Run 4. Outer Step 33. Inner Step 22.

config.json

@@ -268,21 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544640,
-    5544641,
-    5544643,
-    5544645,
-    5544648,
-    5544651,
-    5544653,
-    5544655
+    5544657,
+    5544660,
+    5544663,
+    5544665,
+    5544668,
+    5544670,
+    5544671,
+    5544673
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 22,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1ee06094a7cebc9342d0d1907cb624bfd813cf9bbab12edd8249097047b2cde
+oid sha256:607d9f18c30759edd7a42c87dc5b4f9a4413743f37fbc746f51f8385af6918dc
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3d067fef6a58afe975b4e83e56a1895d7299e21d3293ae117d496411d52dfec
+oid sha256:5b60ebe802486c9c637eef232b6a4acf4d59d388e12188eb0c7cb364c29b5eed
 size 4040701744