|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: sentiment-10Epochs |
|
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. --> |
|
|
|
# sentiment-10Epochs |
|
|
|
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: 0.7030 |
|
- Accuracy: 0.8603 |
|
- F1: 0.8585 |
|
- Precision: 0.8699 |
|
- Recall: 0.8473 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- 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 | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.3645 | 1.0 | 7088 | 0.4315 | 0.8603 | 0.8466 | 0.9386 | 0.7711 | |
|
| 0.374 | 2.0 | 14176 | 0.4015 | 0.8713 | 0.8648 | 0.9105 | 0.8235 | |
|
| 0.3363 | 3.0 | 21264 | 0.4772 | 0.8705 | 0.8615 | 0.9256 | 0.8057 | |
|
| 0.3131 | 4.0 | 28352 | 0.4579 | 0.8702 | 0.8650 | 0.9007 | 0.8321 | |
|
| 0.3097 | 5.0 | 35440 | 0.4160 | 0.8721 | 0.8663 | 0.9069 | 0.8292 | |
|
| 0.2921 | 6.0 | 42528 | 0.4638 | 0.8673 | 0.8630 | 0.8917 | 0.8362 | |
|
| 0.2725 | 7.0 | 49616 | 0.5183 | 0.8654 | 0.8602 | 0.8947 | 0.8283 | |
|
| 0.2481 | 8.0 | 56704 | 0.5846 | 0.8649 | 0.8624 | 0.8787 | 0.8467 | |
|
| 0.192 | 9.0 | 63792 | 0.6481 | 0.8610 | 0.8596 | 0.8680 | 0.8514 | |
|
| 0.1945 | 10.0 | 70880 | 0.7030 | 0.8603 | 0.8585 | 0.8699 | 0.8473 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.18.0 |
|
- Pytorch 1.10.0 |
|
- Datasets 2.0.0 |
|
- Tokenizers 0.11.6 |
|
|
