<!-- 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. -->
V3_20230929-4-xlm-roberta-base-new
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Accuracy: 0.4828
- Loss: 2.7092
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
Training Loss | Epoch | Step | Accuracy | Validation Loss |
---|---|---|---|---|
4.6198 | 0.46 | 200 | 0.35 | nan |
4.1243 | 0.91 | 400 | 0.3244 | nan |
3.7837 | 1.37 | 600 | 0.3273 | nan |
3.7335 | 1.82 | 800 | 0.3293 | nan |
3.4681 | 2.28 | 1000 | 0.3963 | nan |
3.4469 | 2.73 | 1200 | 0.4186 | nan |
3.3005 | 3.19 | 1400 | 0.4307 | 3.0076 |
3.2722 | 3.64 | 1600 | 0.4257 | nan |
3.3514 | 4.1 | 1800 | 0.4832 | 2.5834 |
3.0384 | 4.56 | 2000 | 0.4397 | 2.9867 |
3.0971 | 5.01 | 2200 | 0.3799 | nan |
2.903 | 5.47 | 2400 | 0.5107 | 2.6798 |
3.006 | 5.92 | 2600 | 0.4504 | 2.9205 |
2.7999 | 6.38 | 2800 | 0.4809 | nan |
2.8268 | 6.83 | 3000 | 0.4321 | 2.5767 |
2.8814 | 7.29 | 3200 | 0.4706 | 2.7337 |
2.6975 | 7.74 | 3400 | 0.4831 | nan |
2.7642 | 8.2 | 3600 | 0.4669 | 2.8202 |
2.8996 | 8.66 | 3800 | 0.5187 | 2.7733 |
2.6657 | 9.11 | 4000 | 0.4697 | nan |
2.7318 | 9.57 | 4200 | 0.4532 | nan |
2.7065 | 10.02 | 4400 | 0.4785 | 2.5715 |
2.5635 | 10.48 | 4600 | 0.4969 | 2.8287 |
2.5543 | 10.93 | 4800 | 0.4909 | 2.3697 |
2.5284 | 11.39 | 5000 | 0.4706 | nan |
2.5401 | 11.85 | 5200 | 0.4679 | nan |
2.4722 | 12.3 | 5400 | 0.4983 | 2.3692 |
2.5367 | 12.76 | 5600 | 0.5663 | nan |
2.5331 | 13.21 | 5800 | 0.525 | nan |
2.183 | 13.67 | 6000 | 0.5137 | 2.3417 |
2.4319 | 14.12 | 6200 | 0.5409 | 2.2783 |
2.4168 | 14.58 | 6400 | 0.4828 | 2.7092 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3