Training in progress, step 1000

config.json

@@ -16,7 +16,7 @@
   "decoder_layerdrop": 0.0,
   "decoder_layers": 6,
   "decoder_start_token_id": 50258,
-  "dropout": 0.2,
+  "dropout": 0.1,
   "encoder_attention_heads": 8,
   "encoder_ffn_dim": 2048,
   "encoder_layerdrop": 0.0,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:717ff6721cdc0fec92905c55ec0f915205e48bd9bc37773dfaed8f2157c3ad8a
+oid sha256:339de6a38c3741b04fb97bc0bfa4b726d3d36275dcd54567c818311071460713
 size 290403936

runs/Oct26_10-47-55_99f3b9091519/events.out.tfevents.1729939685.99f3b9091519.1695.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ae8fb5929d435c644e518e1a495a184eb136a05759f54f749687d2ffe948a53
-size 16029
+oid sha256:5cfb9753490abcddfe490721806b8132e3ead24027e5460955d6714dcef1f6b8
+size 17295

runs/Oct26_11-48-39_99f3b9091519/events.out.tfevents.1729943323.99f3b9091519.1695.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c861258a65ee685c9659e082a18ab3fa8c0e61aed6e8cf387e96d58010021a
+size 16029

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cad9d87a3eb2514301e9ef7f2da455fc9117bffd616d9f66712211ea2b75c17
+oid sha256:4165a9818c2b3182da9de8a0411641d9c46ed49a724c5d69798e8f33a18de61d
 size 5496