Saving weights and log at step 1080000

README.md

@@ -27,7 +27,7 @@ Tokenizer:
 Training details:
 
 * Training started on step 360K (bs 16) ppl 21 of earlier model trained with Adam optimizer.
-* Training at step 1000K of 2082K (48%) ppl 15,2
+* Training at step 1080K of 2082K (52%) ppl 15,1
 * Block size: 512
 * Optimizer: adafactor
 * Learning rate: 3.3e-5

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d77af2bdb5c6b7fbeae905633a8986e9c97140208268cd3a34909ebf30b1536
+oid sha256:ab367a621176cf8e8c1c13e41b1ef8aef5d7df98135ba8803d7e3d1ce591c18e
 size 3096134690

opt_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:751daf3e7e3c5efa79ffa8a1cece06bd7cdb4fc23d141b13c64e75b61c0d4f48
+oid sha256:5b2906977c4631bbd76367193367d3208a6203cbaaed59cc4cd3eb66568ac7db
 size 5611008

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8461ae6051ce46f98cdf810433154389d1871441325eda9f8d4380e0e688be54
+oid sha256:7414a181d9192a0c65970236c6939c47883da37e47627a96989461b8e035ccdd
 size 3134045897

runs/events.out.tfevents.1641055391.t1v-n-f9cfcc28-w-0.112189.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:391e0abb9a67782191b2beb53ef7eef37caca761eec84e5f63d2000ee7a76404
-size 149388427
+oid sha256:ec1a823dab3749a65583fa2c40f9c71543fc4962693a34b4597536232e157816
+size 162517787

training_state.json

@@ -1 +1 @@
-{"step": 1000001}
+{"step": 1080001}