Run 4. Outer Step 22. Inner Step 0.

config.json

@@ -268,18 +268,17 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526517,
-    5526524,
-    5526530,
-    5526538,
-    5526544
+    5526553,
+    5526560,
+    5526566,
+    5526573
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 26,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caea0fd26485a2c76697c90f4a83a0c36c7cd2e6d1921ecef4e9d259df9d997b
+oid sha256:38e96a482b3c887bccaf25b02a929fa0312e275b39f0721d726d0b4404d17762
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a0c45ac6e59ce4551246f26219ecff3d2d6d882ccc8701fd90ea3ae6377e147
+oid sha256:ecf7fd3f99854263de91da3a43bf8bf8a86b496b30f47f5138977d1400f873f2
 size 4040701744