model_google_gemma_2_2b_d_gender_bias_hate_bias_ep_1_a_sqn_a_b_p_100_5_v_7
This model is a fine-tuned version of google/gemma-2b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5269
- Balanced Accuracy: 0.8322
- Accuracy: 0.8322
- F1 Micro: 0.8322
- F1 Macro: 0.8322
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Balanced Accuracy | Accuracy | F1 Micro | F1 Macro |
---|---|---|---|---|---|---|---|
0.7301 | 1.0 | 76 | 0.4314 | 0.8059 | 0.8059 | 0.8059 | 0.8045 |
0.1813 | 2.0 | 152 | 0.4905 | 0.8273 | 0.8273 | 0.8273 | 0.8268 |
0.022 | 3.0 | 228 | 0.5269 | 0.8322 | 0.8322 | 0.8322 | 0.8322 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1