Run 4. Outer Step 63. Inner Step 14.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5644594,
-    5644622
+    5644652,
+    5644680
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 14,
   "inner_steps": 0,
   "last_allreduce_block": 5641040,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:064e66269c8702cc7d6fcfb569701d3823921792682aa7179a088fc9d5d62b88
+oid sha256:0d5d9026a961c26c0f04f0c46b98f3d09b1a0441c33167b7284d65ac077e1c11
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d3d2748e7f2f77fcc2f570da3701eda58c5d6b9bce60557f0f19cc5cc1792d4
+oid sha256:d8fc189460107e378e76cbb1bcf4eb549d69c963628ba1b8dcbfad2103e8fa4f
 size 4040701744