roberta_pf_multi
This model is a fine-tuned version of FacebookAI/roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1209
- F1 Weighted: 0.8334
- F1 Samples: 0.8356
- F1 Macro: 0.6779
- F1 Micro: 0.8419
- Accuracy: 0.8133
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 | F1 Weighted | F1 Samples | F1 Macro | F1 Micro | Accuracy |
---|---|---|---|---|---|---|---|---|
0.2528 | 0.3381 | 500 | 0.1723 | 0.7338 | 0.7438 | 0.4055 | 0.7713 | 0.7280 |
0.1744 | 0.6761 | 1000 | 0.1515 | 0.7740 | 0.7622 | 0.5854 | 0.7909 | 0.7415 |
0.1504 | 1.0142 | 1500 | 0.1376 | 0.8062 | 0.8097 | 0.6394 | 0.8188 | 0.7815 |
0.1297 | 1.3523 | 2000 | 0.1315 | 0.8164 | 0.8133 | 0.6676 | 0.8215 | 0.7842 |
0.1197 | 1.6903 | 2500 | 0.1269 | 0.8223 | 0.8257 | 0.6693 | 0.8303 | 0.7997 |
0.122 | 2.0284 | 3000 | 0.1211 | 0.8302 | 0.8325 | 0.6735 | 0.8374 | 0.8072 |
0.1017 | 2.3665 | 3500 | 0.1230 | 0.8284 | 0.8312 | 0.6721 | 0.8370 | 0.8078 |
0.0998 | 2.7045 | 4000 | 0.1209 | 0.8334 | 0.8356 | 0.6779 | 0.8419 | 0.8133 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 2