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,
+  "dropout_rate": 0.05,
   "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:b0271d6d59002685571be5c6dc020ac3710e4987a1cd31d5ca3e2918f9a9bccb
+oid sha256:2cb0159c8d90013bd4c758d24cc2a480b63c1248b871d881dd56c97a4d3f28cc
 size 290459230

runs/Jan13_16-46-28_instance-20240113-151743/events.out.tfevents.1705165116.instance-20240113-151743

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dceb8fd0b862eb37e6ffcbade2befdb10d82172258a9f34b2f7cb4db135a57c
+size 5348

runs/Jan13_17-13-56_instance-20240113-151743/events.out.tfevents.1705166040.instance-20240113-151743

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05db34e603c5cff799a847f528837236261e0fcd15b1fd1ea683ec26001b1e8c
+size 7848

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47fd7e2afcbcbdf647f8bbd66cad2168e3b2d7cf705a8cdb8506f81c3a531118
+oid sha256:f7b329eeb974d2e2dad342b984fffa20c9975c9bc716ffa8e2c930aaf94a28ab
 size 4984