Saving weights and log at step 940000

README.md

@@ -30,7 +30,7 @@ Tokenizer:
 Training details:
 
 * Trained for 70K steps (batch size 64) to ppl 27 on mc4 nl tiny 1 epoch
-* Trained for 900K steps (batch size 16) to ppl 16.2 on mc4 nl full
+* Trained for 940K steps (batch size 16) to ppl 16.1 on mc4 nl full
 * Training continuing
 * Block size: 512
 * Optimizer: adafactor

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dd15b6b3443195b649c98349863cdb4ea5db416d0af59deb752c4f0cefda8b7
+oid sha256:0fc6108ceb04b0eb260bb51e05c838bfe34edb9dae95beb56b8ee0188fb40d74
 size 5262314590

opt_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b55d3da77e33f432751d34890d4cc45a029eaae21192b2b6edaa17ef14e6bcf
+oid sha256:78016f9de2503a950519f04f279d254035f8fb347e507eb2c8745626f07d9340
 size 5778100

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d626da36deceb8dcf070caea44a7d037038c4b1167bd59b28909295bdecb588
+oid sha256:142e35c1e7519d17d1f81c70452f6395dae97c9f47078469a81f398744893181
 size 5363100545

runs/events.out.tfevents.1641156371.t1v-n-2f64d7c8-w-0.13342.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4876750cb0514a8349c9db283b9941a0aad2ea9877924149192c49e19162db1
-size 134442753
+oid sha256:c3cb59e175ed446f3a057a221aaab3eed4ab0a69effd75db86b78e074d3b7062
+size 141080779

training_state.json

@@ -1 +1 @@
-{"step": 900001}
+{"step": 940001}