_second": 401.267,
+      "eval_steps_per_second": 50.163,
+      "step": 24544
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.694296847325541e-06,
+      "loss": 0.1852,
+      "step": 36816
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8860927152317881,
+      "eval_loss": 0.41067004203796387,
+      "eval_runtime": 24.4548,
+      "eval_samples_per_second": 401.352,
+      "eval_steps_per_second": 50.174,
+      "step": 36816
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.3471484236627705e-06,
+      "loss": 0.1257,
+      "step": 49088
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8854814060112073,
+      "eval_loss": 0.4864971339702606,
+      "eval_runtime": 24.4819,
+      "eval_samples_per_second": 400.909,
+      "eval_steps_per_second": 50.119,
+      "step": 49088
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.0892,
+      "step": 61360
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8858889454915945,
+      "eval_loss": 0.5802900791168213,
+      "eval_runtime": 24.5033,
+      "eval_samples_per_second": 400.558,
+      "eval_steps_per_second": 50.075,
+      "step": 61360
+    },
+    {
+      "epoch": 5.0,
+      "step": 61360,
+      "total_flos": 1.6510003421181696e+17,
+      "train_loss": 0.2271464799187174,
+      "train_runtime": 13411.6836,
+      "train_samples_per_second": 146.403,
+      "train_steps_per_second": 4.575
+    }
+  ],
+  "max_steps": 61360,
+  "num_train_epochs": 5,
+  "total_flos": 1.6510003421181696e+17,
+  "trial_name": null,
+  "trial_params": null
+}