Run 4. Outer Step 4. Inner Step 28.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5487245,
-    5487247,
-    5487249,
-    5487251,
-    5487253,
-    5487256,
-    5487259,
-    5487261
+    5487263,
+    5487266,
+    5487268,
+    5487271,
+    5487273
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "inner_steps": 0,
   "last_allreduce_block": 5485540,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba05f3bee8ca326dbc9af08e9bb0344a08a403a65ab93f494cfc0fd607fb960a
+oid sha256:3871ea9975249f8dd924a53e66f01d3977f64cbda4a3c11d0a6012484d25b856
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f361990da3ce23e7046e4575c325088dc2406d8a7c9c0a7b6f3e85bc11d9ffc1
+oid sha256:894d6b580d089260df60376c2243778fd622dee859229c6a7affb987e0a52a0e
 size 4040701744