<!-- 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. -->
combine-60-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: 0.2538
- Precision: 0.8786
- Recall: 0.9210
- F1 Weighted: 0.8993
- F1 Macro: 0.6284
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 |
|---|---|---|---|---|---|---|---|
| 1.12 | 0.09 | 25 | 1.0597 | 0.2586 | 0.5085 | 0.3429 | 0.2247 |
| 0.9016 | 0.18 | 50 | 0.5441 | 0.8258 | 0.8642 | 0.8440 | 0.5895 |
| 0.6163 | 0.27 | 75 | 0.4097 | 0.8713 | 0.9109 | 0.8897 | 0.6215 |
| 0.4973 | 0.36 | 100 | 0.3429 | 0.8726 | 0.9135 | 0.8923 | 0.6234 |
| 0.4666 | 0.46 | 125 | 0.3091 | 0.8774 | 0.9198 | 0.8981 | 0.6277 |
| 0.4458 | 0.55 | 150 | 0.3671 | 0.8788 | 0.8888 | 0.8697 | 0.6153 |
| 0.386 | 0.64 | 175 | 0.2554 | 0.8811 | 0.9229 | 0.9012 | 0.6297 |
| 0.3975 | 0.73 | 200 | 0.2712 | 0.8834 | 0.9255 | 0.9037 | 0.6314 |
| 0.3293 | 0.82 | 225 | 0.2538 | 0.8786 | 0.9210 | 0.8993 | 0.6284 |
Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
