Run 4. Outer Step 65. Inner Step 87.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5650375,
-    5650402
+    5650430,
+    5650458
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 85,
+  "inner_step": 87,
   "inner_steps": 0,
   "last_allreduce_block": 5648011,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9453af140722e7cd4c859d9d2fdac635ac691c0fbd5b529415c890acf83ee607
+oid sha256:22cb0e630ddb823aaf09865bb570cf3d840c205bf9b92d6ce29c6bee62f5fbf7
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e89e66fd327a53eda2133c9e4660aa53572b9f39e3c3da981af8fb9d862e739a
+oid sha256:7d4529d644292e3a504b93ac7e2f963d12cb5889364ecc6e2aa421dece93a90d
 size 4040701744