Run 4. Outer Step 33. Inner Step 20.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544678,
-    5544682,
-    5544685,
-    5544688,
-    5544690,
-    5544692,
-    5544695,
-    5544697
+    5544699,
+    5544702,
+    5544705,
+    5544706,
+    5544713
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "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:a76a0ad70d9a4a303950c5d84c6c62fd4b38a450ff13ee6f599e70da097cc7fc
+oid sha256:3024ffb6bb39015fd82220d844f02fccfca8dbd3e38cd2df69d67053fd8a96b9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5605a07f1d4ed1c942df46f58ac65266500f813491aa6dd9f394827d49bef05c
+oid sha256:0691bb7aa0d71c641c034a02108f2059301b3f1953c1ecee9470fbb1cf103d3c
 size 4040701744