Run 4. Outer Step 64. Inner Step 17.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5647112,
-    5647154
+    5647181,
+    5647208
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 17,
   "inner_steps": 0,
   "last_allreduce_block": 5646655,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf208a2ee957e719810d8996efb5cb47cebd06dde38d660ed1b6685663b5355
+oid sha256:6bb362946b8dcb9faf474216a66b1824c66cd97d6b5df6f2fa2cc74b5ab61941
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aebce01f081014cdab2a6dbf938ae685229b4a09187dce0f303b7c5d11701258
+oid sha256:393f38fa4d556fa307b6874c1d84a3df6e20d7e9d5b88f8c887eca78ce70d954
 size 4040701744