Run 4. Outer Step 60. Inner Step 22.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607875,
-    5607879,
-    5607884,
-    5607887,
-    5607891
+    5607895,
+    5607899,
+    5607903,
+    5607907,
+    5607911
   ],
   "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": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9039fb89cd28a8685dde08747129e24b90d6f301c861a0eda97e72deb6f4b864
+oid sha256:de6bba6592d7fcc785ca14001ff19d20da01f88ea6a7b4d95f3895a215946292
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37a6e5c448d7682ef21cfd35430eef0570839bcc5b27304a0f186431bb2b978d
+oid sha256:980aaa8361a17d1a8b40c6527d355fbf2e48715aa7e79268865a27094af5093c
 size 4040701744