metadata
license: mit
tags:
- text-classification
- generated_from_trainer
datasets:
- paws-x
metrics:
- accuracy
model-index:
- name: paws_x_xlm_r_only_en
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: paws-x
type: paws-x
config: en
split: train
args: en
metrics:
- name: Accuracy
type: accuracy
value: 0.9275
paws_x_xlm_r_only_en
This model is a fine-tuned version of xlm-roberta-base on the paws-x dataset. It achieves the following results on the evaluation set:
- Loss: 0.3472
- Accuracy: 0.9275
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4679 | 1.0 | 386 | 0.2403 | 0.912 |
| 0.1898 | 2.0 | 772 | 0.2232 | 0.9265 |
| 0.1283 | 3.0 | 1158 | 0.2266 | 0.9325 |
| 0.0989 | 4.0 | 1544 | 0.2439 | 0.932 |
| 0.0764 | 5.0 | 1930 | 0.2507 | 0.9305 |
| 0.0627 | 6.0 | 2316 | 0.2941 | 0.931 |
| 0.0507 | 7.0 | 2702 | 0.2995 | 0.93 |
| 0.0436 | 8.0 | 3088 | 0.3279 | 0.9315 |
| 0.0356 | 9.0 | 3474 | 0.3423 | 0.929 |
| 0.031 | 10.0 | 3860 | 0.3472 | 0.9275 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0
- Datasets 2.6.1
- Tokenizers 0.13.1