Fix eval_sample_packing in llama-3 lora example (#1716) [skip ci]

* Fix eval_sample_packing in llama-3 lora example * Update examples/llama-3/lora-8b.yml Co-authored-by: Wing Lian <[email protected]> --------- Co-authored-by: Wing Lian <[email protected]>
axolotl-ai-cloud · Jul 13, 2024 · 219cd0d · 219cd0d
1 parent 634f384
commit 219cd0d
Showing 1 changed file with 1 addition and 0 deletions.
diff --git a/examples/llama-3/lora-8b.yml b/examples/llama-3/lora-8b.yml
@@ -15,6 +15,7 @@ output_dir: ./outputs/lora-out
 
 sequence_len: 4096
 sample_packing: true
+eval_sample_packing: false
 pad_to_sequence_len: true
 
 adapter: lora