Run 4. Outer Step 66. Inner Step 97.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5621872,
-    5621877,
-    5621881,
-    5621885,
-    5621889
+    5621894,
+    5621898,
+    5621902,
+    5621905,
+    5621909
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 96,
+  "inner_step": 97,
   "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:a43126fffca94d4d4f72a0287e6cae661eae9ed1d1cc6ed6fa7aa502c86f8bae
+oid sha256:455a408bdfdd1bd430f943b2e13516ed5c6782a8baebfca1c7589593a6efe9d9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7d774b20907cd5037ad43bd0200b30e7ad242d5e12d15ec994ead57f80feedc
+oid sha256:e8ff43436ed4e334b71ac93f604ec52286dbc73fffbf093737c9a6d591f5076d
 size 4040701744