Training in progress, step 1000

config.json

@@ -19,7 +19,7 @@
   "decoder_layerdrop": 0.0,
   "decoder_layers": 4,
   "decoder_start_token_id": 50258,
-  "dropout": 0.1,
+  "dropout": 0.01,
   "encoder_attention_heads": 6,
   "encoder_ffn_dim": 1536,
   "encoder_layerdrop": 0.0,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67345c492fdbd1ec95751a30c2e0ff4219c87df765040ac4cf876800a7674f5f
+oid sha256:216a345eca862adcff71298b5230a6bee2c3a482be0271531e7fc61e9e04f21d
 size 151061672

runs/Sep16_06-12-55_c022839ab943/events.out.tfevents.1726467177.c022839ab943.214.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50c20f7ee5470250ba4ae1b2f4b671d4cd7e0ada1d1af55ff7f650324b002363
+size 12404

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:082c8e154950256fb5e9f793dffe02af0fce47e44a19eebefd0c6b21cef8bffe
+oid sha256:2de850da4ef513e7b8300785382aa27890e12994f5f9c9c7f2763d02bbe0f340
 size 5496