Run 4. Outer Step 51. Inner Step 33.

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": [
+    5627898,
+    5627926
+  ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 30,
+  "inner_step": 33,
   "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 sha256:08b15135a87d18bd3cd6948a2cdd39221f9e1adac20d6c337c89a57d43697dc2
+oid sha256:7c4d41187ce165b21e8dfb2f4b0be69bc62e3086a46780491680039acbe41619
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:616059b4e25b5dd5795b2386e2e69e316de82eb9a829adce9740741bc704307c
+oid sha256:7a250aa99b8162bb686ee5624f678fe273e020240264ec4cc24478476244bc9d
 size 4040701744