<!-- 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-30-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: 1.5151
- Precision: 0.8404
- Recall: 0.4934
- F1 Weighted: 0.5903
- F1 Macro: 0.4491
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 |
|---|---|---|---|---|---|---|---|
| 1.0948 | 0.52 | 25 | 1.0688 | 0.8549 | 0.3936 | 0.4525 | 0.3417 |
| 0.8944 | 1.04 | 50 | 1.0322 | 0.8312 | 0.8004 | 0.8097 | 0.6402 |
| 0.5958 | 1.56 | 75 | 1.2383 | 0.8377 | 0.5938 | 0.6785 | 0.5159 |
| 0.4904 | 2.08 | 100 | 1.2349 | 0.8497 | 0.6715 | 0.7400 | 0.5643 |
| 0.499 | 2.6 | 125 | 1.0563 | 0.8417 | 0.7119 | 0.7629 | 0.5814 |
| 0.4567 | 3.12 | 150 | 1.3069 | 0.8000 | 0.5205 | 0.6048 | 0.4573 |
| 0.4061 | 3.65 | 175 | 1.4464 | 0.8399 | 0.4422 | 0.5289 | 0.4034 |
| 0.3652 | 4.17 | 200 | 1.4604 | 0.8393 | 0.5016 | 0.6091 | 0.4594 |
| 0.3696 | 4.69 | 225 | 1.5151 | 0.8404 | 0.4934 | 0.5903 | 0.4491 |
Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
