Training in progress, step 340

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
+  "_name_or_path": "distilbert/distilbert-base-multilingual-cased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -23,6 +23,7 @@
   "model_type": "distilbert",
   "n_heads": 12,
   "n_layers": 6,
+  "output_past": true,
   "pad_token_id": 0,
   "problem_type": "single_label_classification",
   "qa_dropout": 0.1,
@@ -31,5 +32,5 @@
   "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.45.2",
-  "vocab_size": 30522
+  "vocab_size": 119547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c80a8b2d6114696cb7dbacd5d5051d4abb7daf5195bd33dcdf352b1f9bf78e18
-size 267835644
+oid sha256:82e3a244bf300007b0a931adc596a3f822522b06103e67942495d6cc4d532ee7
+size 541320452

tokenizer_config.json

@@ -43,7 +43,7 @@
   },
   "clean_up_tokenization_spaces": false,
   "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:d455bda7f1a74add0479266bd7d56a33beebd3c1147591d78bbcdfc653e912c4
+oid sha256:31a64c49e00e567395f60a900f6abf50291428f9b4704620d84845ac2f1802ec
 size 5176