Training in progress, epoch 0

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "FacebookAI/xlm-roberta-base",
+  "_name_or_path": "FacebookAI/roberta-base",
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
@@ -28,10 +28,9 @@
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "model_type": "roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
@@ -39,5 +38,5 @@
   "transformers_version": "4.39.3",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f410d43746c01c0f5ca4cb8191f6280c6de4a90a2195838ab3addd26763a1c7
-size 1112214236
+oid sha256:4cb61f2e08ebd913ef94644fa3a02ffe0bba1364fd7dbe684cbc7caaffdef977
+size 498622052

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4661b2cb6b8a1007906509fe18cbfbc03062a086102bf7b80cfedb80f16c37
-size 17082854
+oid sha256:6a5e0a8892d7e66e3265eaf425e6d51489e1fc56995846ea9fb3397878de4d2e
+size 2108713

tokenizer_config.json

@@ -1,9 +1,10 @@
 {
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -11,7 +12,7 @@
     "1": {
       "content": "<pad>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -19,7 +20,7 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -27,12 +28,12 @@
     "3": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "250001": {
+    "50264": {
       "content": "<mask>",
       "lstrip": true,
       "normalized": false,
@@ -45,10 +46,12 @@
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
+  "errors": "replace",
   "mask_token": "<mask>",
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "tokenizer_class": "XLMRobertaTokenizer",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfe1a9010091611acb02cff979ee3bfc4100ed35aa6a5c4d9e4942f7ba8ae4c4
+oid sha256:18cf78a3a5078b79837909cc3e999501f79bc0a7b40d2cd75aaf7ed1a55b6c40
 size 4920