Run 4. Outer Step 53. Inner Step 30.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5577210,
-    5577213,
-    5577215,
-    5577217,
-    5577218,
-    5577220,
-    5577223,
-    5577225
+    5577228,
+    5577230,
+    5577232,
+    5577235,
+    5577238
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 29,
+  "inner_step": 30,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e77bf829ed9a1800e87a635374f884f76839c21c6e281dc88cdd2b8a4d557b97
+oid sha256:831b40f6361f2f39377ffbb85b2a348a3da6219ecb5ca3bd02aff3ccd2ec1398
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e4b7f48972d03d1d5b1dad4a2361f08194c2712a13ad6828f4d62196b6266c
+oid sha256:d2abe0ed423f08f0cade723841233316e2825af77dd8ae0bcb9835a054e4523b
 size 4040701744