Run 4. Outer Step 10. Inner Step 75.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5505807,
-    5505812,
-    5505815,
-    5505819,
-    5505823
+    5505827,
+    5505831,
+    5505835,
+    5505838,
+    5505842,
+    5505845
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 74,
+  "inner_step": 75,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42206cdd085f028be7857fc5801538dde4cd597f282ba7e837972713daf017f7
+oid sha256:07d07c754d1a433181620190f5514422a2a280c16fe69e92404adeb833d81866
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96d6e3bed7e6cb81f351d947c821645cf4d03197ddc2cebd62aa67be84c9a847
+oid sha256:217e17539b1a3bc91171c72b175def43c162af63527c041d4d8a7e9ee27bfbff
 size 4040701744