Run 4. Outer Step 28. Inner Step 33.

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538036,
-    5538038,
-    5538040,
-    5538042,
-    5538044,
-    5538047,
-    5538049,
-    5538051,
-    5538053,
-    5538055
+    5538058,
+    5538061,
+    5538064,
+    5538066,
+    5538068,
+    5538070,
+    5538072,
+    5538074,
+    5538076,
+    5538078
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c430a9fd813897d663c7f138d8c9315a7a23c7deeb585d754a0a62415dadd098
+oid sha256:e21c52d2fcbd515c8fed0ab87770ed6ad3c909cecd3bcd4d2f5bddbb62149114
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b27c4e5de61bc2de665068407d989ad34c02e1a1261f8d74ebc69a6f6709dfe0
+oid sha256:18eb5ac38029ff895c2ec561eb020710d6b9f6507677a7c5612e3b28ae9d156d
 size 4040701744