Training in progress, step 10

config.json

@@ -5,7 +5,7 @@
   "architectures": [
     "LEDForConditionalGeneration"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.05,
   "attention_window": [
     1024,
     1024,
@@ -30,6 +30,7 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 6,
   "eos_token_id": 2,
+  "hidden_dropout_prob": 0.05,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c578035e50f7fd95a45dc29725b737c57d70977a1bb2427fd480bbdf4cfd3663
+oid sha256:7ff0ccc551d23c36d88094adc7514f23582fcdbe21ce853eca03404400268ca6
 size 647614116

runs/Jul12_05-14-38_25f1d5bfa6fe/events.out.tfevents.1720761305.25f1d5bfa6fe.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aec6192e122ee4323eceaa6ee1142e3b45570b6b7a1150be066e5c63e97bd96
+size 5860

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66d0d1ddf703ff8bdae190c0494d9faea013b5593bf910509f549def825b58d7
+oid sha256:f3983ad88b467a43f94b682f161094b8706d8dd89bbc84a118a4c6c5d411b9d8
 size 5240