Run 4. Outer Step 23. Inner Step 21.

config.json

@@ -268,23 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5531576,
-    5531578,
-    5531581,
-    5531583,
-    5531586,
-    5531589,
-    5531592,
-    5531593,
-    5531594,
-    5531596
+    5531599,
+    5531603,
+    5531606,
+    5531609,
+    5531612,
+    5531614,
+    5531617,
+    5531619,
+    5531621
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 20,
+  "inner_step": 21,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e69ce84de82158899126c2b738fd004944c3134ac22fbf6101d1dc75411a3fdc
+oid sha256:ca1f329826cb220e4f004b26d55a75f886eab944417607efd868495aa0464d84
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b01fb8d46746be8bd84efa2f18fa132e2fe97ec4c19fda062e68f077af451ee
+oid sha256:bf6c4b78cd8539fbf8c93231ad442023b336e57f1e2dbd47b1a9dc4e5ec5724c
 size 4040701744