Add model and its dependencies

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9277522935779816,
+    "eval_loss": 0.27098390460014343,
+    "eval_runtime": 2.2877,
+    "eval_samples": 872,
+    "eval_samples_per_second": 381.163,
+    "eval_steps_per_second": 47.645,
+    "train_loss": 0.06368534423393195,
+    "train_runtime": 4424.0603,
+    "train_samples": 67349,
+    "train_samples_per_second": 152.233,
+    "train_steps_per_second": 4.758
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "sst2",
+  "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_accuracy": 0.9277522935779816,
+    "eval_loss": 0.27098390460014343,
+    "eval_runtime": 2.2877,
+    "eval_samples": 872,
+    "eval_samples_per_second": 381.163,
+    "eval_steps_per_second": 47.645
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a095879d3ba5b240397d52915841bf1cb4541973da804843feebd5c2e4fb74c
+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": 0.06368534423393195,
+    "train_runtime": 4424.0603,
+    "train_samples": 67349,
+    "train_samples_per_second": 152.233,
+    "train_steps_per_second": 4.758
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.9277522935779816,
+  "best_model_checkpoint": "./electra-base-discriminator/fine_tuned_models/checkpoint-8420",
+  "epoch": 10.0,
+  "global_step": 21050,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.8398562688161604e-05,
+      "loss": 0.2419,
+      "step": 2105
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9197247706422018,
+      "eval_loss": 0.2374826818704605,
+      "eval_runtime": 2.2228,
+      "eval_samples_per_second": 392.305,
+      "eval_steps_per_second": 49.038,
+      "step": 2105
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6354277945032536e-05,
+      "loss": 0.1208,
+      "step": 4210
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9151376146788991,
+      "eval_loss": 0.286760151386261,
+      "eval_runtime": 2.2241,
+      "eval_samples_per_second": 392.062,
+      "eval_steps_per_second": 49.008,
+      "step": 4210
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.4309993201903469e-05,
+      "loss": 0.0825,
+      "step": 6315
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.926605504587156,
+      "eval_loss": 0.28928259015083313,
+      "eval_runtime": 2.2158,
+      "eval_samples_per_second": 393.539,
+      "eval_steps_per_second": 49.192,
+      "step": 6315
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.2265708458774402e-05,
+      "loss": 0.0589,
+      "step": 8420
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9277522935779816,
+      "eval_loss": 0.27098390460014343,
+      "eval_runtime": 2.2371,
+      "eval_samples_per_second": 389.795,
+      "eval_steps_per_second": 48.724,
+      "step": 8420
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.0221423715645335e-05,
+      "loss": 0.0432,
+      "step": 10525
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9231651376146789,
+      "eval_loss": 0.27629274129867554,
+      "eval_runtime": 2.2178,
+      "eval_samples_per_second": 393.189,
+      "eval_steps_per_second": 49.149,
+      "step": 10525
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 8.177138972516268e-06,
+      "loss": 0.0323,
+      "step": 12630
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9162844036697247,
+      "eval_loss": 0.4470421373844147,
+      "eval_runtime": 2.2244,
+      "eval_samples_per_second": 392.01,
+      "eval_steps_per_second": 49.001,
+      "step": 12630
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 6.132854229387201e-06,
+      "loss": 0.0231,
+      "step": 14735
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9197247706422018,
+      "eval_loss": 0.4118638336658478,
+      "eval_runtime": 2.2272,
+      "eval_samples_per_second": 391.523,
+      "eval_steps_per_second": 48.94,
+      "step": 14735
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.088569486258134e-06,
+      "loss": 0.0157,
+      "step": 16840
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9243119266055045,
+      "eval_loss": 0.5020723342895508,
+      "eval_runtime": 2.2328,
+      "eval_samples_per_second": 390.544,
+      "eval_steps_per_second": 48.818,
+      "step": 16840
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.044284743129067e-06,
+      "loss": 0.0113,
+      "step": 18945
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9185779816513762,
+      "eval_loss": 0.5500479936599731,
+      "eval_runtime": 2.2323,
+      "eval_samples_per_second": 390.626,
+      "eval_steps_per_second": 48.828,
+      "step": 18945
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0072,
+      "step": 21050
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9208715596330275,
+      "eval_loss": 0.6200240850448608,
+      "eval_runtime": 2.2351,
+      "eval_samples_per_second": 390.131,
+      "eval_steps_per_second": 48.766,
+      "step": 21050
+    },
+    {
+      "epoch": 10.0,
+      "step": 21050,
+      "total_flos": 2.831471218376448e+16,
+      "train_loss": 0.06368534423393195,
+      "train_runtime": 4424.0603,
+      "train_samples_per_second": 152.233,
+      "train_steps_per_second": 4.758
+    }
+  ],
+  "max_steps": 21050,
+  "num_train_epochs": 10,
+  "total_flos": 2.831471218376448e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6204848aba33756940ef473300773c051bbb48efe2c99bbda0e36baa0db8fac
+size 2671