Run 4. Outer Step 21. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526483,
-    5526489,
-    5526496,
-    5526504,
-    5526510
+    5526517,
+    5526524,
+    5526530,
+    5526538,
+    5526544
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fadfa9a8c6773c75176681038cf2ee74a3b62399113de114c147f16a6d7aa42
+oid sha256:caea0fd26485a2c76697c90f4a83a0c36c7cd2e6d1921ecef4e9d259df9d997b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ababe390c3ab7d9aca52f4ba0f0cefae6bc5acc0485029ebfdc17d292fdf467
+oid sha256:1a0c45ac6e59ce4551246f26219ecff3d2d6d882ccc8701fd90ea3ae6377e147
 size 4040701744