Training in progress, step 500

config.json

@@ -27,7 +27,7 @@
   "sep_token_id": 3,
   "tokenizer_class": "BertTokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.18.0",
+  "transformers_version": "4.23.1",
   "type_vocab_size": 2,
   "use_bias": true,
   "use_cache": true,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a98998d836300b9ac25bf126cfb72cf8f17256f4f1b99b5b020ac82e7ce5e95b
+oid sha256:9792675217775a7ad2fe611dd0bafb66a2a5ad9b3b20f7881e82b7703e28d797
 size 471656101

special_tokens_map.json

@@ -1 +1,9 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
+{
+  "bos_token": "<s>",
+  "cls_token": "[CLS]",
+  "eos_token": "</s>",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -1 +1,18 @@
-{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "do_basic_tokenize": true, "never_split": null, "bos_token": "<s>", "eos_token": "</s>", "model_max_length": 4096, "special_tokens_map_file": "/root/.cache/huggingface/transformers/9bea998b48658e35dd618115a266f6c173183a9a4261fc6e40730d74c4b67899.e3640e465e51ce85d94923a0b396029ecc2e3e4c7764031eee57ab272637652d", "name_or_path": "monologg/kobigbird-bert-base", "tokenizer_class": "BertTokenizer"}
+{
+  "bos_token": "<s>",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "mask_token": "[MASK]",
+  "model_max_length": 4096,
+  "name_or_path": "monologg/kobigbird-bert-base",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--monologg--kobigbird-bert-base/snapshots/ceacda477e20abef2c929adfa4a07c6f811323be/special_tokens_map.json",
+  "strip_accents": null,
+  "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 sha256:6df2cdfff5fe8404f0231a1c598c3ed7542d3465301ae6cfe808ad207420bd8e
-size 3055
+oid sha256:3925bb80239522d983700f0eccc7f574288f88b028d65d3aa88da73b7823422a
+size 3375