Run 4. Outer Step 65. Inner Step 7.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5648080,
-    5648109
+    5648143,
+    5648173
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 7,
   "inner_steps": 0,
   "last_allreduce_block": 5639485,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a7684a72c006c07a6f55c7b4661ce9a661fa2631a40be40b36899ca2c3f4f86
+oid sha256:dde90cc5694dd4514ee57a4ab3f020175f19fd40b87ed7b3b259a87951d9ab1c
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:978248d0d3d2faac4562140b94eb2b6bf972f1fb534196d1ff07c0b979d3ccbf
+oid sha256:aeca1a4f74fa970548ec0fef74c9cc5abaebe0e7b16755ee98abcd89121ac24d
 size 4040701744