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 sha256:8552a9320419737e7e390cd8b009cfd861f9fd90f5598787f8d316c7989e3836
-size 430908208
+oid sha256:243a2ed5814a5e09daaac17326341b596bab0132437e6ef74079dcde2a0ab080
+size 709080904

runs/Apr26_23-21-01_tdll-3gpu1/events.out.tfevents.1714166462.tdll-3gpu1.1180687.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb67c74356ade1fa47291e8a83fc8592b01d646c9f1cb0bd163f270f1fe92b10
+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:a1d58eaef55d93b6553bf8759ef725d1648d05f9cf170303e6c5bf19f5862840
+oid sha256:719295443d546ca0cdc27a5099d0d9cd13db243deffdb57086891d9d7b110280
 size 4920