Run 4. Outer Step 10. Inner Step 96.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5506328,
-    5506332,
-    5506336,
-    5506339,
-    5506342,
-    5506346
+    5506350,
+    5506354,
+    5506358,
+    5506362,
+    5506367,
+    5506370
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 95,
+  "inner_step": 96,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41d7a86ba74431dfce44b6f8c28019092f640781adc27f2a9c3c44fd06f403fc
+oid sha256:ee0360d5b65b292ed256031a0d20920a8379bfcad9c5b9d1c54d76ce36ce1f91
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:987db25dc6a81af43da5155e2ca6f0f4c97dc015c2c193e4bdce60922fc56e24
+oid sha256:ce1cd325fc98d2f75869334760f07f2ac243056c41d8839b2c357bf6af1bf784
 size 4040701744