1epoch trained on PAWS

.gitignore

@@ -0,0 +1 @@
+checkpoint-*

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 5.64251610059892,
+    "train_runtime": 333.7038,
+    "train_samples": 7931,
+    "train_samples_per_second": 23.767,
+    "train_steps_per_second": 2.973
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "exBertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "base_model": "beomi/kcbert-base",
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "ex_hidden_size": 252,
+  "ex_intermediate_size": 1024,
+  "ex_num_attention_heads": 12,
+  "ex_num_hidden_layers": 12,
+  "ex_vocab_size": 20135,
+  "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": 300,
+  "model_type": "exbert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "transformers_version": "4.7.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50135
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22b79319a7b3d601effaa9452c0128d7e3ba5c7395cc26f885bd79257f03aa7d
+size 672770099

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, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "use_fast": true, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "exbert"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 5.64251610059892,
+    "train_runtime": 333.7038,
+    "train_samples": 7931,
+    "train_samples_per_second": 23.767,
+    "train_steps_per_second": 2.973
+}

trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 992,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.994959677419355e-05,
+      "loss": 10.8889,
+      "step": 1
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.4798387096774196e-05,
+      "loss": 5.9914,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "step": 992,
+      "total_flos": 2400440637256200.0,
+      "train_loss": 5.64251610059892,
+      "train_runtime": 333.7038,
+      "train_samples_per_second": 23.767,
+      "train_steps_per_second": 2.973
+    }
+  ],
+  "max_steps": 992,
+  "num_train_epochs": 1,
+  "total_flos": 2400440637256200.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c726d8f9c0eb16add1fb83e2d0607a69ad2a6405e5ee5d0744223baa48c49873
+size 2479