Training in progress, epoch 1

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "google-bert/bert-base-multilingual-cased",
   "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,
@@ -27,10 +27,15 @@
   "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": "4.41.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 119547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4879168973532b5e903cf9355e2a40ce3594b540e420e15361ae1ee14e27d94b
-size 435599164
+oid sha256:044dfd32818cddb73403f4ab283af1a494029e8bf4d4edd7a5d35149938f8f69
+size 709083980

runs/Jun20_15-32-23_1d781fe7715a/events.out.tfevents.1718897544.1d781fe7715a.1519.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54c46fb69b5e25d5be55ea18bfb0deb0592fa73f8ed928181e21c31477cc70ab
+size 5604

tokenizer_config.json

@@ -43,7 +43,7 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e654d508b821089e26b47094cc0d751e59bf572712b3884103c34a8f0e94744
+oid sha256:1cb377bf37f9f5c2fc32872f354f8168c65fb486366d07b22bc0030e13a97e34
 size 5112