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:bc77370c448684cb3a563b54e27fb7b827b4daf4f3ba00fb66d191b5a4eb7521
+oid sha256:2098d92c18b5cee98d09315ded251fba4f3193a90b61f3d883d087013deac9df
 size 151061672

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50c20f7ee5470250ba4ae1b2f4b671d4cd7e0ada1d1af55ff7f650324b002363
-size 12404
+oid sha256:b9ea5ef5d04b64cc6b5f0342924fae6d8cfbef4da24e037a88b50fe493d2f03b
+size 15150

runs/Sep17_01-47-47_b3f97db4a34e/events.out.tfevents.1726537670.b3f97db4a34e.451.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9ae584c537fa395245ee92f6026e6a1bbc85418e79f4d1f72cf4c2792944d2
+size 12404

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcb94234bdcb41074afee8803976d6b1c6898bd8c065da031a1c54322afdd07a
+oid sha256:15818f580b0adde9c0f9bc6dcf5575ac604eefc5fe1b6a39392a2f69989de32b
 size 5496