Run 4. Outer Step 60. Inner Step 33.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5608167,
-    5608171,
-    5608175,
-    5608177,
-    5608183
+    5608187,
+    5608191,
+    5608195,
+    5608199,
+    5608203,
+    5608207
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:884389317cc0386298c0bb4dcfb87f718116dbe8a67b8d448c65fa8e7e88694b
+oid sha256:1401d61555d963f4499ee755df19a424bc208e18f1beb6a1c455026fe1845b22
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:514d62eba73994a857adab5d5974310ececa031e35f9bac46f038e74c455b626
+oid sha256:690c6bdf1f963006863fd7c99a27f52b765c70ab25f97fc80f4d612bc6b22d7f
 size 4040701744