Run 4. Outer Step 60. Inner Step 23.

config.json

@@ -267,13 +267,19 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [],
+  "block_list": [
+    5607990,
+    5607996,
+    5608000,
+    5608005,
+    5608009
+  ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0fb6a5b1c9b724e2ea3d112ee74f53ffe01d3f8b915512aa2acf15c6ae9634f
+oid sha256:da2591691ce5f741ade3e31e847c32a68e3a2b3e7a4854da8aaa9fa5c24c9b23
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bd3ce1a719cf42bb8d9203c56f63b7ac7d66baeaa7152d4b6fef33108c2f7f5
+oid sha256:cee37ca995987fc1e4f6fc8896329b7e9a8e31925b0520915a47756601871e6b
 size 4040701744