Training in progress, epoch 1

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "xlm-roberta-large",
+  "_name_or_path": "roberta-base",
   "architectures": [
-    "XLMRobertaForTokenClassification"
+    "RobertaForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
@@ -9,7 +9,7 @@
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "O",
     "1": "B-PERSON",
@@ -38,7 +38,7 @@
     "24": "U-LOCATION"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
     "B-DATE": 9,
     "B-LOCATION": 21,
@@ -68,15 +68,14 @@
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "output_past": true,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.26.1",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 50265
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c90f2fa5dc8facd602c05e96ea276d1b864a787528b28499aec28a7e2c460192
-size 2235605165
+oid sha256:86974988ac962a96776957e35f872ae143265fa7b94be8ea728bc93fec87c1ff
+size 496369773

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
-size 17082758
+oid sha256:a60abad17917ed62a89b321bd425a54df25c2d9af89161f31a67bfefa04a9ac9
+size 2108687

tokenizer_config.json

@@ -3,19 +3,14 @@
   "bos_token": "<s>",
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "errors": "replace",
+  "mask_token": "<mask>",
   "model_max_length": 512,
-  "name_or_path": "xlm-roberta-large",
+  "name_or_path": "roberta-base",
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "special_tokens_map_file": null,
-  "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:c9e6bf0c8c477a8b2c7bef0d86b92fff377e426d4b88688cdc9ce727fb1f04fb
+oid sha256:1bdfb61a75607104e2c981d1e502da1b197887d8593bfe88255e5644f410dfb8
 size 3451