<!-- 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-70-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: 1.7726
- Precision: 0.8498
- Recall: 0.4018
- F1 Weighted: 0.5020
- F1 Macro: 0.3865
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 |
---|---|---|---|---|---|---|---|
1.1007 | 0.22 | 25 | 1.1227 | 0.0021 | 0.0461 | 0.0041 | 0.0294 |
0.8388 | 0.45 | 50 | 0.7289 | 0.8086 | 0.8105 | 0.8075 | 0.6172 |
0.5915 | 0.67 | 75 | 1.0029 | 0.8601 | 0.5155 | 0.6026 | 0.4582 |
0.4876 | 0.89 | 100 | 1.5117 | 0.8650 | 0.4820 | 0.5787 | 0.4426 |
0.3964 | 1.12 | 125 | 1.3913 | 0.8461 | 0.3973 | 0.4908 | 0.3829 |
0.4464 | 1.34 | 150 | 1.3103 | 0.8332 | 0.5130 | 0.5554 | 0.4201 |
0.485 | 1.56 | 175 | 1.5958 | 0.8831 | 0.4277 | 0.5336 | 0.4108 |
0.4471 | 1.79 | 200 | 1.5570 | 0.8774 | 0.4713 | 0.5527 | 0.4252 |
0.3867 | 2.01 | 225 | 1.7726 | 0.8498 | 0.4018 | 0.5020 | 0.3865 |
Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2