Training in progress, step 400

config.json

@@ -20,7 +20,7 @@
   "decoder_layers": 6,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "dropout_rate": 0.05,
+  "dropout_rate": 0.1,
   "encoder_attention_heads": 8,
   "encoder_ffn_dim": 2048,
   "encoder_layerdrop": 0.0,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c7db4e2214a28443a06cff652c74096c09099b40c27961531ce632ea9c2eba8
+oid sha256:e0840bb66afaede00ab2b8e34930e3655862f1734bbb6fd21242f04787c2d8f9
 size 290459230

runs/Jan13_18-19-28_instance-20240113-151743/events.out.tfevents.1705170352.instance-20240113-151743

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:132b0d90a396869889fc7a2603e5febf3d11d973b4240c38afc5ae1e7ae6182d
+size 7845

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00c82bba85e55c20847c2dab79477e4b2f79b58084fa1939b32ced3e6aa95c58
+oid sha256:81de6a67d0c6eb5836f322aa9c06e04375d7a78252ff214ea6b5aaea5bd50c66
 size 4984