Training in progress, step 500

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "mor40/BulBERT-chitanka-model",
   "architectures": [
     "RobertaForMaskedLM"
   ],
@@ -12,11 +13,11 @@
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 514,
+  "max_position_embeddings": 512,
   "model_type": "roberta",
   "num_attention_heads": 12,
-  "num_hidden_layers": 8,
-  "pad_token_id": 1,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.43.3",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c16ea98a33ac294388d173e8cfc0ea8ed770adb90e2044337b7024e8402b63b0
-size 385403316
+oid sha256:4062a7fe97add279eb46837fa6346ae7cf376fdde8f989d4acb3ac50771f6603
+size 328690332

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf2e2d7d3e257c2e599571dd035f2ac337eab22ee22c47a7ffdebd9c2eb9a326
+oid sha256:814e9fa4fa2245bb2cc7e8094171f3622f64b41eeee31c4259eed2cc59d18122
 size 5112