Run 3. Outer Step 10. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5422532,
-    5422536,
-    5422539,
-    5422542,
-    5422545
+    5422576,
+    5422579,
+    5422582,
+    5422585,
+    5422589
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04f7715c58ae48db41e740bbec43bd4bfd3ee51066a89d1151afce96aae093b1
+oid sha256:f2f8d3e6ddaf7e9fecbf60cb9fad587596504fa28d0db33086ab57f8b7108ac8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e85e0a98f401c5ff9d7e4b63353cd039c12cc9f8dcbc55eb52c53f19f83f9a16
+oid sha256:af7a4608143c30ea8fe25c7f75b63a95523d236d0f6fa33466dc5e6f230db864
 size 4040701744