model improved

config.json

@@ -9366,6 +9366,7 @@
     "X|_|root": 4672
   },
   "layer_norm_eps": 1e-07,
+  "legacy": true,
   "max_position_embeddings": 512,
   "max_relative_positions": -1,
   "model_type": "deberta-v2",
@@ -9383,7 +9384,7 @@
   "relative_attention": true,
   "tokenizer_class": "BertTokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.40.1",
+  "transformers_version": "4.48.3",
   "type_vocab_size": 0,
   "vocab_size": 30000
 }

maker.py

@@ -52,7 +52,7 @@ devDS=UDgoeswithDataset("dev.conllu",tkz)
 testDS=UDgoeswithDataset("test.conllu",tkz)
 lid=trainDS(devDS,testDS)
 cfg=AutoConfig.from_pretrained(src,num_labels=len(lid),label2id=lid,id2label={i:l for l,i in lid.items()},ignore_mismatched_sizes=True)
-arg=TrainingArguments(num_train_epochs=3,per_device_train_batch_size=8,output_dir="/tmp",overwrite_output_dir=True,save_total_limit=2,evaluation_strategy="epoch",learning_rate=5e-05,warmup_ratio=0.1,save_safetensors=False)
+arg=TrainingArguments(num_train_epochs=10,per_device_train_batch_size=8,output_dir="/tmp",overwrite_output_dir=True,save_total_limit=2,evaluation_strategy="epoch",learning_rate=5e-05,warmup_ratio=0.1,save_safetensors=False)
 trn=Trainer(args=arg,data_collator=DataCollatorForTokenClassification(tkz),model=AutoModelForTokenClassification.from_pretrained(src,config=cfg,ignore_mismatched_sizes=True),train_dataset=trainDS,eval_dataset=devDS)
 trn.train()
 trn.save_model(tgt)

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c0039ae0ac5f0f44b9c11bce933ae5d3c30672146177d4b99c6ec85ebc5e91
-size 506684053
+oid sha256:cf0b46037eb8048f79e62efe3aa96f219b5b84b938752ba2dc0dbc2108303ca6
+size 506686562

tokenizer_config.json

@@ -45,6 +45,7 @@
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": true,
+  "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "never_split": [