Run 4. Outer Step 11. Inner Step 37.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5507965,
-    5507969,
-    5507973,
-    5507976,
-    5507980,
-    5507984
+    5507988,
+    5507992,
+    5507995,
+    5507999,
+    5508002,
+    5508006
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 36,
+  "inner_step": 37,
   "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 sha256:5102c1863f7ab89f4d4f925978dd3d1052dd427889da3f6af216ba0abb5af096
+oid sha256:300309ae55be49aa401c584756fb59ae630eec0607d052e794dd3ca8724abe27
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84f11d7f4bb9f1f9dfdef62b37851ce4c36e6933f80d611bd526a89a66293384
+oid sha256:801dfee8a062d071e023202449634f10f14d01d12abcd1e340f29946bce23034
 size 4040701744