Training in progress, step 200

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "NbAiLab/nb-bert-base",
   "architectures": [
-    "XLMRobertaForTokenClassification"
+    "BertForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -15,28 +15,36 @@
     "1": "B-STARTDATE",
     "2": "I-STARTDATE",
     "3": "B-SALARY",
-    "4": "I-SALARY"
+    "4": "I-SALARY",
+    "5": "B-WORKPLACE",
+    "6": "I-WORKPLACE"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
     "B-SALARY": 3,
     "B-STARTDATE": 1,
+    "B-WORKPLACE": 5,
     "I-SALARY": 4,
     "I-STARTDATE": 2,
+    "I-WORKPLACE": 6,
     "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,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.11.3",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 119547
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7267bcecc3332c3a4fc7107d5bf540a4ad2e56010e1817393dcf715e1c11bcdb
-size 1109912305
+oid sha256:7042212b39d9e47a97dbc2f3de158272cd5a045c84ea8291ca79995a050341ee
+size 709156337

runs/Oct26_12-23-04_e777c2f2731e/1635251346.6031783/events.out.tfevents.1635251346.e777c2f2731e.741.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3475e9456db4a78306f82819e06971aab37fc059f645615818f9433a4d12f45
+size 4535

runs/Oct26_12-23-04_e777c2f2731e/events.out.tfevents.1635251346.e777c2f2731e.741.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c0387360ac4ea20dc01877cf9732ba44bd81770d71be9417b5d8d8cd249237d
+size 4117

special_tokens_map.json

@@ -1 +1 @@
-{"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}}
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -1 +1 @@
-{"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"}
+{"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"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a31d83a8b45794f7395978e7f9e1cbcb5d2eebfcf9daa6c4ab55e1f630ac8d64
+oid sha256:de8d0e3672b6b2ccdc401fd59e24885e3bdcedc43ecda452502205bcf8e0c871
 size 2863