|
--- |
|
base_model: bigcode/starencoder |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: starencoder-vd-25-75 |
|
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. --> |
|
|
|
# starencoder-vd-25-75 |
|
|
|
This model is a fine-tuned version of [bigcode/starencoder](https://huggingface.co/bigcode/starencoder) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7599 |
|
- Accuracy: 0.7019 |
|
- Precision: 0.7660 |
|
- Recall: 0.5883 |
|
- F1: 0.6655 |
|
- Roc Auc: 0.7028 |
|
|
|
## 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: 9e-06 |
|
- train_batch_size: 45 |
|
- eval_batch_size: 45 |
|
- seed: 420 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Roc Auc | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-------:| |
|
| 0.6213 | 1.0 | 551 | 0.5820 | 0.6628 | 0.6816 | 0.6212 | 0.6500 | 0.6631 | |
|
| 0.5585 | 2.0 | 1102 | 0.5802 | 0.6690 | 0.7861 | 0.4715 | 0.5895 | 0.6706 | |
|
| 0.5109 | 3.0 | 1653 | 0.5687 | 0.6886 | 0.7681 | 0.5474 | 0.6393 | 0.6897 | |
|
| 0.4645 | 4.0 | 2204 | 0.5875 | 0.6973 | 0.7742 | 0.5640 | 0.6526 | 0.6984 | |
|
| 0.4161 | 5.0 | 2755 | 0.5819 | 0.7097 | 0.7425 | 0.6491 | 0.6926 | 0.7101 | |
|
| 0.3756 | 6.0 | 3306 | 0.6319 | 0.7058 | 0.7451 | 0.6327 | 0.6843 | 0.7064 | |
|
| 0.3451 | 7.0 | 3857 | 0.6542 | 0.7025 | 0.7358 | 0.6394 | 0.6842 | 0.7030 | |
|
| 0.3144 | 8.0 | 4408 | 0.7204 | 0.7017 | 0.7607 | 0.5955 | 0.6680 | 0.7025 | |
|
| 0.2978 | 9.0 | 4959 | 0.7168 | 0.7032 | 0.7524 | 0.6130 | 0.6756 | 0.7040 | |
|
| 0.2757 | 10.0 | 5510 | 0.7599 | 0.7019 | 0.7660 | 0.5883 | 0.6655 | 0.7028 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.1.0.dev20230605+cu121 |
|
- Datasets 2.14.0 |
|
- Tokenizers 0.13.3 |
|
|
