Run 4. Outer Step 11. Inner Step 29.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5507773,
-    5507777,
-    5507781,
-    5507785,
-    5507788
+    5507793,
+    5507796,
+    5507800,
+    5507803,
+    5507807,
+    5507810
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 28,
+  "inner_step": 29,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24cde47d30c3d31270669e6647185bcc97a7a153c933cbc469ca3eb718170e5a
+oid sha256:87a9fb7d72526aa4039a2cfc6ad2ea3fb5aeab91cbd846d269fb431393e78f47
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:821bc1f52053b9891c610030465159c2a524dd06d9800c612ff8d21adfb4ba9c
+oid sha256:11e3b67a83a0b6c0a664779450cf9d7ec6f39ddbed3a2ca5b5a9e04f9e67f1e8
 size 4040701744