metadata
license: mit
base_model: youngggggg/ToxiGen-ConPrompt
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: implicit-toxicgenconprompt-all-no-lora
results: []
implicit-toxicgenconprompt-all-no-lora
This model is a fine-tuned version of youngggggg/ToxiGen-ConPrompt on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8445
- Accuracy: {'accuracy': 0.8500114495076712}
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 20
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.236 | 1.0 | 2217 | 0.4258 | {'accuracy': 0.8410808335241584} |
| 0.123 | 2.0 | 4434 | 0.5409 | {'accuracy': 0.8465765972063202} |
| 0.0585 | 3.0 | 6651 | 0.7576 | {'accuracy': 0.8477215479734371} |
| 0.0273 | 4.0 | 8868 | 0.8445 | {'accuracy': 0.8500114495076712} |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2