Run 3. Outer Step 10. Inner Step 14.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5422275,
-    5422278,
-    5422282,
-    5422285,
-    5422288
+    5422315,
+    5422319,
+    5422322,
+    5422325,
+    5422328
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 14,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aabdce32905f44440b4c35d99fbd561086fedbe145ad3e923bcd72d7cd971f2
+oid sha256:f047ad3267b0ab54ab7f09b2cf909f7e2126652d84b1741ba4fe01eff261a08a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6b2f6a98237806b5233878d6fab47b45e0569c86ecadddd1813033220cf37c2
+oid sha256:1134c52c45b9890f62670eb59cd0c4f276e9f64f2a95ba32e3a9adace8208c48
 size 4040701744