Training in progress, step 400

config.json

@@ -19,7 +19,7 @@
   "decoder_layerdrop": 0.0,
   "decoder_layers": 12,
   "decoder_start_token_id": 50258,
-  "dropout": 0.15,
+  "dropout": 0.1,
   "encoder_attention_heads": 12,
   "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7583078277c78c92692c59694ef6020329f60690ad525ea101a6148d0d7653c
+oid sha256:c17173362fbfadfb86cde7583a5424b40ca80231c218e422872fcf0444d5339c
 size 966995080

runs/Sep04_01-47-55_289943d7ae45/events.out.tfevents.1725414506.289943d7ae45.694.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f6507acae1713e6eb370d425e52a543ad3846c5686fcfce9a95e907fbf8e0f2
-size 10069
+oid sha256:a87ce11e1e8fa2704fbb788a6b7f9710caabc25f66b58ea3d908cb6b8c8d5d63
+size 11231

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec3629cef4f70d1b50cc534d80437da7b22d15565b9c61d8a10359e824124c39
+oid sha256:6eb88dcba416d2219778feee275f4a8e0fd1de2ed13d1482262a5f49c93fc9dd
 size 5240