Training in progress, step 500

config.json

@@ -2,13 +2,13 @@
   "architectures": [
     "DebertaForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.01,
+  "attention_probs_dropout_prob": 0.05,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.01,
+  "hidden_dropout_prob": 0.05,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "layer_norm_eps": 1e-07,
+  "layer_norm_eps": 1e-05,
   "legacy": true,
   "max_position_embeddings": 512,
   "max_relative_positions": -1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edd31bf5c2d1cb957759c507f7153e029c225e84ace6a1b564325d306057a1f1
+oid sha256:4e7f8c6fec052de4a83c675765c7668a20a8ce6d218be49dda79b77437509fc6
 size 556799560

runs/May05_03-58-40_316a0eaf9060/events.out.tfevents.1746417542.316a0eaf9060.259.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9191eb21efbc0d22db373e4752d0042e445a158431856cd8d7b5a3301e23ddab
+size 5225

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a50ea4e73f2b3d0af395175433d3aa9e5d548229324ebe32fb602f1ec83970c5
+oid sha256:287f07ca565f3369b75bcf8f024887bef957e7bea56e6fb4febb5cbd1fa24e9d
 size 5304