Run 4. Outer Step 61. Inner Step 10.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5641336,
-    5641368
+    5641403,
+    5641436
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 8,
+  "inner_step": 10,
   "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:c4f2a74aa8cb917cc13933700f38b1c29c41c1588241b1a4178b31c9427d9e32
+oid sha256:5ade515aaeea31994c29086e41344edf3f226a0e55b81288f420195fa34c850b
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e111aa34bba45ef1ac92b734522f61585a664ed6c4099973b394918b6099dc01
+oid sha256:70b6d6bcfe497aa9587980c57fb2a872bf6915884099f91796ccea0eb8742544
 size 4040701744