Run 4. Outer Step 57. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5585541,
-    5585545,
-    5585549,
-    5585553,
-    5585557
+    5585562,
+    5585566,
+    5585570,
+    5585573,
+    5585577
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5584811,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c4d9d89512e2bff782eb421878449c67c41a78c5d6338806fa5725e7a59e41
+oid sha256:114e87d5af6da503fd247234b3c26a5bcff0e0b24e4e5ebbb1626a420e087ed0
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e67bf33ce7d91495d2a06c9fa6fa0ac30db9bf32d9a09e4d620e30f0ab9cee14
+oid sha256:16c4184c1740595965c85850f58755cf1da014871cc3d2448a524063eceab827
 size 4040701744