Training in progress, step 200

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "NbAiLab/nb-bert-base",
+  "_name_or_path": "xlm-roberta-base",
   "architectures": [
-    "BertForTokenClassification"
+    "XLMRobertaForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "directionality": "bidi",
-  "gradient_checkpointing": false,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -17,34 +17,34 @@
     "3": "B-SALARY",
     "4": "I-SALARY",
     "5": "B-WORKPLACE",
-    "6": "I-WORKPLACE"
+    "6": "I-WORKPLACE",
+    "7": "B-WORKHOURS",
+    "8": "I-WORKHOURS"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
     "B-SALARY": 3,
     "B-STARTDATE": 1,
+    "B-WORKHOURS": 7,
     "B-WORKPLACE": 5,
     "I-SALARY": 4,
     "I-STARTDATE": 2,
+    "I-WORKHOURS": 8,
     "I-WORKPLACE": 6,
     "O": 0
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "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",
+  "output_past": true,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.11.3",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 119547
+  "vocab_size": 250002
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d990e43ba6bd92251ed0c2574f34ee624c32232cc4c9047461290dd8fff4fbfa
-size 709156337
+oid sha256:1a3074f7f2154bd0b7c022de80893d77702b3e045daf6f77881d627e9e06dffb
+size 1109929655

special_tokens_map.json

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

tokenizer_config.json

@@ -1 +1 @@
-{"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, "special_tokens_map_file": null, "name_or_path": "NbAiLab/nb-bert-base", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base", "tokenizer_class": "XLMRobertaTokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de8d0e3672b6b2ccdc401fd59e24885e3bdcedc43ecda452502205bcf8e0c871
+oid sha256:d887dd2b62bb50ddd0267a86ea7537aa81a66c0edbb282f23381a173fb5eed3f
 size 2863