|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: sentiment-10Epochs-3 |
|
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-3 |
|
|
|
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: 0.7703 |
|
- Accuracy: 0.8568 |
|
- F1: 0.8526 |
|
- Precision: 0.8787 |
|
- Recall: 0.8279 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.3637 | 1.0 | 7088 | 0.3830 | 0.8571 | 0.8418 | 0.9429 | 0.7603 | |
|
| 0.37 | 2.0 | 14176 | 0.4128 | 0.8676 | 0.8582 | 0.9242 | 0.8010 | |
|
| 0.325 | 3.0 | 21264 | 0.4656 | 0.8737 | 0.8664 | 0.9189 | 0.8197 | |
|
| 0.2948 | 4.0 | 28352 | 0.4575 | 0.8703 | 0.8652 | 0.9007 | 0.8324 | |
|
| 0.3068 | 5.0 | 35440 | 0.4751 | 0.8705 | 0.8653 | 0.9016 | 0.8317 | |
|
| 0.2945 | 6.0 | 42528 | 0.5509 | 0.8668 | 0.8618 | 0.8956 | 0.8305 | |
|
| 0.2568 | 7.0 | 49616 | 0.6201 | 0.8632 | 0.8567 | 0.8994 | 0.8178 | |
|
| 0.2107 | 8.0 | 56704 | 0.6836 | 0.8614 | 0.8576 | 0.8819 | 0.8346 | |
|
| 0.1966 | 9.0 | 63792 | 0.7030 | 0.8583 | 0.8532 | 0.8848 | 0.8238 | |
|
| 0.1675 | 10.0 | 70880 | 0.7703 | 0.8568 | 0.8526 | 0.8787 | 0.8279 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.18.0 |
|
- Pytorch 1.10.0 |
|
- Datasets 2.0.0 |
|
- Tokenizers 0.11.6 |
|
|
