Training in progress, epoch 1

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "roberta-base",
+  "_name_or_path": "xlm-roberta-large",
   "architectures": [
-    "RobertaForTokenClassification"
+    "XLMRobertaForTokenClassification"
   ],
   "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": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "O",
     "1": "B-PERSON",
@@ -38,7 +38,7 @@
     "24": "U-LOCATION"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "B-DATE": 9,
     "B-LOCATION": 21,
@@ -68,14 +68,15 @@
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
   "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": 50265
+  "vocab_size": 250002
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94198c354b807aaae92711910a6da965fcf50dbb8a4a35ca062809352665b094
-size 496369773
+oid sha256:b9f951be776ada140b1370128b89e915ce001198f04732a5811e234767c62c18
+size 2235605165

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

tokenizer_config.json

@@ -3,14 +3,19 @@
   "bos_token": "<s>",
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "errors": "replace",
-  "mask_token": "<mask>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "model_max_length": 512,
-  "name_or_path": "roberta-base",
+  "name_or_path": "xlm-roberta-large",
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "special_tokens_map_file": null,
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
+  "tokenizer_class": "XLMRobertaTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43c97c84be7b09a25e9f840616a51ad116358faf681cc33edfba5ddefbf749f3
+oid sha256:c9e6bf0c8c477a8b2c7bef0d86b92fff377e426d4b88688cdc9ce727fb1f04fb
 size 3451