Run 4. Outer Step 22. Inner Step 13.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5527060,
-    5527066,
-    5527072,
-    5527078,
-    5527084
+    5527091,
+    5527096,
+    5527103,
+    5527109,
+    5527116
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bcc9e345dca22422a842e0d5311d7a41b98d39c1f604c201dd72f8218fcdeaa
+oid sha256:8c422c4648b4732e039cb423b7b417a458fa927120aabfc4c03b782b0aa13d49
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02ca0b7f7bba5614e744fe7d66fec69f38971121abfc6db930931d58d402923
+oid sha256:cd97022644af1e6dd2e243ad02f8a02383b15f59eaa207b2ca7c39e984946e1c
 size 4040701744