Run 4. Outer Step 40. Inner Step 19.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5555865,
-    5555869,
-    5555873,
-    5555878,
-    5555882
+    5555887,
+    5555891,
+    5555895,
+    5555900,
+    5555904
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 18,
+  "inner_step": 19,
   "inner_steps": 0,
   "last_allreduce_block": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac022a4c182de43d616ba84d390f5cd6cf682c9dc13732f514af1f90926e473a
+oid sha256:3eb297d891242c072260b6bcd815c497b6b902f39e3c68b2ff294231fea3d331
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eb8a72ec48f96a424a110fb177841de552c8393c19ba659ffa56116f45ef424
+oid sha256:59460ee4c0712cfe86875d3d4cf5256630a85f438e51b897d720ef118d4b0622
 size 4040701744