Run 4. Outer Step 62. Inner Step 25.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611313,
-    5611317,
-    5611322,
-    5611327,
-    5611331
+    5611337,
+    5611341,
+    5611346,
+    5611351,
+    5611355
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "inner_steps": 0,
   "last_allreduce_block": 5605539,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871a80febe5fe4189efc41f7354eb862d5fca160bd1ea4500dad9846fbff8cb3
+oid sha256:e364fbc91aa7030189463774707d251dbe76e8acc3059e984792774270344994
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a838db723f89a713f6005068206999fb1137d6012b985d63dd75b7a68f6dea49
+oid sha256:950c24de48ca6e8e10ad4a9fbd82921f059dedb58d59287690e4ba49387292ef
 size 4040701744