Run 3. Outer Step 9. Inner Step 65.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5409698,
-    5409699,
-    5409701,
-    5409703,
-    5409706
+    5409734,
+    5409735,
+    5409737,
+    5409740,
+    5409743
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 63,
+  "inner_step": 65,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b82559bda3395b900d3eb605938f3dbb83f334a52bbc54222bddc02a8cb9cd53
+oid sha256:271b52dffe415325229fd87702297c32fee6252e4af6a9f0cc991c5269d28e81
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16176373fa1e11a25f0d5d3c12cd70ca8fa2c66fb222d398def9e0f6ed1ed88f
+oid sha256:ceea4ec2667b90fbda5b7470249ece96e9d92be4db966bc72ff549e0b66baee3
 size 4040701744