Training in progress, epoch 1

added_tokens.json

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

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "classla/xlm-roberta-base-multilingual-text-genre-classifier",
+  "_name_or_path": "klue/roberta-base",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -7,6 +7,7 @@
   "bos_token_id": 0,
   "classifier_dropout": null,
   "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -53,13 +54,13 @@
   "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "tokenizer_class": "BertTokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.33.2",
+  "transformers_version": "4.34.0",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 32000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29d10d54ec3d0c6f2933c9d6dd169ce154e06c01479fda3912bd6c066b481e05
-size 1112292209
+oid sha256:446220dc869a69bbe3c1aa43cacb218929b2b4aa012b75cd11465bc45adb01e2
+size 442590065

special_tokens_map.json

@@ -1,15 +1,9 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:affcfb1f45c4b14a70a6589c3d153b430ed4309e5a6613a88dab64d5a923a5d6
-size 17082925
+oid sha256:f528deccb283323c613f41f4cd7cd1ab207d533f13acf524fc27678317e2ed5c
+size 752097

tokenizer_config.json

@@ -1,29 +1,60 @@
 {
-  "bos_token": "<s>",
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": false,
-  "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "max_length": 512,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_to_multiple_of": null,
-  "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
-  "sep_token": "</s>",
-  "stride": 0,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "<unk>"
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a8988cf8b091cf988d07c7ebd0bec50f75c8f2a0452cfbe28cd1ea956c697fa
+oid sha256:39a55c006bbec520686e9d3bf51be88e268c1d4382cecd5401c6f24bf63fb9c6
 size 4091

unigram.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71b44701d7efd054205115acfa6ef126c5d2f84bd3affe0c59e48163674d19a6
-size 14763234
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260