Run 4. Outer Step 66. Inner Step 98.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5621914,
-    5621918,
-    5621923,
-    5621927,
-    5621930
+    5621936,
+    5621940,
+    5621944,
+    5621948,
+    5621952
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 97,
+  "inner_step": 98,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:455a408bdfdd1bd430f943b2e13516ed5c6782a8baebfca1c7589593a6efe9d9
+oid sha256:72bd181002529ec1765d27845e0340fdb45d3f89ca69658ea07fcf1f4a551ecf
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8ff43436ed4e334b71ac93f604ec52286dbc73fffbf093737c9a6d591f5076d
+oid sha256:bb399218a75843b094c6a6b62698fa47ea6d4825e71504d21e0d1326ce821431
 size 4040701744