Run 4. Outer Step 21. Inner Step 29.

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526018,
-    5526020,
-    5526022,
-    5526024,
-    5526025,
-    5526027,
-    5526029,
-    5526031,
-    5526033,
-    5526035
+    5526037,
+    5526039,
+    5526042,
+    5526044,
+    5526045,
+    5526047,
+    5526050,
+    5526052,
+    5526054,
+    5526056
   ],
   "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": 5525369,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03f94c032a8c7fb5807bdf3ba46e7118c76c5f57225efd1db01118d4b7e48011
+oid sha256:e18106d9b4097e3120b18dfbb35b20eea8cf9283b5acd453b79c2360f00ea786
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ad2c0bd92806f1d33ecd33752eb45b2683fd48d64e896db59c59b42a9a8d99a
+oid sha256:afa4c05f1dd2e1337deaf357673f75388a944be082362d333d0c45773b4052a4
 size 4040701744