Run 4. Outer Step 83. Inner Step 10.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5673127,
-    5673145
+    5673165,
+    5673185
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 9,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5672513,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dcb2366d0120d9aab8a359d85a92a428217cdb5e0e12f88c11864ebbda3fcd4
+oid sha256:e9e6f367d7d1ca363ea008271c8d742e7049b82f90ee151f177f6dd62407ddcd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e246eb8e07bf6a6201af05c5c34d5c2f5e4b4cc699212494ee874fe38567527
+oid sha256:9f211261fe9baf80f88ea7071193bff03d0675312066b0546bb1c12e8eb3e8df
 size 4040701744