Run 4. Outer Step 40. Inner Step 36.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5556365,
-    5556370,
-    5556374,
-    5556378,
-    5556382
+    5556387,
+    5556391,
+    5556395,
+    5556399,
+    5556403
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0b1aa9f908aaa76fb6ed33134c77d71655fdcb9a4013041fccd35bb0350e852
+oid sha256:4de425a4dd4d01714c313ba0f023488fd0fa247d7f920b33618f308e05f1894b
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f899946c61698bd2b07cac02204e7b991cdc3222432213dd5d4163496ad7c7c9
+oid sha256:386e54ed1a2f67838f5b9fff6ce8f293f451b580a3fc3226310e0fe8000109ef
 size 4040701744