Run 4. Outer Step 30. Inner Step 16.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5540994,
-    5540998,
-    5541002,
-    5541007,
-    5541011
+    5541016,
+    5541020,
+    5541024,
+    5541028,
+    5541032
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "inner_steps": 0,
   "last_allreduce_block": 5539810,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:005650a0ce7f180db561af17399da7ae62ea04e12ef1bd7e1b3b619002128cd4
+oid sha256:274a79b3f90f95ced73b7f41d1cd39fef6c07d98b9aaa2a87b5d536f42584d11
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cca487a0bbc5efcee928f6a917e2bdb351f19692b029a29b2b9928f96949940b
+oid sha256:d37887d373a2681d47d415ffa770912827355274f4f5bc5e6ecc82074155c26f
 size 4040701744