Training in progress, step 30000

config.json

@@ -18,7 +18,7 @@
     "LABEL_0": 0
   },
   "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
+  "max_position_embeddings": 8194,
   "model_type": "xlm-roberta",
   "num_attention_heads": 16,
   "num_hidden_layers": 24,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:737b40310823000d200182b18aa0baffeceda06a4beeb403a4e1c85eed186203
-size 2239614572
+oid sha256:cb6c933724e6625f1ac5c5cb61e8e283e90a353950bed3cf133786d97ebfb0d1
+size 2271071852

tokenizer_config.json

@@ -41,7 +41,6 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
@@ -51,6 +50,7 @@
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
+  "sp_model_kwargs": {},
   "tokenizer_class": "XLMRobertaTokenizer",
   "unk_token": "<unk>"
 }