Run 4. Outer Step 24. Inner Step 56.

config.json

@@ -268,18 +268,25 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5533275,
-    5533277,
-    5533279,
-    5533281,
-    5533283
+    5533285,
+    5533286,
+    5533288,
+    5533289,
+    5533290,
+    5533292,
+    5533294,
+    5533297,
+    5533299,
+    5533301,
+    5533304,
+    5533307
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 55,
+  "inner_step": 56,
   "inner_steps": 0,
   "last_allreduce_block": 5531651,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8de93f843300b100b928788dcfc7090a490eaaf09be41d5b4b317bd0dee95786
+oid sha256:5082d6c29c4b97d08256fe33e45ac53b268e3b39249a3e002d2116287d86267c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:176176d0cdee676c738e02c293a9efd370fa409047f22d11b19104b4c9fad32d
+oid sha256:fd56ddfbeb9b57307b5dd561b734e5be2be072952ea9faa41e22a67a875f8ae3
 size 4040701744