Run 4. Outer Step 13. Inner Step 40.

config.json

@@ -268,20 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5511010,
-    5511015,
-    5511017,
-    5511022,
-    5511025,
-    5511031,
-    5511035
+    5511040,
+    5511044,
+    5511048,
+    5511052,
+    5511056,
+    5511060
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5508496,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e35a9da8b8b120f6aed02f8b92eceabc5158532d8f84b7aa3d996bebca411324
+oid sha256:3e8e9ea820b9e45735bbb478e6f1db09ee12b941f47c7966785487ac9c3c0a01
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdcb4437a08bebd0f3758170733a7cfc5d30c5c9f1fd65abb13a104aa122f622
+oid sha256:d01c67d2adb58b27ccb2030734b2d63f2358dd38b40b2fee88ace9a849d280dd
 size 4040701744