Run 4. Outer Step 50. Inner Step 10.

config.json

@@ -268,38 +268,33 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5571777,
-    5571778,
-    5571778,
-    5571779,
-    5571780,
-    5571780,
-    5571781,
-    5571782,
-    5571783,
-    5571783,
-    5571784,
-    5571784,
-    5571785,
-    5571786,
-    5571787,
-    5571788,
-    5571788,
-    5571789,
-    5571790,
-    5571791,
-    5571792,
-    5571793,
-    5571793,
-    5571794,
-    5571795
+    5571796,
+    5571798,
+    5571799,
+    5571800,
+    5571801,
+    5571802,
+    5571803,
+    5571804,
+    5571805,
+    5571806,
+    5571807,
+    5571807,
+    5571808,
+    5571809,
+    5571810,
+    5571811,
+    5571812,
+    5571813,
+    5571814,
+    5571816
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 8,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5571611,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c64dd7a3480233edc22f1ec70c11ff48755237814c942d021977f03ab54f1a3
+oid sha256:fcd24ed4dbb4dc60c51b4b8efa2379dddc5ad5060a829a9fedf33fd743e9bff5
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96724bfd0a688cff006555e3176a42541bf9955e8ad6f475ffb459062219b95d
+oid sha256:00ce6e71d77eadb5929d9622c3181d463ce15f928dd7d21c8b09322fa9d9d05b
 size 4040701744