Run 4. Outer Step 66. Inner Step 5.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5651124,
-    5651158
+    5651193,
+    5651333
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 3,
+  "inner_step": 5,
   "inner_steps": 0,
   "last_allreduce_block": 5643114,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba9f9c64d9c6e886216d6c22661c26d94c50847d603d936215b7ae18adf844e7
+oid sha256:12cf844beac65d68b074289bb7b69c927f0143cb598ef95bb4947ef065f4ae75
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73103ccc5380b18e35f88c95bc9bcc4a80c3ce9e5684766ae5cd2690c34fc650
+oid sha256:35b01c6548523f6a19dffcb9bda49d939c88868006f1f126eb1fd60a9fd32278
 size 4040701744