Run 4. Outer Step 65. Inner Step 12.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5648438,
-    5648511
+    5648545,
+    5648757
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 10,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5643114,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34b82f919ab125f9e5b5af042c8650ea66b90aa8c0782e56ea5711b05533cc48
+oid sha256:a18eacf844eae3f8b1ac9237e3d8949efe2ad8c58d1cb716a6f3ee44e516ff5f
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c93a6ee96192542dacc88b5c3f5940d17e62a0969571b0fa2c282f80989d4d4
+oid sha256:528fd832f5c382069107363b7e7e3bad3f45b2110c7046e2c73860063676892d
 size 4040701744