Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
+  "_name_or_path": "distilbert-base-multilingual-cased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -13,6 +13,7 @@
   "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,
@@ -21,5 +22,5 @@
   "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.28.0",
-  "vocab_size": 30522
+  "vocab_size": 119547
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4dc1fd339f0ca825857960dceb49c33b0f13ecd9f917dd3a37c5db58e1785dc
-size 267855533
+oid sha256:cb575ac9e1b5ace85c95e006307cd2baae83af0dcbcab73f0d9e74a00fa5f1b9
+size 541340333

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "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 sha256:9c13917a547adbfc7b7a797d55ee7da8d226ee71489972b1e5277168d6f55bec
+oid sha256:c730ffeca52eb629ede7adb0b7d9a543a97744375583722c5f2d64b8f0a993bd
 size 3643