Run 4. Outer Step 40. Inner Step 35.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5556029,
-    5556033,
-    5556037,
-    5556041,
-    5556045,
-    5556049
+    5556054,
+    5556058,
+    5556062,
+    5556066,
+    5556071,
+    5556075
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5553805,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b49301367e288db77fcd095395ae9298275a2a77ab4c2a7a713229dc7cbca70
+oid sha256:5872c2675699bc3ebbe5492d6c58b1a9ada52c93c84ca56f57b78e6e7f148174
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01e25a09900d1cc725790fad356442722b63c96e03d37a3361c00bffa0941ea1
+oid sha256:1b80cd12b5a8c266c32e119f32761009514f63ded6e369acff4d982266876bcd
 size 4040701744