<!-- 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. -->
xlm-roberta-base-09072023-revised
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: 0.7354
- Loss: 1.2865
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: 10
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| 1.2004 | 0.77 | 100 | 0.6813 | 1.4010 |
| 1.5282 | 1.54 | 200 | 0.7119 | 1.2520 |
| 1.6864 | 2.31 | 300 | 0.6591 | 1.5774 |
| 1.5648 | 3.08 | 400 | 0.72 | 1.3837 |
| 1.6035 | 3.85 | 500 | 0.7092 | 1.3721 |
| 1.6456 | 4.62 | 600 | 0.6557 | 1.5037 |
| 1.472 | 5.38 | 700 | 0.6822 | 1.3919 |
| 1.5617 | 6.15 | 800 | 0.7014 | 1.4154 |
| 1.4883 | 6.92 | 900 | 0.7269 | 1.2583 |
| 1.4402 | 7.69 | 1000 | 0.6877 | 1.5842 |
| 1.5903 | 8.46 | 1100 | 0.7184 | 1.3132 |
| 1.4025 | 9.23 | 1200 | 0.7148 | 1.2230 |
| 1.4793 | 10.0 | 1300 | 0.7354 | 1.2865 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
