Run 4. Outer Step 52. Inner Step 38.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576200,
-    5576203,
-    5576205,
-    5576208,
-    5576210,
-    5576212,
-    5576214,
-    5576217
+    5576220,
+    5576221,
+    5576226,
+    5576229,
+    5576231
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 37,
+  "inner_step": 38,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ee1f475d6792439f13b4a131d5f99f1478aa82700666b37e92ae2e414a84640
+oid sha256:5ae9782a86a6e7da254585ce949a5092d47f2575ceda33085f6d6122abb469db
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64dc633103231d45e843fab4fc3e70f3bf931c310498b9aca072130629f7ef58
+oid sha256:428a7d33eaccc6ac47b98417b1f4fb64479fba505774ee93d1d3fded165a1139
 size 4040701744