|
|
--- |
|
|
library_name: transformers |
|
|
license: mit |
|
|
base_model: xlm-roberta-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: output_fp16 |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# output_fp16 |
|
|
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.4230 |
|
|
- Accuracy: 0.8382 |
|
|
|
|
|
## 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: 0.0003 |
|
|
- train_batch_size: 32 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 15 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:-----:|:------:|:---------------:|:--------:| |
|
|
| 0.5485 | 1.0 | 12272 | 0.4865 | 0.8100 | |
|
|
| 0.4989 | 2.0 | 24544 | 0.4720 | 0.8193 | |
|
|
| 0.4743 | 3.0 | 36816 | 0.5417 | 0.7859 | |
|
|
| 0.4762 | 4.0 | 49088 | 0.4359 | 0.8313 | |
|
|
| 0.4525 | 5.0 | 61360 | 0.4297 | 0.8365 | |
|
|
| 0.4457 | 6.0 | 73632 | 0.4273 | 0.8398 | |
|
|
| 0.4205 | 7.0 | 85904 | 0.4343 | 0.8321 | |
|
|
| 0.4315 | 8.0 | 98176 | 0.4287 | 0.8357 | |
|
|
| 0.4271 | 9.0 | 110448 | 0.4299 | 0.8394 | |
|
|
| 0.4031 | 10.0 | 122720 | 0.4250 | 0.8353 | |
|
|
| 0.4 | 11.0 | 134992 | 0.4401 | 0.8345 | |
|
|
| 0.3899 | 12.0 | 147264 | 0.4178 | 0.8418 | |
|
|
| 0.3921 | 13.0 | 159536 | 0.4313 | 0.8386 | |
|
|
| 0.3849 | 14.0 | 171808 | 0.4212 | 0.8378 | |
|
|
| 0.3777 | 15.0 | 184080 | 0.4230 | 0.8382 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.53.2 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.21.2 |
|
|
|
