Run 3. Outer Step 12. Inner Step 67.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5470097,
-    5470100,
-    5470103,
-    5470105,
-    5470108
+    5470143,
+    5470145,
+    5470147,
+    5470150,
+    5470152
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 66,
+  "inner_step": 67,
   "inner_steps": 0,
   "last_allreduce_block": 5450451,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a36aec60b6bfffb8cb0c973c0e9934064b7a7fd2a9ca00e46a09619530b4a3e
+oid sha256:2021391e75ea364dba188d33ee3a470a2a88461a1c59b56e98df2423875b9ca0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2de6c9cb5fb40476e2824c47a4285d287d7ad5eb35449c40f96161b3d0a8da38
+oid sha256:cbc79f765f369f19990cd87c60a0f8cb64509127b96e28b58e614444a1af1b10
 size 4040701744