Run 4. Outer Step 12. Inner Step 31.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5509189,
-    5509193,
-    5509196,
-    5509200,
-    5509204,
-    5509208,
-    5509212
+    5509215,
+    5509219,
+    5509223,
+    5509226,
+    5509230,
+    5509234,
+    5509238
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 30,
+  "inner_step": 31,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2932d70da1252995fe34e2128ed668f01e989683a04805eb7caefa5f7c951aeb
+oid sha256:be3dbc9936aa6fb6294569647ff55e402a40bd3752518bd4cce8c24869927c7b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c171da3cbf407fedded559259aa563b7d57f903bf6325b3bccf3433d686648d
+oid sha256:a998255a597ca19df01fbfe475a42756e6800235e030b31449878575e85994a3
 size 4040701744