|
--- |
|
license: apache-2.0 |
|
base_model: PartAI/TookaBERT-Base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: my_model |
|
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. --> |
|
|
|
# my_model |
|
|
|
This model is a fine-tuned version of [PartAI/TookaBERT-Base](https://huggingface.co/PartAI/TookaBERT-Base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9495 |
|
- Precision: 0.5098 |
|
- Recall: 0.4866 |
|
- F1: 0.4979 |
|
- Accuracy: 0.8050 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 10 | 1.4199 | 0.3919 | 0.3102 | 0.3463 | 0.7206 | |
|
| No log | 2.0 | 20 | 1.2065 | 0.4497 | 0.3824 | 0.4133 | 0.7573 | |
|
| No log | 3.0 | 30 | 1.0512 | 0.4792 | 0.4305 | 0.4535 | 0.7759 | |
|
| No log | 4.0 | 40 | 0.9780 | 0.5056 | 0.4840 | 0.4945 | 0.8022 | |
|
| No log | 5.0 | 50 | 0.9495 | 0.5098 | 0.4866 | 0.4979 | 0.8050 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
