<!-- 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. -->
scenario-kd-from-scratch-gold-silver-data-smsa-model-xlm-roberta-base
This model is a fine-tuned version of xlm-roberta-base on the smsa dataset. It achieves the following results on the evaluation set:
- Loss: 2.6026
- Accuracy: 0.8849
- F1: 0.8487
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6969
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 0.29 | 100 | 5.8356 | 0.7563 | 0.5133 |
| No log | 0.58 | 200 | 5.6344 | 0.7381 | 0.5131 |
| No log | 0.87 | 300 | 3.9034 | 0.8135 | 0.6972 |
| No log | 1.16 | 400 | 6.1307 | 0.7246 | 0.6337 |
| 4.8933 | 1.45 | 500 | 3.1055 | 0.8548 | 0.8130 |
| 4.8933 | 1.74 | 600 | 2.8950 | 0.8675 | 0.8281 |
| 4.8933 | 2.03 | 700 | 3.4584 | 0.8516 | 0.8268 |
| 4.8933 | 2.33 | 800 | 2.7556 | 0.8746 | 0.8397 |
| 4.8933 | 2.62 | 900 | 2.8181 | 0.8619 | 0.8209 |
| 2.6283 | 2.91 | 1000 | 2.8800 | 0.8643 | 0.8286 |
| 2.6283 | 3.2 | 1100 | 3.0356 | 0.8587 | 0.8063 |
| 2.6283 | 3.49 | 1200 | 2.6577 | 0.8714 | 0.8380 |
| 2.6283 | 3.78 | 1300 | 3.7094 | 0.8325 | 0.7720 |
| 2.6283 | 4.07 | 1400 | 2.7679 | 0.8675 | 0.8049 |
| 1.8799 | 4.36 | 1500 | 2.6853 | 0.8810 | 0.8489 |
| 1.8799 | 4.65 | 1600 | 2.8177 | 0.8635 | 0.8252 |
| 1.8799 | 4.94 | 1700 | 2.9277 | 0.8675 | 0.8042 |
| 1.8799 | 5.23 | 1800 | 2.9604 | 0.8651 | 0.7855 |
| 1.8799 | 5.52 | 1900 | 2.6743 | 0.8738 | 0.8195 |
| 1.608 | 5.81 | 2000 | 3.1438 | 0.8643 | 0.7975 |
| 1.608 | 6.1 | 2100 | 2.9100 | 0.8714 | 0.8120 |
| 1.608 | 6.4 | 2200 | 2.6482 | 0.8738 | 0.8194 |
| 1.608 | 6.69 | 2300 | 3.6885 | 0.8452 | 0.7466 |
| 1.608 | 6.98 | 2400 | 2.9792 | 0.8667 | 0.8103 |
| 1.3592 | 7.27 | 2500 | 2.6809 | 0.8810 | 0.8387 |
| 1.3592 | 7.56 | 2600 | 2.5589 | 0.8778 | 0.8350 |
| 1.3592 | 7.85 | 2700 | 2.5239 | 0.8841 | 0.8464 |
| 1.3592 | 8.14 | 2800 | 2.3706 | 0.8857 | 0.8441 |
| 1.3592 | 8.43 | 2900 | 2.5983 | 0.8762 | 0.8316 |
| 1.1517 | 8.72 | 3000 | 2.6026 | 0.8849 | 0.8487 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
