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 sha256:7ad414bd0fc8543ce7675cb358dba25b1a219556c0f17f8e6bf72f8009e49b98
-size 430908208
+oid sha256:e8ed1b7924711e452214e25a5f1727ade771879e52cddaf986a1167d189fe9b1
+size 709080904

runs/Apr24_16-45-57_dll-3gpu3/events.out.tfevents.1713969958.dll-3gpu3.3518932.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cde9602fbc7e5f7e19ee951ab1043d7f5d7b44e2cc70d31a9e862331f975856
+size 5027

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 sha256:7eb12560430626e9a469239933e335e281c01b38a553febed8c4aabba73228c6
+oid sha256:78320cf9b6359efc180b3030f0c10c2a1772f1a9d42bee224c4195eecd61144f
 size 4920