Training in progress, epoch 1

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -1,36 +1,44 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_name_or_path": "Babelscape/wikineural-multilingual-ner",
   "architectures": [
     "BertForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "directionality": "bidi",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
     "0": "O",
-    "1": "B-PER",
-    "2": "I-PER",
-    "3": "B-ORG",
-    "4": "I-ORG",
-    "5": "B-LOC",
-    "6": "I-LOC",
-    "7": "B-MISC",
-    "8": "I-MISC"
+    "1": "B-corporation",
+    "2": "I-corporation",
+    "3": "B-creative-work",
+    "4": "I-creative-work",
+    "5": "B-group",
+    "6": "I-group",
+    "7": "B-location",
+    "8": "I-location",
+    "9": "B-person",
+    "10": "I-person",
+    "11": "B-product",
+    "12": "I-product"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "B-LOC": 5,
-    "B-MISC": 7,
-    "B-ORG": 3,
-    "B-PER": 1,
-    "I-LOC": 6,
-    "I-MISC": 8,
-    "I-ORG": 4,
-    "I-PER": 2,
+    "B-corporation": 1,
+    "B-creative-work": 3,
+    "B-group": 5,
+    "B-location": 7,
+    "B-person": 9,
+    "B-product": 11,
+    "I-corporation": 2,
+    "I-creative-work": 4,
+    "I-group": 6,
+    "I-location": 8,
+    "I-person": 10,
+    "I-product": 12,
     "O": 0
   },
   "layer_norm_eps": 1e-12,
@@ -39,10 +47,15 @@
   "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",
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.32.1",
+  "transformers_version": "4.27.0.dev0",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 119547
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6dca96e635c16b42bc3463b148e16b86ca4a5008fc05b35d4bbbe349d613a9e
-size 430971305
+oid sha256:19b092115eead75b466456ab33bf2e06bc8d1b12aacf6928b3fd20579df1a504
+size 709160685

tokenizer_config.json

@@ -1,11 +1,11 @@
 {
-  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e62c319e56643b1324f76b8bead3dee7ccdf1daaafda57f7ada31094a2c2ec9f
-size 4027
+oid sha256:afdbe76b5cbf22e6a19c916ddd7f9ff30097725200d9a98a946f90d5770f3727
+size 3515