Run 4. Outer Step 7. Inner Step 159.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5499071,
-    5499074,
-    5499076,
-    5499078,
-    5499081,
-    5499083,
-    5499085
+    5499088,
+    5499090,
+    5499091,
+    5499093,
+    5499095
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 158,
+  "inner_step": 159,
   "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:e4c3b3feea10d7bf7dd2ff4dbdccc1bbe84ad6d4124feeb402531494d48c7027
+oid sha256:4055835c10d257eeae6c9ac848cf5de38f21cf8d15c105950da3e9f71a48bf80
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cb028e2c910fa394e9f7e0245b15e7bd1bcf369a27d867b0af3b19ec81a5202
+oid sha256:5d727a645eeac9e5c0ad6b46fb6d66e2843939fb64d4ec4357e7a60f339b02e4
 size 4040701744