Upload benchmark_results.md with huggingface_hub
Browse files- benchmark_results.md +24 -0
benchmark_results.md
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Hyperparameter Search Results for `BRlkl/BingoGuard-bert-base-pt-optimized`
|
| 2 |
+
|
| 3 |
+
This model was selected through a randomized search over a hyperparameter space.
|
| 4 |
+
The best performing model was chosen based on the highest average F1 score across multiple benchmark datasets.
|
| 5 |
+
|
| 6 |
+
## Best Hyperparameters
|
| 7 |
+
|
| 8 |
+
```
|
| 9 |
+
learning_rate: 5e-05
|
| 10 |
+
per_device_train_batch_size: 16
|
| 11 |
+
num_train_epochs: 4
|
| 12 |
+
weight_decay: 0.01
|
| 13 |
+
lr_scheduler_type: cosine
|
| 14 |
+
```
|
| 15 |
+
|
| 16 |
+
## Final Benchmark Results (Full Dataset Training)
|
| 17 |
+
|
| 18 |
+
| dataset | accuracy | f1_score | recall | precision |
|
| 19 |
+
|:----------------------------------|-----------:|-----------:|---------:|------------:|
|
| 20 |
+
| BRlkl/BingoGuard-train-test-pt | 0.902834 | 0.948936 | 0.902834 | 1 |
|
| 21 |
+
| BRlkl/openai-moderation-eval-pt | 0.672024 | 0.635341 | 0.91954 | 0.485339 |
|
| 22 |
+
| BRlkl/WildGuardTest-pt | 0.844614 | 0.825166 | 0.82626 | 0.824074 |
|
| 23 |
+
| BRlkl/XSTest-pt | 0.82 | 0.819599 | 0.92 | 0.738956 |
|
| 24 |
+
| BRlkl/toxic-chat-pt (40% holdout) | 0.940887 | 0.673913 | 0.898551 | 0.53913 |
|