Run 4. Outer Step 33. Inner Step 21.

config.json

@@ -268,18 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544702,
-    5544705,
-    5544706,
-    5544712,
-    5544715
+    5544719,
+    5544721,
+    5544723,
+    5544726,
+    5544728,
+    5544731,
+    5544734,
+    5544737,
+    5544739
   ],
   "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": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f8629d6bf3084bad0bb7f2a1c468d66d9c705568c31c8aec820d97bdcc84289
+oid sha256:e1f2437a1269ad9291f9312e7917bb31a392410144ec7e107928c7197c550a9b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04858612055a1f0ae3d32ed06b3d9e4c931500edea167f424ecdb52ee1af3e81
+oid sha256:dfd776f13a523c02f7e651e0d17cf911755b67996d7b869232dce14d6b713dd8
 size 4040701744