Run 4. Outer Step 60. Inner Step 4.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607320,
-    5607324,
-    5607329,
-    5607333,
-    5607337
+    5607341,
+    5607346,
+    5607350,
+    5607354,
+    5607359
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 3,
+  "inner_step": 4,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:825509a9c44f7c2eee3225e02eaefc9147a0d8b76243928d0807e7c198933e08
+oid sha256:86249103223c168bebc5ae5dc13ff4fa336d8f65a77308da9c8c009f79453fcf
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d408814afa41ba8a4a13584f577c99236b9116ca5dfbc36b9d3c329265fa24a5
+oid sha256:e1718c23a0ba0808789c1e394a384c87468a74045952af4df4cf49c0f0658e17
 size 4040701744