Training in progress, epoch 1

added_tokens.json

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

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "mor40/BulBERT-chitanka-model",
+  "_name_or_path": "mor40/BulBERT-ner-bsnlp",
   "architectures": [
     "BertForTokenClassification"
   ],
@@ -44,7 +44,7 @@
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.33.2",
+  "transformers_version": "4.34.0",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 50265

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0383f2e05f287f4422929606085404b7e9d436cb8ab77b3b2e14dce31ee022a9
+oid sha256:a4af337cdbb8a43a244cf7dae1cb5d002a65381a4ed24b911fa9fce675320968
 size 326176745

tokenizer_config.json

@@ -1,13 +1,60 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "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": [],
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
+  "max_length": 512,
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0adf010e53280ae84a0e74913b1645ed874c5c5a26453e800ff653845b90a1f
-size 4027
+oid sha256:500b8e8582c6faabdbf0025e5a88bf388b8159567f9ae5788871babdf215cdae
+size 4091