Run 4. Outer Step 58. Inner Step 22.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603226,
-    5603232,
-    5603238,
-    5603244,
-    5603250
+    5603258,
+    5603264,
+    5603270,
+    5603276,
+    5603282
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 22,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:529ad853ad5b289f52b5f877e39b5d41efe47603547f0aa5222c1a0e5c92fc4a
+oid sha256:a3d68ce1e4c3be5f54b2c26857cf25e222548eb9ccb57c90b6ab381e9c76ec5f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0fcf6c060c4a8774ac80d29d1058b851c37d91ea86ef4eaaac5d8c066756f38
+oid sha256:815263c295977ba9827a8dbeb4a5cdc8985643eb726eef521dc7dc5225f2aa10
 size 4040701744