Run 4. Outer Step 11. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5508030,
-    5508036,
-    5508041,
-    5508047,
-    5508053
+    5508059,
+    5508065,
+    5508071,
+    5508076,
+    5508082
   ],
   "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": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4986359060f7d3c7e32edeec2215234d974ae2877ac6aa5630ae8945f522b881
+oid sha256:e9942a540a350e149104625e504e838c9792159f3be170dff13eab2fccb39fbf
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d43691d2153312898931b3550abdf3a2911d2f4b335ae76c1ed184bf65d174b5
+oid sha256:0df256b89593d24d6d3ad2eb0ff6abf6c9b6c607db1e6eebc50c6837c7e4a7a7
 size 4040701744