Run 4. Outer Step 58. Inner Step 37.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604792,
-    5604797,
-    5604801,
-    5604806,
-    5604810
+    5604814,
+    5604819,
+    5604823,
+    5604828,
+    5604833
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 36,
+  "inner_step": 37,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:244fd3f942ddf5392fb516d9ab38f0f891987f28d78d270dd6b002e6bf227692
+oid sha256:0236dbb9488d551ea351471ca3d081b602247f8e2911bc76ec4afe5eb2f48e8b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d83a455f21d08aebe12c224c5da00bf24b5991fbd519f643855112b11fceb3
+oid sha256:bab024d91525c4e6890d6c463bf2ea205f2f29c0ff82df8f1d43ed848e573b48
 size 4040701744