Run 4. Outer Step 50. Inner Step 22.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5572138,
-    5572142,
-    5572146,
-    5572150,
-    5572154,
-    5572157,
-    5572161
+    5572167,
+    5572170,
+    5572174,
+    5572179,
+    5572182,
+    5572186,
+    5572190
   ],
   "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": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a8d10eb7de796bb2f2367a5beff8137f0615213bd2c5a5cb1c00969b1c54b84
+oid sha256:c90f56e5219dbdb99c5d7a05f56d72fa7c71460c9edf8e008b6af0a27247211f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eac2fbf33c322a3b3aac47689b9761a83068a90c57b6115e0772457e8706a52
+oid sha256:cf92023f5b486960cf7ea082f73496267c8f9b1b2be62dff93e772bf57115269
 size 4040701744