Run 4. Outer Step 58. Inner Step 16.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603045,
-    5603051,
-    5603058,
-    5603065,
-    5603072
+    5603081,
+    5603088,
+    5603095,
+    5603101,
+    5603108
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b1a312c4adb728b7cbac8a99aebf693c11378fabb34590ecfaf45eb9d494b3f
+oid sha256:15d0eb93830024d1b9abc46301eaa90b7a5b55fe80c0fcef0dc8af55dae73007
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:335f2d0d28f6bd963eae8ff0069f807631af66d6d0f38f0b96fdb6e5ba425b36
+oid sha256:724e66765c3fe1ff64b9c593894d831d7f92d1f2f04809113f0a1b7437565b64
 size 4040701744