|
--- |
|
license: mit |
|
base_model: xlnet-base-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: xlnet-base-cased-HU |
|
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. --> |
|
|
|
# xlnet-base-cased-HU |
|
|
|
This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8571 |
|
- Accuracy: 0.8465 |
|
- F1: 0.7979 |
|
- Precision: 0.875 |
|
- Recall: 0.7333 |
|
|
|
## 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: 16 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.7086 | 1.0 | 64 | 0.6695 | 0.5866 | 0.0 | 0.0 | 0.0 | |
|
| 0.6423 | 2.0 | 128 | 0.6102 | 0.6929 | 0.6777 | 0.5985 | 0.7810 | |
|
| 0.5089 | 3.0 | 192 | 0.5276 | 0.7756 | 0.7016 | 0.7791 | 0.6381 | |
|
| 0.491 | 4.0 | 256 | 0.8212 | 0.7559 | 0.6310 | 0.8413 | 0.5048 | |
|
| 0.3367 | 5.0 | 320 | 0.6119 | 0.8189 | 0.7982 | 0.7398 | 0.8667 | |
|
| 0.2412 | 6.0 | 384 | 0.4921 | 0.8346 | 0.7742 | 0.8889 | 0.6857 | |
|
| 0.154 | 7.0 | 448 | 0.8891 | 0.8268 | 0.7609 | 0.8861 | 0.6667 | |
|
| 0.1075 | 8.0 | 512 | 0.9218 | 0.8504 | 0.8021 | 0.8851 | 0.7333 | |
|
| 0.081 | 9.0 | 576 | 0.8782 | 0.8465 | 0.7958 | 0.8837 | 0.7238 | |
|
| 0.0727 | 10.0 | 640 | 0.8571 | 0.8465 | 0.7979 | 0.875 | 0.7333 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.43.0.dev0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
