Run 4. Outer Step 60. Inner Step 13.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607638,
-    5607642,
-    5607646,
-    5607650,
-    5607655,
-    5607658
+    5607663,
+    5607667,
+    5607670,
+    5607674,
+    5607678
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3096a3cc41c10a41c232c1faf7cbef57bcc89cc3b6681ff54a670c4d7e1204a7
+oid sha256:67271cdd528bd2cdb2216cba83658e6b308548c49aaabf4c72d13cc1afe805a2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8ac4f7c0f2df5a71f1f1e7774e4147cbf2463d38d05c1712af1248c1f993cef
+oid sha256:f7eb22e62b32b3186db8f76276bea3e6380c78036da0e6e0afb2f1888162b64e
 size 4040701744