Run 4. Outer Step 7. Inner Step 38.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5493613,
-    5493618,
-    5493624,
-    5493629,
-    5493634
+    5493639,
+    5493644,
+    5493649,
+    5493655,
+    5493660
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 37,
+  "inner_step": 38,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:889e5059a5bd27fa866e3556ab6cb9849f442688dc5006a272a7fa0f3d3cf38a
+oid sha256:3f68de9fb13a7e7a8ca10e036868f865dd600ffefb33a05a30ef4e905e028839
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:650a0670687076b9742bb8d698d57598b08751c2d74c821e89c1ba4bf4cf1d33
+oid sha256:633ffc2bf94417fc4ab809cdf736c5cc4940b3af6bea89314e6bf2238e8e3b09
 size 4040701744