Run 4. Outer Step 60. Inner Step 17.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607757,
-    5607761,
-    5607766,
-    5607769,
-    5607773
+    5607778,
+    5607781,
+    5607785,
+    5607789,
+    5607793
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8866181b97138548f866380c08f2ef3ccc8059e6cfbfdb3cbd5e3f6c45a5ac6
+oid sha256:fdd6bd63c25f4b537dd8dbbc44563396d99409698b83f0e1b9c69a1a5c36bfe6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0172ab942091d5048694a81d8bc5b8e9d91491504e773c4d87678be9aba01756
+oid sha256:ead0e963d692daa74baa484e70f5874fb25125b8aaac52d6dd3ea9d87b41bb41
 size 4040701744