Run 4. Outer Step 53. Inner Step 8.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5630595,
-    5630623
+    5630652,
+    5630681
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 6,
+  "inner_step": 8,
   "inner_steps": 0,
   "last_allreduce_block": 5568918,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8843647efacb323da6ab7613bbed6c0d4179aa429c6703ab4b5f955bd3830a0e
+oid sha256:bbf268fa1ed2c8861574aa3a9a8ba2effb5a1e213981914f2bb2ef28cd10b1f5
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8c9a2582163d9239f293beee705a9424266b49da124a441803df733c7de8b66
+oid sha256:a600353d56cf3fd4f8b403d2741832b723bda5b1e72a05bcb8723e4c93c3f9e6
 size 4040701744