Training in progress, step 500

config.json

@@ -1,11 +1,12 @@
 {
-  "_name_or_path": "skt/kobert-base-v1",
+  "_name_or_path": "kykim/bert-kor-base",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "author": "Heewon Jeon(madjakarta@gmail.com)",
   "classifier_dropout": null,
+  "directionality": "bidi",
+  "embedding_size": 768,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
@@ -18,7 +19,6 @@
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "kobert_version": 1.0,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -30,12 +30,17 @@
   "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.26.1",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 8002
+  "vocab_size": 42000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c77ff64ab58f7c25ee5d56de2d97f8140cc98f8063451e10220324f48b6918d1
-size 368832629
+oid sha256:9ee21002121deb86cb70c57c00663836b9449c691660f1ac546eabf5ed3a5f5b
+size 473274485

runs/Feb15_03-23-13_b575e53afbdf/1676431496.033246/events.out.tfevents.1676431496.b575e53afbdf.353.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ddd2dc5d42573583312276204d9f6fd2043306e86e9f927f77e9c9fbbf6d31
+size 5736

runs/Feb15_03-23-13_b575e53afbdf/events.out.tfevents.1676431496.b575e53afbdf.353.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aced1a9872d9cef2beee4928eceb73e6a5ae5b5c1cf8a6ad720f10e43dc9dbac
+size 4136

special_tokens_map.json

@@ -1,14 +1,6 @@
 {
-  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "[MASK]",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "unk_token": "[UNK]"

tokenizer_config.json

@@ -1,25 +1,16 @@
 {
-  "additional_special_tokens": null,
-  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "eos_token": "[SEP]",
-  "keep_accents": false,
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "[MASK]",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "model_max_length": 1000000000000000019884624838656,
-  "name_or_path": "skt/kobert-base-v1",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "kykim/bert-kor-base",
+  "never_split": null,
   "pad_token": "[PAD]",
-  "remove_space": true,
   "sep_token": "[SEP]",
-  "sp_model_kwargs": {},
-  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--skt--kobert-base-v1/snapshots/a9f5849fce18fb088f0cd0f9b29ec3f756958464/special_tokens_map.json",
-  "tokenizer_class": "KoBERTTokenizer",
+  "special_tokens_map_file": null,
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:797d791fe18cf9a081593e58d3ded7a5f2b7b7feb414a9d2566510a0d6ab48e7
+oid sha256:600a3ef1dce93da4a1978d5696118a7a5110b6593a70a2f81bc5e0e1cfe7526c
 size 3515