Training in progress, step 500

config.json

@@ -2,9 +2,9 @@
   "architectures": [
     "DebertaForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.5,
-  "hidden_act": "sigmoid",
-  "hidden_dropout_prob": 0.5,
+  "attention_probs_dropout_prob": 0.01,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.01,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
@@ -17,7 +17,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "pooler_dropout": 0,
-  "pooler_hidden_act": "sigmoid",
+  "pooler_hidden_act": "gelu",
   "pooler_hidden_size": 768,
   "pos_att_type": [
     "c2p",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a360c71d3508f772a19a09a6cb8b6d4f7fa0c9655180756ad646433010ba113
+oid sha256:7d7c9f3a3a67b727a9624d865a817bdd0593a9f0ade50325bf931257945657e3
 size 556799560

runs/May04_15-09-31_2585728651be/events.out.tfevents.1746372126.2585728651be.220.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73d15f8134a7007ea134b45577e65e7022a89088a0d11040eff7210f832655e1
+size 405

runs/May04_15-28-22_2585728651be/events.out.tfevents.1746372524.2585728651be.220.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70a56405b1dedd6baad46e8cb66d1225202a3d1521c825545af0a0b9ae63db52
+size 5224

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37182fa6384f053bbe64bd5fc582a7ddf9aa889c7058e29829620d5e76753402
+oid sha256:a50ea4e73f2b3d0af395175433d3aa9e5d548229324ebe32fb602f1ec83970c5
 size 5304