Run 4. Outer Step 62. Inner Step 18.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5643472,
-    5643502
+    5643531,
+    5643560
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 18,
   "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:c935cd1139f39fccda77260e646aeba5a94c8a7c4786eec218d17a25d2ac4f4b
+oid sha256:e5bca6fb80f9dbd0142caf6270c7a79013f9af0055ba7640de3d39d6640c9b88
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4114c3a1591a132b088dd11474a86a76448fe843b5c3eaa7d06569be92bd85e
+oid sha256:dcff3c859cb8fe9c374597765e379e4ad5fd5d26d72b134d3b65b2d594ffaed2
 size 4040701744