Run 4. Outer Step 15. Inner Step 68.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5514955,
-    5514959,
-    5514963,
-    5514966,
-    5514970
+    5514974,
+    5514978,
+    5514982,
+    5514986,
+    5514989,
+    5514993
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 67,
+  "inner_step": 68,
   "inner_steps": 0,
   "last_allreduce_block": 5511564,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22d085da22130dc7770eab49012472e711673c3b33387c969eb9519cac28b7b6
+oid sha256:1765d3485343a2ba8173364667e7e2959e057d7cd6070c3e7fb012bc8e8215c0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9bc265ad7fd715c3ad9f72ea307cd58c195d4db7366d3491c112845893ab4f9
+oid sha256:ea67038305c9db138838bb156049b76c9a95626f0917a305a142f1899dd6abf5
 size 4040701744