Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
+  "_name_or_path": "Geotrend/distilbert-base-ru-cased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForMaskedLM"
@@ -13,6 +13,7 @@
   "model_type": "distilbert",
   "n_heads": 12,
   "n_layers": 6,
+  "output_past": true,
   "pad_token_id": 0,
   "qa_dropout": 0.1,
   "seq_classif_dropout": 0.2,
@@ -20,5 +21,5 @@
   "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.36.2",
-  "vocab_size": 30522
+  "vocab_size": 14283
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c70a850dce55dfe6bbde24d2017b6447d15aad69cfd7f0019147fa21c25434ca
-size 267954768
+oid sha256:44439ebe36f595508c6223d41c98aa2b778176fe412bde8ad3f416c13020d0ec
+size 218003556

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db8953ecf71979aacee8df32220f6e8599f350c7171592d67936a2d6c30ad5e1
+oid sha256:af09d947dcd014b6469e28a984144dd86912b412dc875bd4e5f03e14fcca28a0
 size 4728