Training in progress, step 500

config.json

@@ -8,7 +8,7 @@
   "d_model": 512,
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
-  "dropout": 0.2,
+  "dropout": 0.3,
   "dropout_rate": 0.1,
   "eos_token_id": 1,
   "feed_forward_proj": "relu",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8799758159a5cb2a3832179bcd3ba584c32bb9a4782daaf59cc718e8441ab537
+oid sha256:882f3ae4a9a04ee9ee22f5c199b1b5f743c7a436be8a640b628a0732db37ef13
 size 242071641

runs/Mar23_09-28-59_4ed3d44c87f5/1711186216.9374185/events.out.tfevents.1711186216.4ed3d44c87f5.204.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:738e3e46d765e1339bb302350257713acb648a5a5110477814a2bb7ae528a535
+size 6046

runs/Mar23_09-28-59_4ed3d44c87f5/events.out.tfevents.1711186216.4ed3d44c87f5.204.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fbef0c5b656932ce9531a10e1861b9148d23edae3530e6f330a024e0a019cfa
+size 4950

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e78d7f87f267450cb08ad34ac63fcba60daef5a2969b696d41449afe6b5fcab3
+oid sha256:23159a287ed76afcfc4cae059da7ead9f9dae6e157f798fa7968deee0d8b5cd8
 size 3707