Run 4. Outer Step 36. Inner Step 15.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5549950,
-    5549956,
-    5549959,
-    5549963,
-    5549968
+    5549973,
+    5549979,
+    5549982,
+    5549986,
+    5549991
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 14,
+  "inner_step": 15,
   "inner_steps": 0,
   "last_allreduce_block": 5549491,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:430749bd7acde6dca4a3fb25f536fe828fec44d4ca4254f51fd000717dc847d1
+oid sha256:51059eff1ac05813a5c26e3cc4c81487804463ef45336492f12c571eb46dd032
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24379e4c7acab6eb3fb3cbd214af45a0233d409091f7f5cfefa8128ef406c26d
+oid sha256:82a015a55322a8330e390719b4c31dfd66c37fd7b94fb62374d725ed6abf5441
 size 4040701744