<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
synthetic-50-vsfc-xlm-r
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4091
- Precision: 0.8556
- Recall: 0.5243
- F1 Weighted: 0.6121
- F1 Macro: 0.4655
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: 64
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 Weighted | F1 Macro |
---|---|---|---|---|---|---|---|
1.0942 | 0.31 | 25 | 1.0558 | 0.8673 | 0.3816 | 0.3914 | 0.2948 |
0.9353 | 0.62 | 50 | 1.0523 | 0.8262 | 0.7448 | 0.7727 | 0.5946 |
0.6801 | 0.94 | 75 | 1.5973 | 0.8845 | 0.3664 | 0.4515 | 0.3550 |
0.5368 | 1.25 | 100 | 1.2531 | 0.8369 | 0.5755 | 0.6656 | 0.5041 |
0.4458 | 1.56 | 125 | 1.4147 | 0.8289 | 0.4485 | 0.5348 | 0.4102 |
0.4611 | 1.88 | 150 | 1.4477 | 0.8686 | 0.4649 | 0.5568 | 0.4276 |
0.3957 | 2.19 | 175 | 1.7033 | 0.8750 | 0.4637 | 0.5633 | 0.4317 |
0.4183 | 2.5 | 200 | 1.6080 | 0.8555 | 0.4479 | 0.5540 | 0.4217 |
0.3482 | 2.81 | 225 | 1.4091 | 0.8556 | 0.5243 | 0.6121 | 0.4655 |
Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2