Run 4. Outer Step 22. Inner Step 18.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5527280,
-    5527286,
-    5527292,
-    5527298,
-    5527304
+    5527311,
+    5527318,
+    5527323,
+    5527329,
+    5527336
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c773bfa20eaf3932a5254f32248b0136389c5f06e6e26cb9d9ab49bf6bfb8bde
+oid sha256:31ceb03390c14b4b702b34936f5cf84df41f810c829ca18405b6202933722379
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d92c3bf72f8d4f719c3031ce3bde1b1f53776151764d5adcc8b150d3985143d
+oid sha256:15dc92de7057cc5385d404ca1861abe34db33b27028bc3e41a2947f791552cc8
 size 4040701744