Run 4. Outer Step 7. Inner Step 68.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5496106,
-    5496110,
-    5496114,
-    5496118,
-    5496122,
-    5496125
+    5496130,
+    5496134,
+    5496140,
+    5496143,
+    5496147
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 67,
+  "inner_step": 68,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:955e544eadb2d6c32bd7a80e0febc61f7aac14124ce1f07346178fa4651d2774
+oid sha256:0119d265aa94458dfdeb81261f6713794e80ceb79fe8abb7b12cf8df357df7a5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6458d0cfd3d26e09b57c8c1cc9f2f54932748dc2802437afbfe435d985b06ceb
+oid sha256:f2a07248a331746264268f4cf57fdfadcf21bb389cd013a907b0844f730a9d49
 size 4040701744