Run 4. Outer Step 51. Inner Step 21.

config.json

@@ -267,13 +267,16 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [],
+  "block_list": [
+    5627577,
+    5627605
+  ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 18,
+  "inner_step": 21,
   "inner_steps": 0,
   "last_allreduce_block": 5571611,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93592c3f738813080a456fc75909fb5d11886e980b8fc98deeef2fde2b3506dd
+oid sha256:cae27eabdb404c81e5f2f8f03b72ba5f5f765a46f3acefa1207e91b5e832b097
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f361d7b436dfad05f5ad6bec31ab7b45f9b6f18f12ee32164e5a319a4286cb7d
+oid sha256:5edd01f0eac14b9fc9e12fa26e70adf9a8e6a61b2e456e114bed01850dd5ef2b
 size 4040701744