Run 4. Outer Step 57. Inner Step 8.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601212,
-    5601219,
-    5601227,
-    5601234,
-    5601242
+    5601250,
+    5601257,
+    5601264,
+    5601271,
+    5601279
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 8,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:522f8117c56a03c19f1f18b6d1953fc54c615f1ebaea6f724be9cdf84055cef6
+oid sha256:d02f72fb01e296049d0433db44911277d593a2e36190af69456b3db28b3cbff6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18bb2810849bcdd93ed7ae518fdf8e1a12cc0671c7481ef436363afd8b76a7f7
+oid sha256:893ece5295a139e0bb7f096e319a4c6d3ec1b3f32fc85912d2f86a151ec71b47
 size 4040701744