metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
model-index:
- name: xlmr-si-en-all_shuffled-42-test1000
results: []
xlmr-si-en-all_shuffled-42-test1000
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8606
- R Squared: -0.0217
- Mae: 0.7408
- Pearson R: 0.5130
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | R Squared | Mae | Pearson R |
|---|---|---|---|---|---|---|
| No log | 1.0 | 438 | 0.6977 | 0.1718 | 0.7326 | 0.4475 |
| 0.7872 | 2.0 | 876 | 0.6551 | 0.2223 | 0.6841 | 0.5166 |
| 0.6178 | 3.0 | 1314 | 0.8606 | -0.0217 | 0.7408 | 0.5130 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.6
- Tokenizers 0.14.1