Training in progress, step 500

config.json

@@ -1,25 +1,25 @@
 {
-  "_name_or_path": "microsoft/deberta-v3-xsmall",
+  "_name_or_path": "microsoft/deberta-v3-base",
   "architectures": [
     "DebertaV2ForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 384,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 1536,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-07,
   "max_position_embeddings": 512,
   "max_relative_positions": -1,
   "model_type": "deberta-v2",
   "norm_rel_ebd": "layer_norm",
-  "num_attention_heads": 6,
+  "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "pooler_dropout": 0,
   "pooler_hidden_act": "gelu",
-  "pooler_hidden_size": 384,
+  "pooler_hidden_size": 768,
   "pos_att_type": [
     "p2c",
     "c2p"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adca21531de52ba1622a8208366290326b1b08e9635e560c29c59041dd000c22
-size 283860016
+oid sha256:aae86d32a9f0b6c1dea2ae74395163f52d7c9f5daccfdb2384bd9db40d20dddf
+size 738231856

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b8843fd60452b2ee77050a224e132fba9e3f23d97e3fab65f26b6ed69f8dd70
+oid sha256:075ae1fbccd329b3e256a3e7c66c8ecde732bae31e872953b8f24b031f0856a6
 size 4600