Run 4. Outer Step 50. Inner Step 172.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5625685,
-    5625716
+    5625747,
+    5625778
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 170,
+  "inner_step": 172,
   "inner_steps": 0,
   "last_allreduce_block": 5556551,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4bc09c312ffc4f326e3ab77b55e3ad5c2d68ca507c4dc66f9f63ca1c1263893
+oid sha256:17b3bcfbb73536c2a904800e7a67808b38f48eeaab5a267175e555a94da6740e
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5fcea8cc7b7c2273308223dbe7b5ae5d1a4885ff8169ee13fb0e9013b547bd0
+oid sha256:a71739391231fe7bb778a4de6e30364c7d85625934bd5fa4092b82e6045ffbdb
 size 4040701744