Training in progress, epoch 1

config.json

@@ -8,7 +8,7 @@
   "d_model": 128,
   "decoder_start_token_id": 259,
   "dense_act_fn": "relu",
-  "dropout_rate": 0.1,
+  "dropout_rate": 0.3,
   "eos_token_id": 1,
   "feed_forward_proj": "relu",
   "initializer_factor": 1.0,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8c715be5902f6892acf3dfc8ce522c7669329cdcac869ec1e0e64745fdfc08f
+oid sha256:47a6230810a39258a2ef6a87c74d02a183ee156947d65189305ec46e4cc63b06
 size 10059592

runs/Nov22_13-52-47_0fe1d4a1022c/events.out.tfevents.1700661168.0fe1d4a1022c.209.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9560c200a55adbfb194749c44526f432efeac8d6216269385936fc36c979b3a
+size 4779

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c8770abfe58123814a2e529e0aeddd56ec46348379902b8501c22745372020c
+oid sha256:6de771aa37db4a1a743cb122fe79bd7ee149348933c60714d2f3b69cde1563bd
 size 4728