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,
   "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:ec3d425758658dfea738cf936a26e93796ce35b2843103927bb30063f210e635
+oid sha256:8a59b05b8aaf92683baae85565b4827ab0d98731614caf65b49af4d3978053a9
 size 290459230

runs/Jan13_13-30-18_instance-20240113-135745-ai/events.out.tfevents.1705152714.instance-20240113-135745-ai

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae9beac1b9cb748a9b94d1cce5b65492fd604c11831491cf856ad2be55f99f0e
+size 5349

runs/Jan13_13-35-11_instance-20240113-135745-ai/events.out.tfevents.1705152926.instance-20240113-135745-ai

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1ca5488c01088350241a0a6371fc4f77d396f0040c6a74b8f0ddc49787bc41b
+size 5349

runs/Jan13_13-43-55_instance-20240113-135745-ai/events.out.tfevents.1705153449.instance-20240113-135745-ai

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddccedb7d7e3d4757dc4cb4ca1a29d138ee8fce34c3d93b5e87e424b6fd7daeb
+size 7846

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:296a1b5983235d0ce0f132001f520b0d4e75efa2679f312fe95e35d481a80931
+oid sha256:d565a190248dd08cd1cb42616d17d49135f78bfad33e5e11837325a8ca3594ac
 size 4984