Run 4. Outer Step 27. Inner Step 11.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5536814,
-    5536819,
-    5536823,
-    5536828,
-    5536832
+    5536838,
+    5536842,
+    5536846,
+    5536851,
+    5536856
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 10,
+  "inner_step": 11,
   "inner_steps": 0,
   "last_allreduce_block": 5535854,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a999fa50836320b6df67c27b4b8de72e10bd39a801ac9166dd2ed0f749592b7
+oid sha256:840d123197629da516e267de2ea22ac9a5d010cac33b310f873e051638dfdc74
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24e9fd93a074bc7485e2203abf70eef4c5964d59805365aca08223823e8142c9
+oid sha256:5b42b9f5b2b7a5592a059bf0d11fd003b5fec37214aba9df016389ce5c508e0d
 size 4040701744