Run 4. Outer Step 54. Inner Step 20.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5632076,
-    5632105
+    5632137,
+    5632166
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 18,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5568918,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65a8e79839695678e70fb1c3ca684a4fa7d20b021e7c573fb6aaa82f621a5160
+oid sha256:a0f59bea4c8ee6884659c145c0e5cbdcc89327ffd21a0359162d757cfdea84fe
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:244486cfc373ab407464bc1be410ea5890f77b5243857f629d36a519b85b18f3
+oid sha256:17481c597ace26a8a0be89b517d504592d84bb56146c8112fefe907a3182d2ab
 size 4040701744