|
--- |
|
license: mit |
|
base_model: DeepaPeri/xlm-roberta-base-en-5 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
model-index: |
|
- name: xlm-roberta-base-en-15 |
|
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. --> |
|
|
|
# xlm-roberta-base-en-15 |
|
|
|
This model is a fine-tuned version of [DeepaPeri/xlm-roberta-base-en-5](https://huggingface.co/DeepaPeri/xlm-roberta-base-en-5) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5872 |
|
- F1: 0.8359 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 20 |
|
- eval_batch_size: 20 |
|
- 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 | F1 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:| |
|
| 0.1525 | 1.0 | 1000 | 0.3252 | 0.8107 | |
|
| 0.1294 | 2.0 | 2000 | 0.3068 | 0.8076 | |
|
| 0.1024 | 3.0 | 3000 | 0.3503 | 0.8117 | |
|
| 0.0778 | 4.0 | 4000 | 0.3877 | 0.8248 | |
|
| 0.0587 | 5.0 | 5000 | 0.4293 | 0.8113 | |
|
| 0.0397 | 6.0 | 6000 | 0.4690 | 0.8235 | |
|
| 0.0313 | 7.0 | 7000 | 0.4946 | 0.8283 | |
|
| 0.0188 | 8.0 | 8000 | 0.5559 | 0.8327 | |
|
| 0.0121 | 9.0 | 9000 | 0.5771 | 0.8361 | |
|
| 0.0079 | 10.0 | 10000 | 0.5872 | 0.8359 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
|
|