Run 4. Outer Step 25. Inner Step 14.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5533619,
-    5533623,
-    5533627,
-    5533631,
-    5533635
+    5533640,
+    5533643,
+    5533647,
+    5533651,
+    5533655,
+    5533659
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 13,
+  "inner_step": 14,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6878dc76a082c5182edcd49b0a2453e62b7692102e597799dbdd1718a280d015
+oid sha256:4a115fc7d67b76e66f37d5777996d8d8a78fa7f201fc317f62e7aba568d36f72
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df9a2f43b8dbd73519991be2ee7e6a55ccddf801717ea8aa83b640c036fd687f
+oid sha256:10ec2b4528be08e75f2745ba44b8cb50f32f51754d35d60a629f29ab79808fb1
 size 4040701744