Run 4. Outer Step 75. Inner Step 23.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5663492,
-    5663511
+    5663532,
+    5663549
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5662361,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21d463003859d7f697d234830a2fd80ee2c22587a6d738f8bb78e88d9c450e43
+oid sha256:9d4a4ea7d5047a0d12485ddea77c38184bfbdd4968326904df5daec34710bf40
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12662249b4ea5eaeaf18cd1b89d4f550cd5d84dfe8621366514d9cacf5eb6838
+oid sha256:21b470eb4a828558c62779f4b127b0482b8ee7b8c527a796334597c3ca6d9df4
 size 4040701744