Run 4. Outer Step 26. Inner Step 38.

config.json

@@ -268,18 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5535808,
-    5535810,
-    5535813,
-    5535815,
-    5535817
+    5535820,
+    5535822,
+    5535823,
+    5535826,
+    5535828,
+    5535831,
+    5535834,
+    5535837,
+    5535839
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 37,
+  "inner_step": 38,
   "inner_steps": 0,
   "last_allreduce_block": 5534554,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c806aa284a70a247f2b414debb4d390725a8304e6405ccc19e870017de595261
+oid sha256:4079247d7d427f36c363f25e3aa9483bd4586630e74d27685444de31cdcf39ca
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40f48bda6c75654c934c4ed767e7530ac258a63d34e27c6734700a5b900dc023
+oid sha256:dcd1e9673b2273dfb61895edd521e8b84e7f78eb834dc46f96bbff160dfcdce5
 size 4040701744