Run 4. Outer Step 22. Inner Step 0.

config.json

@@ -268,18 +268,17 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526520,
-    5526527,
-    5526533,
-    5526538,
-    5526545
+    5526552,
+    5526558,
+    5526564,
+    5526570
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 29,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb3e62f21333eb1e3d5325f4f840cec53d75e1ce1fe467fb286a780986452308
+oid sha256:c412d65eba16719a66111cf96dd0bf1478d32ad7a40ae215f4017780d5d3f9d4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:435bbedf16984eafa21410dc4c1188f199dee2ffee1fd963a524be872502745d
+oid sha256:1964fdb7b09b6ac06f7b069a8a010e6834d8b8a75d5c795ef7b89855e3c2e0f4
 size 4040701744