Run 4. Outer Step 17. Inner Step 15.

config.json

@@ -268,20 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5519435,
-    5519439,
-    5519442,
-    5519446,
-    5519449,
-    5519453,
-    5519457
+    5519461,
+    5519464,
+    5519468,
+    5519472,
+    5519476,
+    5519479
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 14,
+  "inner_step": 15,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7c49db09ba344369516f901918dcae057eb16e7822736c4749a34033bef6edd
+oid sha256:391c31312a4fb2d982d47c1ce2f55d9673cdce35f8ceb76b3c78b176e96d1983
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:660e92f5cb72747c3a288370123f62161c89063e0d4064f5e211aa89c5c6e0ec
+oid sha256:b6e965c1e4fa5d98e7efb0b1bc02e0f4820dc3ab5c5f046f1685af45a03505f2
 size 4040701744