Run 3. Outer Step 12. Inner Step 66.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5470052,
-    5470055,
-    5470058,
-    5470061,
-    5470064
+    5470097,
+    5470100,
+    5470103,
+    5470105,
+    5470108
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 65,
+  "inner_step": 66,
   "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 sha256:65808802886bd6cec59910e0749c72c0408c1670b2ccc17463140723ddfe43f3
+oid sha256:3a36aec60b6bfffb8cb0c973c0e9934064b7a7fd2a9ca00e46a09619530b4a3e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a93c6962def76571e96353b47aec707d72c3ef70e24ed3f5a8df9f8f9a4ff5a
+oid sha256:2de6c9cb5fb40476e2824c47a4285d287d7ad5eb35449c40f96161b3d0a8da38
 size 4040701744