|
--- |
|
library_name: peft |
|
license: apache-2.0 |
|
base_model: distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: distilbert-base-uncased-lora-text-classification |
|
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. --> |
|
|
|
# distilbert-base-uncased-lora-text-classification |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1819 |
|
- Accuracy: {'accuracy': 0.897} |
|
|
|
## 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: 0.001 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 4 |
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- num_epochs: 15 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------------------:| |
|
| No log | 1.0 | 250 | 0.5093 | {'accuracy': 0.862} | |
|
| 0.4169 | 2.0 | 500 | 0.5829 | {'accuracy': 0.849} | |
|
| 0.4169 | 3.0 | 750 | 0.6257 | {'accuracy': 0.885} | |
|
| 0.1958 | 4.0 | 1000 | 0.7867 | {'accuracy': 0.878} | |
|
| 0.1958 | 5.0 | 1250 | 0.7045 | {'accuracy': 0.886} | |
|
| 0.0879 | 6.0 | 1500 | 0.8638 | {'accuracy': 0.882} | |
|
| 0.0879 | 7.0 | 1750 | 0.9795 | {'accuracy': 0.876} | |
|
| 0.024 | 8.0 | 2000 | 1.2233 | {'accuracy': 0.886} | |
|
| 0.024 | 9.0 | 2250 | 1.2044 | {'accuracy': 0.884} | |
|
| 0.014 | 10.0 | 2500 | 1.1903 | {'accuracy': 0.88} | |
|
| 0.014 | 11.0 | 2750 | 1.1673 | {'accuracy': 0.89} | |
|
| 0.0136 | 12.0 | 3000 | 1.1105 | {'accuracy': 0.895} | |
|
| 0.0136 | 13.0 | 3250 | 1.1652 | {'accuracy': 0.893} | |
|
| 0.0005 | 14.0 | 3500 | 1.1656 | {'accuracy': 0.894} | |
|
| 0.0005 | 15.0 | 3750 | 1.1819 | {'accuracy': 0.897} | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.14.0 |
|
- Transformers 4.48.3 |
|
- Pytorch 2.6.0+cu124 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.21.0 |
