Run 4. Outer Step 54. Inner Step 86.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580117,
-    5580120,
-    5580122,
-    5580124,
-    5580126,
-    5580128,
-    5580129,
-    5580132
+    5580134,
+    5580137,
+    5580139,
+    5580142,
+    5580144
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 85,
+  "inner_step": 86,
   "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 sha256:09cba4b272ad7afc4a784f51917f2fdb90857d3082c54ccf9db05269e181e399
+oid sha256:84ff28abd308b1c57240cfb943666b2ca2191e8fb849b44847214fe686a7f14e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4808e62f385ccfaa483126af942db738d07313bc733ade99b891a51dc69ca7fb
+oid sha256:80c333c7c091eeb71de06e76a56661391a034d852b94cbcf9278cff223d2a9cf
 size 4040701744