Run 3. Outer Step 9. Inner Step 69.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5409827,
-    5409829,
-    5409831,
-    5409833,
-    5409834
+    5409862,
+    5409864,
+    5409865,
+    5409868,
+    5409869
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 68,
+  "inner_step": 69,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eabc2b6edea95f21a07a3347277154c95779068e1e3c4c153ebb7ddc946b246
+oid sha256:90a1058e23d569f2421da208eaef10854b39ab3638df0efcd8161715fccf2849
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f719b59c0e7c91c703f2b2e31a68d5a4352de8ab972114f766fde10e0e28eedb
+oid sha256:9c3e5b5fac9aa077b8f4eb4fbb6d6f2f8c2a4e5a81f7e702c0dda0e61db1a3fc
 size 4040701744