metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
model-index:
- name: QA_SYNTH_DATA_WITH_UNANSWERABLE_05_SEPT
results: []
QA_SYNTH_DATA_WITH_UNANSWERABLE_05_SEPT
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: 0.0053
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0478 | 1.0 | 16275 | 0.0446 |
| 0.0825 | 2.0 | 32550 | 0.0349 |
| 0.0674 | 3.0 | 48825 | 0.0366 |
| 0.0088 | 4.0 | 65100 | 0.0301 |
| 0.0102 | 5.0 | 81375 | 0.0110 |
| 0.0036 | 6.0 | 97650 | 0.0040 |
| 0.0 | 7.0 | 113925 | 0.0055 |
| 0.0 | 8.0 | 130200 | 0.0056 |
| 0.0 | 9.0 | 146475 | 0.0052 |
| 0.0 | 10.0 | 162750 | 0.0053 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3