Training in progress, step 500

config.json

@@ -14,7 +14,7 @@
   "d_model": 384,
   "decoder_attention_heads": 6,
   "decoder_ffn_dim": 1536,
-  "decoder_layerdrop": 0.05,
+  "decoder_layerdrop": 0.0,
   "decoder_layers": 4,
   "decoder_start_token_id": 50258,
   "dropout": 0.1,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e127fb2d03f2c7be2f5f8900354078adff5afe690348e216faed947ed7297034
+oid sha256:6482e31aaa42a418d30cd86712f1ffb77e65dc593153a6e4e7274a56318507dd
 size 151097331

runs/Dec08_15-11-56_ip-172-16-55-172.ap-south-1.compute.internal/events.out.tfevents.1670512495.ip-172-16-55-172.ap-south-1.compute.internal.26079.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69d6346a0aa461940a79800900e7f0df53838c88f7d6f9a6edae3474c8481435
-size 14653
+oid sha256:b1eb1db1cfea58283ce9b5fce3723670828747c7a1440215f5e3117b1c35a9dd
+size 14967

runs/Dec08_17-03-16_ip-172-16-55-172.ap-south-1.compute.internal/1670519020.3428178/events.out.tfevents.1670519020.ip-172-16-55-172.ap-south-1.compute.internal.26079.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d7db0a6effdd5770f36eb3da95cbe129537b007efcb86f6eb0984fcbeb55fc2
+size 5803

runs/Dec08_17-03-16_ip-172-16-55-172.ap-south-1.compute.internal/events.out.tfevents.1670519020.ip-172-16-55-172.ap-south-1.compute.internal.26079.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cb52e4c0d9767ec5bd04360b30cd5d8c01d5f04c039c806f74f8eefd4d02b6c
+size 7736

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac1a60c354e521b9a92de7531574a4b86cc11ee4e8f832a7be9e358fe648d490
+oid sha256:e4cb4d88e892c34a61877f1b032ffe74b12333a7ad390274494dab70a381bf8b
 size 3567