Training in progress, epoch 1

config.json

@@ -1,12 +1,11 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "dmis-lab/biobert-v1.1",
   "architectures": [
-    "XLMRobertaForTokenClassification"
+    "BertForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "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,
@@ -22,17 +21,16 @@
     "I-EXT": 2,
     "O": 0
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.30.2",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 28996
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a0d7dac7a55fc406374cb12df8a0c9c734559c489ea477dfb9898338fcce4de
-size 1109892529
+oid sha256:a3facdc4174a3ad54fd4cfe0c630fed64c2dd94ee7e207da8a316d87816562c5
+size 430958385

runs/Aug18_12-01-36_cn2895/events.out.tfevents.1692374500.cn2895.861833.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a4f1cbdc04c857a061abac35ae8be69eb8dd553082e7b63f6197a7a64333467
-size 6954
+oid sha256:5205087acefac5d4fcbec548450f49dd29affd79e66f7ba835d619f743b3291a
+size 7308

runs/Aug18_12-11-51_cn2895/events.out.tfevents.1692375115.cn2895.890363.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a69e940998ab0bdcbec5cf9f6a3bab912544608269cad55a79b49ccc940de667
+size 4550

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "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>"
+  "cls_token": "[CLS]",
+  "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:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
-size 17082758
+oid sha256:cb26b43c98e8266ae3e99c2a583cf8315d73b33a17e6b20b4df7ff1f22392d34
+size 669021

tokenizer_config.json

@@ -1,19 +1,15 @@
 {
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "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 sha256:49afad50630d8cb8066e27efcb8da907bfc57a1afd9b443f851313e7f2c41364
+oid sha256:2d3d869c1dc09335af57d4d50530d5906a9649a19cc96a72b9c9d66d25f945af
 size 3887