Run 2. Outer Step 11. Inner Step 28.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5363619,
-    5363624,
-    5363628,
-    5363633,
-    5363637
+    5363672,
+    5363676,
+    5363680,
+    5363685,
+    5363689
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 28,
   "inner_steps": 0,
   "last_allreduce_block": 5358692,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408656a10c3e100fac4b6b52c5e9870c80764ad9319bffefc931d3bf08069d4c
+oid sha256:2b7a10558ee87317b7c57fbed386d6ea54b6de4aa33b4d658795ac1680b158cf
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aff02d92359c4c8fb0fe6947d0e0f344eb6dd11c392ac0012009e930450620c
+oid sha256:fd40474ff653702bd228903cb07c3d53763c5c5e0b56d133ccfd3115a0bccd32
 size 4040701744