Run 4. Outer Step 27. Inner Step 36.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5537029,
-    5537031,
-    5537033,
-    5537035,
-    5537039
+    5537041,
+    5537044,
+    5537045,
+    5537047,
+    5537049,
+    5537051,
+    5537053,
+    5537055,
+    5537057,
+    5537059
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5535854,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:158a934c987c93eb1e5f8ee5e3acfb76a6a4cb9144e4d48a21152ed109a62139
+oid sha256:26f3caccbaeb69bf28496d57debfd0ec62e7f25684865ffe28ae8ac6ac088c87
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ca671bd135867630baf8919fa1c65bd31957470dfd81ae523fa4cb6aaa6854e
+oid sha256:6e38737e1dce3bed2e4f25b57a9791f4bb28160da8c5ce2b2d2d02ec5a52426f
 size 4040701744