Run 4. Outer Step 22. Inner Step 1.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526588,
-    5526595,
-    5526602,
-    5526608,
-    5526615
+    5526623,
+    5526630,
+    5526637,
+    5526643,
+    5526650
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 1,
   "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 sha256:38e96a482b3c887bccaf25b02a929fa0312e275b39f0721d726d0b4404d17762
+oid sha256:18e9793e6fc3c953310f74e96bb232feae68b2d278c4de8200045686babbda57
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecf7fd3f99854263de91da3a43bf8bf8a86b496b30f47f5138977d1400f873f2
+oid sha256:5b75e81676e3545eae85f04b07ff5348e77a140e89d72cad8184f83c26ff5b6c
 size 4040701744