Run 4. Outer Step 61. Inner Step 69.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5642942,
-    5642946,
-    5642950,
-    5642954,
-    5642958
+    5642963,
+    5642968,
+    5642972,
+    5642977,
+    5642981
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 68,
+  "inner_step": 69,
   "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:e7bdefe8273d00651dab7a6c87bf5bcef6e7a68d8c84a6b9c966b5566535b301
+oid sha256:a3b4c28e4dbd1507a522c1d397342d55cf03ab06c668776ba3f272a75131ac7a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17109de3284faa9e522b47bce394e32a46507489bd1e7800b5b243352d135e32
+oid sha256:f96e3bc75f9159cc7e44b590f91304fea7cc82f02754d0db51f064d8df48a244
 size 4040701744