Training in progress, epoch 1

added_tokens.json

@@ -1,7 +1,7 @@
 {
-  "[CLS]": 0,
+  "[CLS]": 2,
   "[MASK]": 4,
-  "[PAD]": 1,
-  "[SEP]": 2,
-  "[UNK]": 3
+  "[PAD]": 0,
+  "[SEP]": 3,
+  "[UNK]": 1
 }

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "klue/roberta-base",
+  "_name_or_path": "kykim/bert-kor-base",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
+  "directionality": "bidi",
+  "embedding_size": 768,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
@@ -49,18 +49,22 @@
     "LABEL_8": 8,
     "LABEL_9": 9
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
   "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",
-  "tokenizer_class": "BertTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.34.0",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 42000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68dfac82fcf3e918f7d932073c0326afaa4da666d63a3a6eacf774b4412c5f92
-size 442590065
+oid sha256:55b5489cbd6693c7e73e177cdcdb60318f7b232fd142610ddd521a544eb15bee
+size 473306993

special_tokens_map.json

@@ -1,7 +1,5 @@
 {
-  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f528deccb283323c613f41f4cd7cd1ab207d533f13acf524fc27678317e2ed5c
-size 752097
+oid sha256:508df639d8abd9ad6ed6ebc0ed892f31fb7f1f091fe7a9cddec42dfd939e25fd
+size 1007781

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[CLS]",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "[PAD]",
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "[SEP]",
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,7 +25,7 @@
       "special": true
     },
     "3": {
-      "content": "[UNK]",
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -42,18 +42,16 @@
     }
   },
   "additional_special_tokens": [],
-  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
-  "do_lower_case": false,
-  "eos_token": "[SEP]",
+  "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "strip_accents": 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 sha256:39a55c006bbec520686e9d3bf51be88e268c1d4382cecd5401c6f24bf63fb9c6
+oid sha256:a82cb208c80ab4085bd749641b69b336a485f16e651b65e0a15df02234ffe084
 size 4091