Run 4. Outer Step 12. Inner Step 22.

config.json

@@ -268,20 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5508955,
-    5508958,
-    5508962,
-    5508965,
-    5508969,
-    5508972,
-    5508976
+    5508980,
+    5508983,
+    5508987,
+    5508990,
+    5508994,
+    5508997,
+    5509001,
+    5509004
   ],
   "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": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d4444a6de9b721addf9f6a77a8f4bc53e5568362764f5a4cd1c77e7bf252e76
+oid sha256:533b6856e7f8eb766b6625c76841eab0699a613c8d33ff823f0555ad31e5377b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1b12af7f83c61c88317baaef83628e3adeee4863ec6ba9b4df84f54d810f46d
+oid sha256:1ae4022e0671969795303657357b6a5fad13588e92cac29e46500b6c80db6c94
 size 4040701744