Training in progress, step 500

config.json

@@ -1,18 +1,19 @@
 {
-  "_name_or_path": "microsoft/deberta-base",
+  "_name_or_path": "microsoft/deberta-v3-base",
   "architectures": [
-    "DebertaForSequenceClassification"
+    "DebertaV2ForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
+  "hidden_dropout_prob": 0.5,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-07,
   "max_position_embeddings": 512,
   "max_relative_positions": -1,
-  "model_type": "deberta",
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
@@ -20,13 +21,15 @@
   "pooler_hidden_act": "gelu",
   "pooler_hidden_size": 768,
   "pos_att_type": [
-    "c2p",
-    "p2c"
+    "p2c",
+    "c2p"
   ],
   "position_biased_input": false,
+  "position_buckets": 256,
   "relative_attention": true,
+  "share_att_key": true,
   "torch_dtype": "float32",
   "transformers_version": "4.42.4",
   "type_vocab_size": 0,
-  "vocab_size": 50265
+  "vocab_size": 128100
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f33405386dce3f90800d3931d83da15bdce499fdf5a3526a3e47920523ce559
-size 556799560
+oid sha256:e07b7308f6f36be00733bed8b37148023cf0947ae2619c59031dcb48dd880f01
+size 737719272

runs/Sep04_16-42-01_0ecfd9ff1619/events.out.tfevents.1725468135.0ecfd9ff1619.2927.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1dd4abf1e0ae2c85997e560b7c31502b6689a0dddc8ce479fd54efef36237dc
+size 5927

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b1eb15a591d4d048b9736d82305d22ce128b6860c935ce7dd4b2388a3dd6b1e
+oid sha256:d32be354cdec47d29bc1f8e98e13bd37902babd35bd9a8299642238b1051981c
 size 5176