Run 4. Outer Step 54. Inner Step 90.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580242,
-    5580245,
-    5580246,
-    5580248,
-    5580251,
-    5580254,
-    5580257
+    5580260,
+    5580264,
+    5580266,
+    5580267,
+    5580268
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 89,
+  "inner_step": 90,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5c79856461cb267f46394039fd08ae322180884c032dd041edc5d34d4b117bb
+oid sha256:47e1f4133101b00ab915893fe43ef55f3a46fab0eb30d082fd6a3bf0655ed523
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b872384152024837cb7328eeda0506ebc6ae8beca3e10ec5343384d7445f4907
+oid sha256:df1035a565246d81577fc737664e39497926ff2142850af9a9469566ae96e09f
 size 4040701744