Run 3. Outer Step 9. Inner Step 13.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5399399,
-    5399403,
-    5399408,
-    5399412,
-    5399415
+    5399446,
+    5399451,
+    5399455,
+    5399459,
+    5399463
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "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 sha256:37040a938b7d2b4140deff6abeac457888af7998e0628d0434d9f0e383580cdc
+oid sha256:d5a36ff39ec4c78649b576a36576ce43d1dc7eff20efe1e8f6c7a4aff3c5e723
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07cf9bf45a8a869ad54e9999a323317c39211f563e6fdb6de53b51bee9341ed6
+oid sha256:1fefa10dbfad2b8c4f69aa6b8d0af189b737117ed41e393eab5b0d321d6200be
 size 4040701744