Run 4. Outer Step 62. Inner Step 23.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611183,
-    5611187,
-    5611191,
-    5611195,
-    5611199
+    5611204,
+    5611208,
+    5611212,
+    5611217,
+    5611221
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5568918,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b4169a04a83ca213b6e0dffea216597731ce32e72bf13e1f3e8cafb7931bdba
+oid sha256:2bd2b39d7863de51e933fc90e3f4952e0b844655b19b934a6f251e2efcdd3593
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a549ba6e075894edd2fb06696f9ff40598e88eea9909397aa1e1c11da25df5f4
+oid sha256:abd5a4c83ab7e96fdc88272b5273ccac0bea39578063681c5e849449ade098a5
 size 4040701744