|
--- |
|
license: apache-2.0 |
|
base_model: casual/nlp_til2 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: nlp_til2 |
|
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. --> |
|
|
|
# nlp_til2 |
|
|
|
This model is a fine-tuned version of [casual/nlp_til2](https://huggingface.co/casual/nlp_til2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0128 |
|
- Precision: 0.9739 |
|
- Recall: 0.9708 |
|
- F1: 0.9723 |
|
- Accuracy: 0.9960 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 18 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 219 | 0.0548 | 0.8595 | 0.8533 | 0.8564 | 0.9777 | |
|
| No log | 2.0 | 438 | 0.0538 | 0.8705 | 0.8560 | 0.8632 | 0.9788 | |
|
| 0.0699 | 3.0 | 657 | 0.0531 | 0.8735 | 0.8626 | 0.8680 | 0.9785 | |
|
| 0.0699 | 4.0 | 876 | 0.0459 | 0.8872 | 0.8833 | 0.8853 | 0.9816 | |
|
| 0.0635 | 5.0 | 1095 | 0.0437 | 0.8876 | 0.8934 | 0.8905 | 0.9829 | |
|
| 0.0635 | 6.0 | 1314 | 0.0358 | 0.9093 | 0.9001 | 0.9047 | 0.9859 | |
|
| 0.0567 | 7.0 | 1533 | 0.0333 | 0.9170 | 0.9111 | 0.9140 | 0.9874 | |
|
| 0.0567 | 8.0 | 1752 | 0.0303 | 0.9364 | 0.9229 | 0.9296 | 0.9889 | |
|
| 0.0567 | 9.0 | 1971 | 0.0263 | 0.9432 | 0.9285 | 0.9358 | 0.9905 | |
|
| 0.0498 | 10.0 | 2190 | 0.0258 | 0.9320 | 0.9419 | 0.9369 | 0.9908 | |
|
| 0.0498 | 11.0 | 2409 | 0.0237 | 0.9431 | 0.9445 | 0.9438 | 0.9916 | |
|
| 0.0437 | 12.0 | 2628 | 0.0187 | 0.9646 | 0.9534 | 0.9590 | 0.9936 | |
|
| 0.0437 | 13.0 | 2847 | 0.0179 | 0.9636 | 0.9609 | 0.9623 | 0.9945 | |
|
| 0.0425 | 14.0 | 3066 | 0.0159 | 0.9671 | 0.9642 | 0.9657 | 0.9949 | |
|
| 0.0425 | 15.0 | 3285 | 0.0146 | 0.9654 | 0.9648 | 0.9651 | 0.9952 | |
|
| 0.0464 | 16.0 | 3504 | 0.0137 | 0.9691 | 0.9687 | 0.9689 | 0.9956 | |
|
| 0.0464 | 17.0 | 3723 | 0.0135 | 0.9713 | 0.9695 | 0.9704 | 0.9957 | |
|
| 0.0464 | 18.0 | 3942 | 0.0128 | 0.9739 | 0.9708 | 0.9723 | 0.9960 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
