Excitement_Seeking_binary
This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0947
- Accuracy: 0.6600
- Precision: 0.6608
- Recall: 0.6559
- F1: 0.6583
- Auc: 0.7005
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 1234
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Auc |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 118 | 0.6041 | 0.6737 | 0.7340 | 0.5436 | 0.6246 | 0.7516 |
| No log | 2.0 | 236 | 0.5918 | 0.7036 | 0.7335 | 0.6384 | 0.6827 | 0.7544 |
| No log | 3.0 | 354 | 0.6325 | 0.6824 | 0.6637 | 0.7382 | 0.6989 | 0.7433 |
| No log | 4.0 | 472 | 0.7191 | 0.6501 | 0.62 | 0.7731 | 0.6881 | 0.7335 |
| 0.5332 | 5.0 | 590 | 0.8838 | 0.6700 | 0.6411 | 0.7706 | 0.6999 | 0.7185 |
| 0.5332 | 6.0 | 708 | 1.0428 | 0.6650 | 0.6897 | 0.5985 | 0.6409 | 0.7031 |
| 0.5332 | 7.0 | 826 | 1.0947 | 0.6600 | 0.6608 | 0.6559 | 0.6583 | 0.7005 |
Framework versions
- Transformers 4.44.1
- Pytorch 1.11.0
- Datasets 2.12.0
- Tokenizers 0.19.1