Run 4. Outer Step 25. Inner Step 42.

config.json

@@ -268,18 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5534622,
-    5534623,
-    5534624,
-    5534627,
-    5534629
+    5534632,
+    5534634,
+    5534636,
+    5534638,
+    5534640,
+    5534642,
+    5534644,
+    5534646,
+    5534648,
+    5534650,
+    5534652
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5533305,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8cf15ffb2d3051f93dd1326d64f760428123dc78575ba20f441e8b0f3abca0a
+oid sha256:55febfa4f5345f9da2ad8168745a1922d61168577453fbb5e4d331fcc921d743
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bab7a74b9c958a7af10a8dc6d44b8464a3e77491c54af1fb26867829344ae3d
+oid sha256:0ceb83dfe2ea10026d3a121ea8254c7c93816eff03376c8ae4e4392268d93a21
 size 4040701744