model_gpt2_lora_d_hate_bias_hate_bias_ep_1_a_sqn_a_b_p_100_3_v_9
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5651
- Balanced Accuracy: 0.7146
- Accuracy: 0.7146
- F1 Micro: 0.7146
- F1 Macro: 0.7144
- Precision Micro: 0.7146
- Precision Macro: 0.7153
- Recall Micro: 0.7146
- Recall Macro: 0.7146
- Auc: 0.7817
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Balanced Accuracy | Accuracy | F1 Micro | F1 Macro | Precision Micro | Precision Macro | Recall Micro | Recall Macro | Auc |
---|---|---|---|---|---|---|---|---|---|---|---|---|
0.965 | 1.0 | 46 | 0.7126 | 0.5255 | 0.5255 | 0.5255 | 0.5216 | 0.5255 | 0.5263 | 0.5255 | 0.5255 | 0.5269 |
0.8371 | 2.0 | 92 | 0.6944 | 0.5633 | 0.5633 | 0.5633 | 0.5592 | 0.5633 | 0.5658 | 0.5633 | 0.5633 | 0.5831 |
0.735 | 3.0 | 138 | 0.6701 | 0.6102 | 0.6102 | 0.6102 | 0.6092 | 0.6102 | 0.6113 | 0.6102 | 0.6102 | 0.6322 |
0.7042 | 4.0 | 184 | 0.6539 | 0.6291 | 0.6291 | 0.6291 | 0.6282 | 0.6291 | 0.6303 | 0.6291 | 0.6291 | 0.6659 |
0.6273 | 5.0 | 230 | 0.6283 | 0.6382 | 0.6382 | 0.6382 | 0.6333 | 0.6382 | 0.6459 | 0.6382 | 0.6382 | 0.7125 |
0.5903 | 6.0 | 276 | 0.6031 | 0.6711 | 0.6711 | 0.6711 | 0.6692 | 0.6711 | 0.6751 | 0.6711 | 0.6711 | 0.7418 |
0.5198 | 7.0 | 322 | 0.5834 | 0.6875 | 0.6875 | 0.6875 | 0.6875 | 0.6875 | 0.6875 | 0.6875 | 0.6875 | 0.7591 |
0.4772 | 8.0 | 368 | 0.5753 | 0.6965 | 0.6965 | 0.6965 | 0.6965 | 0.6965 | 0.6966 | 0.6965 | 0.6965 | 0.7697 |
0.4775 | 9.0 | 414 | 0.5644 | 0.7130 | 0.7130 | 0.7130 | 0.7129 | 0.7130 | 0.7134 | 0.7130 | 0.7130 | 0.7808 |
0.4182 | 10.0 | 460 | 0.5651 | 0.7146 | 0.7146 | 0.7146 | 0.7144 | 0.7146 | 0.7153 | 0.7146 | 0.7146 | 0.7817 |
Framework versions
- PEFT 0.11.1
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 4