Run 4. Outer Step 28. Inner Step 27.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5537785,
-    5537789,
-    5537793,
-    5537797,
-    5537801,
-    5537806
+    5537811,
+    5537815,
+    5537819,
+    5537823,
+    5537827,
+    5537831
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 26,
+  "inner_step": 27,
   "inner_steps": 0,
   "last_allreduce_block": 5531651,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aae6056dbcc1173fa2f069866121ecb8b8bb382d3f960d216ef1d30cf80a4241
+oid sha256:0f8ed1f82e352fa0803d53d8068fe623e3bfbe8858da3779eba59c794ba529b1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aca1ce1a51f046b5033356e3ddc40be616aa2eb3bb2c5b39ac4fee806a13de0e
+oid sha256:c06c2329a3e5a44360f1c849bd0b69c59801eea51f64aca50ef6df6c72436144
 size 4040701744