pixel-base-finetuned-xnli-translate-train-all
This model is a fine-tuned version of Team-PIXEL/pixel-base on the XNLI dataset.
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: 256
- eval_batch_size: 8
- seed: 555
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- training_steps: 50000
- mixed_precision_training: Apex, opt level O1
Framework versions
- Transformers 4.17.0
- Pytorch 1.11.0
- Datasets 2.0.0
- Tokenizers 0.12.1
- Downloads last month
- 17
Dataset used to train Team-PIXEL/pixel-base-finetuned-xnli-translate-train-all
Evaluation results
- Joint validation accuracy on XNLIself-reported0.625