Run 4. Outer Step 22. Inner Step 2.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526623,
-    5526630,
-    5526637,
-    5526644,
-    5526651
+    5526658,
+    5526665,
+    5526672,
+    5526679,
+    5526686
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1,
+  "inner_step": 2,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f1a418ee3e5ccd7078ab456e9ea7eb5401183dab49f8780ecc06563beae2461
+oid sha256:dfcb289e4cce8528afe25f3fbc5773d36cc1e37b2818e3d6dfca9672de436af4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86d1519ea7460a5aa6c38323268eebfca302fdc59c2c7cf893bd54e6da9deb05
+oid sha256:aa0ed2aafbb087533262fb279f5fc7336f858ab9f1f01eb402c7df76d484a8bd
 size 4040701744