Run 4. Outer Step 36. Inner Step 31.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5550462,
-    5550467,
-    5550471,
-    5550475,
-    5550479
+    5550484,
+    5550488,
+    5550492,
+    5550496,
+    5550500
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 30,
+  "inner_step": 31,
   "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 sha256:632f9be4facbafc460472d0cc3f04820b742f5ab9f060d963905476f868cfdf5
+oid sha256:4e5f2768e1f39ba7b6fe2a9d8fcb7b158b76a7356aa2d8ed01baa3aac5baae26
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fee2054330c9654cd7eb10fe2661c6dfc1b48603eab1408e70c2caa7da96636
+oid sha256:f5d9c23163f6244f8c9ea37b1ab7bd9f323566fb2f084b6c1dac92807843a2b9
 size 4040701744