Run 4. Outer Step 58. Inner Step 6.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5587329,
-    5587332,
-    5587334,
-    5587337,
-    5587340,
-    5587343
+    5587346,
+    5587349,
+    5587352,
+    5587355,
+    5587358,
+    5587361
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f899a05018c8f2bfa939058e0242ab24cd01beab27c0cf8eb1765121467fe04
+oid sha256:a2109672bda52602c9bdae57ed08376275505b3e3f9f9cef7cefd7c435be7818
 size 8081782439

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83ef00a759d5ba71aac5b5a3a9eac3342798f691bbb325732e7b85195817bd24
+oid sha256:7ffa54d19b25086851a92c8d165eb420a992c53e049bc2222e407850a71d7349
 size 4040701744