BRlkl commited on
Commit
1e23579
·
verified ·
1 Parent(s): 4182092

Upload benchmark_results.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. 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 |