Run 4. Outer Step 40. Inner Step 1.

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": [
+    5555385,
+    5555389,
+    5555394,
+    5555398,
+    5555402
+  ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 1,
   "inner_steps": 0,
   "last_allreduce_block": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad0d00ffe039a1d8af53737af7f65e1227901c71566c8b7833c81a2e60f7066f
+oid sha256:01094e88a32b775841234e4305275668fc04e71b68a5c1bec03fcc85f45b340c
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed7722acc0394bb91c8cb851ce0e959424d902fa873f762513d418fd2d62a613
+oid sha256:d561b13a11942b8c3c47270ca6486df5f2dea2a5dae7499ad2d406d13d26b9f0
 size 4040701744