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 sha256:18340d1aeb511620d81a0e60429efe4b6cc0ce1b0c30bcef84ad0d32bec0cc34
+oid sha256:fddc86e57fdf624e81385b05d51b4de3a936e09c87451857d08e086f230ed1d9
 size 151061672

runs/Jun05_09-39-23_8c117880d29e/events.out.tfevents.1717580390.8c117880d29e.667.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:556d7a6f67f1e13c898ce1b9f6c3a6bf440456353466e6c2cc1779db7d4520f2
+size 14428

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1732f6db65415878a312ba1513caa310fd3f98e37f2878ddba06a4e712d827b9
+oid sha256:d4e8e1abe17343a1f26c8431eea32c94d510a86331bd8afa5b6b992111574ea1
 size 5240