Run 4. Outer Step 66. Inner Step 23.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5651605,
-    5651635
+    5651665,
+    5651695
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5641040,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae7e01fb7f4bf349885a6e921d014187a89accd35c2a7010b478df071e4938ee
+oid sha256:cf83e5e6fc42c19a2e7598eed92c5e5185613adfc7fd6a610a3ceea603dbdd64
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a031db26f0b4f9a9c0a88e2b00acdecfcdcf2f0ea12300e23c5d60cd293c8ada
+oid sha256:49b15c111d5cbbd237dd83e346afecf6629c59cb097457363c7ecb448e1fb6ec
 size 4040701744