Run 4. Outer Step 58. Inner Step 36.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604769,
-    5604774,
-    5604778,
-    5604782,
-    5604787
+    5604792,
+    5604797,
+    5604801,
+    5604806,
+    5604810
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbb4e9dabe5018b7e6473714ed4b4e4b3d9ab04887e3ad1f5ee96fcc988899e0
+oid sha256:244fd3f942ddf5392fb516d9ab38f0f891987f28d78d270dd6b002e6bf227692
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb71617f4f3cc10b0f6a273b338975cb2d41a142defc98460745485353551cfb
+oid sha256:48d83a455f21d08aebe12c224c5da00bf24b5991fbd519f643855112b11fceb3
 size 4040701744