Run 4. Outer Step 21. Inner Step 25.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526233,
-    5526239,
-    5526245,
-    5526250,
-    5526256
+    5526262,
+    5526268,
+    5526273,
+    5526279,
+    5526285
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "inner_steps": 0,
   "last_allreduce_block": 5513324,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2012a2760167d21596c556f51f548e349ec03617ddcd2b46bb152159d199e9f3
+oid sha256:ea50ee6e87152f1212ee3a36e47541037feb487716c0b78348058cfb5bf4ef2d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:622b315d4df2f61b0f0318d5aecb2ae2d051a1872302243fcae83174ab9614ea
+oid sha256:b6572a7359740a027f8b83689aa846ac64abfd689bce1623848c4fb2f72c7086
 size 4040701744