Run 4. Outer Step 12. Inner Step 5.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5508562,
-    5508566,
-    5508569,
-    5508573,
-    5508576,
-    5508580,
-    5508584
+    5508588,
+    5508591,
+    5508595,
+    5508599,
+    5508603,
+    5508606,
+    5508610
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 4,
+  "inner_step": 5,
   "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 sha256:5b2c83c6a7e7ffb75ad7c09896853fd0d2d42286b7304e73fbbebda805525154
+oid sha256:f05c44fbf524e5e8e92966c7cfbc84565649bc698ef25a89f806b6a881809a2d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7efa13437d1cbc1a036a8ed186e9ce9013e70a673681ea4aa6af2f9d38f8e7e8
+oid sha256:1b74849f1b1958eb81c8a1b4e0b86b57dc800bedcc17e99d6b0252315192a640
 size 4040701744