Run 4. Outer Step 38. Inner Step 8.

config.json

@@ -268,20 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5553824,
-    5553828,
-    5553832,
-    5553836,
-    5553840,
-    5553844,
-    5553848
+    5553853,
+    5553857,
+    5553861,
+    5553866,
+    5553870,
+    5553874
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 8,
   "inner_steps": 0,
   "last_allreduce_block": 5552497,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1396ed67a6eeee0ec14056544c8c2318d9fa8f79a91a16e597a51da41c3d3843
+oid sha256:56001eb184f75ecb455153b3fa787044c3b16a14df901febaae457907ae89b17
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b5bba951e1999ee198cdacacf82552ac70a31474ce3e796aef634133e542e1
+oid sha256:038e4d3b8cc7503ebc441904fcf5f88ad3856f7a96e413b3d5df772c4473468c
 size 4040701744