Run 4. Outer Step 23. Inner Step 23.

config.json

@@ -268,23 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5531580,
-    5531582,
-    5531584,
-    5531588,
-    5531590,
-    5531592,
-    5531594,
-    5531596,
-    5531597,
-    5531600
+    5531603,
+    5531605,
+    5531607,
+    5531610,
+    5531612,
+    5531614,
+    5531616,
+    5531618,
+    5531619,
+    5531622,
+    5531624
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5772e7178cf91f23c08e94be6af3ff976ce654742e5d98bdd414e0aad3e6505e
+oid sha256:3eac6c8b6482c08fd242459ca781b301ef13dd86e5fa226e361595ceed9f756a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1509f211a4e9dda246d5ee5bb707e7115a7f46d4c47982b49b0b38f058de4c5
+oid sha256:7e6f5190ef65fee17dc80f0cf64dee8fe5078461058c293d9c1814ef32fe2bcb
 size 4040701744