Run 4. Outer Step 56. Inner Step 8.

config.json

@@ -267,19 +267,13 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [
-    5599555,
-    5599559,
-    5599563,
-    5599567,
-    5599571
-  ],
+  "block_list": [],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 3,
+  "inner_step": 8,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b13d5c1ac6c54294dc5cedfa38bb8ee470c82be134160d560ba5dcc357d2441
+oid sha256:7aaf7adfb5b15185ce8e81267fd8d03223c38ada2ab6b8b9600ccbb99e18b92a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0537a66c7bf82e0b7ffc66a3e83a04218d20645778ad9e30fd14daa80708948a
+oid sha256:300545904e3bfa7e344293cf33d69628dcdf9a13b25432d1c6c99173fcf44134
 size 4040701744