Run 4. Outer Step 28. Inner Step 24.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5537798,
-    5537800,
-    5537802,
-    5537804,
-    5537806,
-    5537809,
-    5537812,
-    5537814,
-    5537817
+    5537819,
+    5537822,
+    5537824,
+    5537826,
+    5537830
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6bb0a4e45ea31accf40ffb0990cf95cfce6cffac1f4ae35f4e649132ab1268d
+oid sha256:8dd6608be4ec22b0c8c06fd156459cd0e55c6cb52b012b79f115e0698e27c6f1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ace82191f84615ed3e8bd6587bc1951cafd4b47bef2a2b1f80fee76cc1b35817
+oid sha256:4c9db5243887e08f10141bac79ca37aaf607681fde92826267b3a13397d06f2d
 size 4040701744