Run 4. Outer Step 55. Inner Step 8.

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": [
+    5633156,
+    5633185
+  ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 6,
+  "inner_step": 8,
   "inner_steps": 0,
   "last_allreduce_block": 5632906,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f19fdb89b869df984985860d061b40484efbe03b38a0f88739f053b08473776f
+oid sha256:6ed4ca9b0f99492ee02988258efb113c1a7a90bb96af3ebed282eceb8509a106
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44160738d6dbe4fafb5ac51bad059db6988368635d800b14bc3324c3562e3cfd
+oid sha256:6c1c7b0e051d834234cb13406ae2041193bb1a5fcf74320be4ee8d3d02f3b95c
 size 4040701744