Training in progress, epoch 1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -1,11 +1,9 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "microsoft/deberta-v3-base",
   "architectures": [
-    "BertForTokenClassification"
+    "DebertaV2ForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -45,16 +43,27 @@
     "I-TaskName": 12,
     "O": 0
   },
-  "layer_norm_eps": 1e-12,
+  "layer_norm_eps": 1e-07,
   "max_position_embeddings": 512,
-  "model_type": "bert",
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
   "torch_dtype": "float32",
   "transformers_version": "4.23.1",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "type_vocab_size": 0,
+  "vocab_size": 128100
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e4d15d595efafa800453610c5f561aa4a9899c79971a687c4b3013d10bd1330
-size 435683121
+oid sha256:3caac61944e37ff1fe421707daf1fc313870544851fdc48063c0e89081442f0b
+size 735443887

special_tokens_map.json

@@ -1,5 +1,7 @@
 {
+  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -1,15 +1,17 @@
 {
   "add_prefix_space": true,
+  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "name_or_path": "bert-base-uncased",
+  "name_or_path": "microsoft/deberta-v3-base",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
   "special_tokens_map_file": null,
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f86581a44d3378a536fe67952e3ecc0fe10db95841c20a2d1fbf1bdbfe5a8589
+oid sha256:a330159fe90edd986bfad9c324118455920beceb6cc1eaed04e9fde6ec47bba6
 size 3503