Run 4. Outer Step 61. Inner Step 66.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5642848,
-    5642891
+    5642919,
+    5642945
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 64,
+  "inner_step": 66,
   "inner_steps": 0,
   "last_allreduce_block": 5641040,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5f9095f511c5de36f5b911762a9d40c329754841d70c95a4d52f6fab6fe1b98
+oid sha256:261420aceaaf5a119acd7bef65a0b442e28f93d8828137a43dccd7e777faef5a
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f51cf5fc769436c8bea323e0c42d3de9ad1806224078948b8a9df082ea17f513
+oid sha256:3117a600b1513e005eaa413db2176faa091c80ce7d5eb250ad5c640e5dff96a4
 size 4040701744