metadata
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: test-results-concat
results: []
test-results-concat
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9408
- Accuracy: 0.6012
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: 123
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0408 | 0.33 | 5000 | 0.9773 | 0.5697 |
| 0.9442 | 0.67 | 10000 | 0.9701 | 0.5853 |
| 0.9579 | 1.0 | 15000 | 0.9502 | 0.5895 |
| 0.8867 | 1.33 | 20000 | 0.9467 | 0.5897 |
| 0.8819 | 1.67 | 25000 | 0.9371 | 0.5893 |
| 0.8748 | 2.0 | 30000 | 0.9408 | 0.6012 |
| 0.7759 | 2.33 | 35000 | 0.9734 | 0.5968 |
| 0.7599 | 2.67 | 40000 | 0.9722 | 0.5948 |
| 0.7626 | 3.0 | 45000 | 0.9654 | 0.5975 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1