Run 4. Outer Step 21. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526291,
-    5526297,
-    5526303,
-    5526308,
-    5526314
+    5526320,
+    5526326,
+    5526331,
+    5526337,
+    5526343
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "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:ea50ee6e87152f1212ee3a36e47541037feb487716c0b78348058cfb5bf4ef2d
+oid sha256:f1e529444e66e4e8b4f6d2c971b18604cf99a0e4efe29931ea897f0e6ec7cabc
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6572a7359740a027f8b83689aa846ac64abfd689bce1623848c4fb2f72c7086
+oid sha256:16c9c7566a82ffe3f3882a2005d2481a37d9a7dff88f03493bd08cafd6ebcb91
 size 4040701744