Run 4. Outer Step 23. Inner Step 4.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5529526,
-    5529532,
-    5529537,
-    5529543,
-    5529548
+    5529556,
+    5529561,
+    5529566,
+    5529572,
+    5529577
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 3,
+  "inner_step": 4,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dd4e9277b64a4610ca64e8ef62662030dec31870b97c7a809c818ddfbef48dd
+oid sha256:cb9da4ad5520890b35a2aafd547b6b2a742ddf0f74606819f4454d36437cca9d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5b25050b78f14df9ea6d6be5fe41140d643870cfc201d57120a2608f7fcb3f9
+oid sha256:dab60cab8a8b22751218b4c15f2157fc37fd43e49e4317d76c145fe808d534f0
 size 4040701744