Training in progress, step 1000

config.json

@@ -16,7 +16,7 @@
   "decoder_layerdrop": 0.0,
   "decoder_layers": 6,
   "decoder_start_token_id": 50258,
-  "dropout": 0.01,
+  "dropout": 0.0,
   "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 sha256:9ebc8d99df81d1d0dc60de9a1543783581c460eff038d299c0a64d524565153f
+oid sha256:ac33227aca9032ad107fdaee5a2584ffffef257f9c5418a93282c3bc391fe8d3
 size 290403936

runs/Oct22_01-45-37_b633203d4f25/events.out.tfevents.1729561543.b633203d4f25.775.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45021937d1b57bfb12559a204a6a9657fd540e7439880edc34a3089a80a5e702
-size 88
+oid sha256:cfed202bec86ddb489584a2213a4d30beede30c263eabd816321558335261e81
+size 6908

runs/Oct22_01-46-27_b633203d4f25/events.out.tfevents.1729561589.b633203d4f25.775.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:204c206adf69e22985a562c751fd7c59af17182b8b0247704dfb68bdcc852254
+size 12391

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bb7a7e9527a3f5dd98c6ae945ce1c56310851755329e5d53d3b864bb640c5fb
+oid sha256:82aeac8955920584efb2087541d986aa8051d6f728568bbdc660cb02b1906685
 size 5496