Run 4. Outer Step 33. Inner Step 23.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544676,
-    5544678,
-    5544681,
-    5544683,
-    5544685,
-    5544687,
-    5544690
+    5544692,
+    5544695,
+    5544698,
+    5544701,
+    5544704
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:607d9f18c30759edd7a42c87dc5b4f9a4413743f37fbc746f51f8385af6918dc
+oid sha256:e277f8135ebb5d2acaf52d4c996a70139069b1d586fe3a248c755696d3424111
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b60ebe802486c9c637eef232b6a4acf4d59d388e12188eb0c7cb364c29b5eed
+oid sha256:a4b6142dfb2f23af65e7155e32f91631ad23f352535a6e64f5a78525273a4f90
 size 4040701744