Run 4. Outer Step 7. Inner Step 158.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5499132,
-    5499134,
-    5499137,
-    5499139,
-    5499142,
-    5499144,
-    5499146
+    5499149,
+    5499151,
+    5499154,
+    5499156,
+    5499159
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 157,
+  "inner_step": 158,
   "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 sha256:2fc01181cf46997eda31e315097d8e5119d949eefa3435dd8e85d9f993be7078
+oid sha256:7b044e77c523baa698ffe410008a2f89876f735391e12bf730df41bb63deb596
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0550802e919baf09c5226a2491c467132225dc520f61dd7dba7622574ee0fdf3
+oid sha256:7bc45931083f884eb9c91e26252813818df8a9621b8c8e399c03353fe7f782a2
 size 4040701744