|
--- |
|
license: mit |
|
base_model: xlm-roberta-base |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: xlmr-si-en-all_shuffled-2020-test1000 |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# xlmr-si-en-all_shuffled-2020-test1000 |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8030 |
|
- R Squared: 0.0373 |
|
- Mae: 0.7088 |
|
- Pearson R: 0.5232 |
|
|
|
## 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: 2020 |
|
- 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 | 0.7537 | 0.0964 | 0.7613 | 0.3509 | |
|
| 0.8088 | 2.0 | 876 | 0.6291 | 0.2458 | 0.6462 | 0.5263 | |
|
| 0.6342 | 3.0 | 1314 | 0.8030 | 0.0373 | 0.7088 | 0.5232 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|