Run 3. Outer Step 5. Inner Step 266.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5384502,
-    5384506,
-    5384510,
-    5384514,
-    5384517
+    5384543,
+    5384547,
+    5384551,
+    5384554,
+    5384558
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 264,
+  "inner_step": 266,
   "inner_steps": 0,
   "last_allreduce_block": 5378990,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a28cb63423fb6690a70992eaa80fa76799dea157dab4d2b8439c9c7de9678cc6
+oid sha256:d95fb6d8b874c35f58abd3f1e5f79952f4ddf5cf5a08c79b85f5173896723d45
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef125c5b408a189488d88a396d83c6927408020197a017aa013d291a9f13c4fa
+oid sha256:71cce7a655ba581ab8d0b9386804b573e92241169298a66f5e40bf567fd81f3b
 size 4040701744