Run 4. Outer Step 7. Inner Step 72.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5494784,
-    5494790,
-    5494795,
-    5494800,
-    5494805
+    5494811,
+    5494816,
+    5494821,
+    5494826,
+    5494831
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 71,
+  "inner_step": 72,
   "inner_steps": 0,
   "last_allreduce_block": 5473073,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c24f1cc3eaa170f1ae392a588751f65b743523056ed7569fe833029d215bb6c6
+oid sha256:dc1801d624aec3aaee4be5ec75ca5ec8a431eb4c7f88abc4266e2860264c8b52
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab576bc290c52af6d5f7730d5e8d8d8df891fb0ec4ccf12d9a4bf26860323739
+oid sha256:2100f3bd2444fb85ed7eb97c441ba89d8d22d1406a5913512aa051d5071a1961
 size 4040701744