memo3_ND
This model is a fine-tuned version of MiMe-MeMo/MeMo-BERT-03 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5131
- F1-score: 0.8634
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: 5e-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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1-score |
|---|---|---|---|---|
| 0.1986 | 1.0 | 1177 | 0.4906 | 0.8009 |
| 0.187 | 2.0 | 2354 | 0.5147 | 0.7915 |
| 0.172 | 3.0 | 3531 | 0.5131 | 0.8634 |
| 0.1868 | 4.0 | 4708 | 0.5832 | 0.7950 |
| 0.1653 | 5.0 | 5885 | 0.5538 | 0.8530 |
| 0.1585 | 6.0 | 7062 | 0.4072 | 0.8625 |
| 0.1637 | 7.0 | 8239 | 0.5193 | 0.8417 |
| 0.1514 | 8.0 | 9416 | 0.5005 | 0.8508 |
| 0.151 | 9.0 | 10593 | 0.5406 | 0.8521 |
| 0.159 | 10.0 | 11770 | 0.5156 | 0.8533 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 6
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for yemen2016/memo3_ND
Base model
MiMe-MeMo/MeMo-BERT-03