metadata
license: mit
tags:
- text-classification
- generated_from_trainer
datasets:
- xnli
metrics:
- accuracy
model-index:
- name: xnli_xlm_r_only_ur
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: xnli
type: xnli
config: ur
split: train
args: ur
metrics:
- name: Accuracy
type: accuracy
value: 0.6526104417670683
xnli_xlm_r_only_ur
This model is a fine-tuned version of xlm-roberta-base on the xnli dataset. It achieves the following results on the evaluation set:
- Loss: 0.8165
- Accuracy: 0.6526
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: 1.5e-05
- train_batch_size: 192
- eval_batch_size: 192
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.0253 | 1.0 | 2046 | 0.8330 | 0.6382 |
0.9659 | 2.0 | 4092 | 0.8105 | 0.6530 |
0.9445 | 3.0 | 6138 | 0.7978 | 0.6558 |
0.9254 | 4.0 | 8184 | 0.7791 | 0.6594 |
0.9075 | 5.0 | 10230 | 0.7792 | 0.6614 |
0.8892 | 6.0 | 12276 | 0.7812 | 0.6554 |
0.8728 | 7.0 | 14322 | 0.7762 | 0.6538 |
0.8565 | 8.0 | 16368 | 0.8019 | 0.6494 |
0.8427 | 9.0 | 18414 | 0.8067 | 0.6558 |
0.8332 | 10.0 | 20460 | 0.8165 | 0.6526 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0
- Datasets 2.6.1
- Tokenizers 0.13.1