Training in progress, step 500

config.json

@@ -1,10 +1,11 @@
 {
-  "_name_or_path": "emilyalsentzer/Bio_ClinicalBERT",
+  "_name_or_path": "../models/bert-base-multilingual-cased",
   "architectures": [
     "BertForQuestionAnswering"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "directionality": "bidi",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -16,10 +17,15 @@
   "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": "4.38.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 119547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbcf183433a26dcfa2e4202f127fcb94df42e62827ec335afa4fe8bb5eb828a3
-size 430908208
+oid sha256:f3478725671b1a040850b4a9fedd7ac978117d533c641a8ccc391ff8f3de3c8c
+size 709080904

runs/Apr26_23-13-32_tdll-3gpu3/events.out.tfevents.1714166013.tdll-3gpu3.417869.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adfc1ce2489b142a9937dbc8dad06760b30262f087abec4cc0aba1f8d2fa8abb
+size 5028

tokenizer_config.json

@@ -43,11 +43,9 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
+  "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01078cc4ff97afb3ea602d714ed44787536b4f15c47f21f6385ae639a40f727d
+oid sha256:d39a19f12809a46759d2c5a1d457cdd5ab3b1c7046b9d21eb926cc6956e56a0f
 size 4920