Run 4. Outer Step 50. Inner Step 24.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5572260,
-    5572264,
-    5572269,
-    5572273,
-    5572277
+    5572282,
+    5572286,
+    5572290,
+    5572295,
+    5572299
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "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:db7157c9d31e44952d0b55baacd3fca738c7c20d1764faca7aa59078e626a558
+oid sha256:a102b6c5fca7bc848241fd0e46850316ec2802665b18cd4ca2f34e4166e1b186
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83b7ab1f11afa8bd2db7f28577860047655087f37c25070e8a3ac7f50fd51442
+oid sha256:a3c8e696e7f7682b3fc10b810b899f840bfc7ad77a0962a38b263e814fc3d54c
 size 4040701744