Training in progress, step 102

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert/distilbert-base-multilingual-cased",
+  "_name_or_path": "distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -23,7 +23,6 @@
   "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,
@@ -32,5 +31,5 @@
   "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.45.2",
-  "vocab_size": 119547
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70216bd33a63e68fc06767f1b1786cc9b026a405c0318b722da54734a53170d0
-size 541320452
+oid sha256:7df245748d5c776ce4ffd0b929fefe2154e603e917dc321cdfb61f89017b49f3
+size 267835644

tokenizer_config.json

@@ -43,7 +43,7 @@
   },
   "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
-  "do_lower_case": false,
+  "do_lower_case": true,
   "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 sha256:5e546cbaa3a25d3a4cde313c6682928ed81fbf249ba6e6112c5890aaf6057a12
+oid sha256:92b34e833d87b5b5baa1af1a144c7eb6ae7db6731cb9f35f463dfe91a7340f12
 size 5176