Run 4. Outer Step 10. Inner Step 74.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5505784,
-    5505788,
-    5505791,
-    5505795,
-    5505799,
-    5505803
+    5505807,
+    5505812,
+    5505815,
+    5505819,
+    5505823
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 73,
+  "inner_step": 74,
   "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 sha256:479c7940c535419d5234770910df8296bc8a9b9e07256622cfc6c999ecee5521
+oid sha256:42206cdd085f028be7857fc5801538dde4cd597f282ba7e837972713daf017f7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11f8220473a74209a06763c397a89d32c9334a023201248c91e6745f4922f46f
+oid sha256:96d6e3bed7e6cb81f351d947c821645cf4d03197ddc2cebd62aa67be84c9a847
 size 4040701744