Run 4. Outer Step 62. Inner Step 8.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5643314,
-    5643343
+    5643371,
+    5643398
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 6,
+  "inner_step": 8,
   "inner_steps": 0,
   "last_allreduce_block": 5643114,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6b8638a0c0c713d867f1333c1cea2c2d3cb6925ed0f925242f60e41050c077d
+oid sha256:31a871fa6c555f1aa45893b952bc5b8fcb7d95e15a91453bbce361315e97c93c
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22fb2877e7672949b9035b5d16a5d8b69b5912654a56f4172458813dc16ad932
+oid sha256:de25b1f0fe27a43f25732956503c98af65702f0e862bf43d217d2531ebf51357
 size 4040701744