Run 4. Outer Step 58. Inner Step 27.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5586906,
-    5586911,
-    5586915,
-    5586919,
-    5586923
+    5586929,
+    5586933,
+    5586937,
+    5586942,
+    5586946
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 26,
+  "inner_step": 27,
   "inner_steps": 0,
   "last_allreduce_block": 5583387,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:650848d354cf8281286df2c64e61d12096c51456cc9b510b840871d8cf966187
+oid sha256:4250160187041c6ae402b2afac02afa2fc74090d193627c104760891acc4f60d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9e216af5d11dbb3efa7950e27d480ff409cbda21e9397d444af7bf893de2d7a
+oid sha256:80b91ed8df6ce129dd7728b7b7b086e364800478e10ca71997144e1d3f428a33
 size 4040701744