metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
model-index:
- name: xlmr-ne-en-all_shuffled-42-test1000
results: []
xlmr-ne-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: 0.7451
- R Squared: 0.1276
- Mae: 0.6822
- Pearson R: 0.6010
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 | 0.6144 | 0.2807 | 0.6051 | 0.5401 |
| 0.6976 | 2.0 | 876 | 0.6408 | 0.2498 | 0.6383 | 0.6047 |
| 0.483 | 3.0 | 1314 | 0.7451 | 0.1276 | 0.6822 | 0.6010 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.6
- Tokenizers 0.14.1