Training in progress, step 500

config.json

@@ -19,7 +19,7 @@
   "decoder_layerdrop": 0.0,
   "decoder_layers": 12,
   "decoder_start_token_id": 50258,
-  "dropout": 0.0,
+  "dropout": 0.4,
   "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 sha256:8706d985f7947399b1b957815ce4cad097142e220b276bf64e517b0582c32d33
+oid sha256:89b1904deb64a63996a5045399740ecc86099484aff939008ff53d79bcb776a0
 size 966995080

runs/May31_13-21-08_a100gpu5/events.out.tfevents.1717154477.a100gpu5.2286578.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7279b96b972290d2eaf37bb69ed387f5adda20b680e69099bce9f486c3ea871f
+size 12215

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db2f057801b2b5336c8231b4149b5b48eb293b3d1978bb2d0b9baab729ba9a2c
+oid sha256:02840a62a0aba2d3050541b48ae140a6ac3999f9c8c3f5966ec3c4f14d3514c6
 size 5112