Saving weights and log at step 880000

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 800K of 2M (38%) ppl 15,3[D
+* Training at step 880K of 2M (38%) ppl 15,3
 * 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 sha256:154b7b3ce133740107ea7a047d2925f56384b902ca711d54565edbed32eaecf0
+oid sha256:cfc08d5c4120eff8f546db9675affda9bdaba5b8dfe2e81f9257a499e1b3b53c
 size 3096134690

opt_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c2f2374b237f8ede160a1917f986b87c9c4c5f42a8bb0cecd5e629fadb70611
+oid sha256:384b781970c22b5c572a23c3bf0f384c614dd13a0815f125b896de9735228377
 size 5611008

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b83d532814eda9eb5e2d22190b579ed962180d7876ae12912d2646cc5a7ea8d
+oid sha256:6c85a006e388f0880cef392c8d434653cc69d3377ac9f44f6fa8ca6ba6bb2799
 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 sha256:6b8c3b6576329b97c2b78ea1f06d27c20a76fd902ad80bd437cbc202eef9f82b
-size 119474337
+oid sha256:8e01abfe0cb320dd193e448be51c5c1c7473b01caef47ea4246cf07d8b5e9f24
+size 131559285

training_state.json

@@ -1 +1 @@
-{"step": 800001}
+{"step": 880001}