Run 4. Outer Step 29. Inner Step 13.

config.json

@@ -268,18 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538938,
-    5538940,
-    5538942,
-    5538944,
-    5538946
+    5538948,
+    5538950,
+    5538952,
+    5538954,
+    5538956,
+    5538958,
+    5538960,
+    5538962,
+    5538964,
+    5538966,
+    5538968
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:108a023414c86264a21572520abf0c03d3eab732141d80c2f51e525d77f627f9
+oid sha256:580f40ed2c767e12563a7a860b85d61657dce731d08ce9e41f5107877b53bee1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1f4a39ef5a1022433f7ba18aa433bdc30d30cc49cf4cace0275a8e0b6951f06
+oid sha256:d46cb5c09468b0114c708a3ebedf13a7d16a60e9d7956bc7f3d9b05e5776d8cb
 size 4040701744