Run 4. Outer Step 85. Inner Step 10.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5675480,
-    5675495
+    5675514,
+    5675532
   ],
   "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": 5675035,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:026091f3618dc3bb868e8847f9d16ef0bb8ab848b8d6c438e3366fa5897d11d4
+oid sha256:5a36251f4f013ce6cd71bf02511149faf8f1ff829d66efccc1dd597790951425
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d7e4a86f65e8323115f82a0beb16146f1bfad8bc2e9940246939e693de93794
+oid sha256:188d6c680ea62233e0e7aed3d73e6b415afb71e68e666b0df24d4159db7eb1e2
 size 4040701744