metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: distilbert-base-uncased
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-lora-text-classification
results: []
distilbert-base-uncased-lora-text-classification
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0117
- Accuracy: {'accuracy': 0.889}
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: 4
- eval_batch_size: 4
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 250 | 0.4717 | {'accuracy': 0.859} |
| 0.4287 | 2.0 | 500 | 0.4378 | {'accuracy': 0.876} |
| 0.4287 | 3.0 | 750 | 0.5879 | {'accuracy': 0.87} |
| 0.1987 | 4.0 | 1000 | 0.6395 | {'accuracy': 0.885} |
| 0.1987 | 5.0 | 1250 | 0.7766 | {'accuracy': 0.885} |
| 0.0524 | 6.0 | 1500 | 0.8409 | {'accuracy': 0.891} |
| 0.0524 | 7.0 | 1750 | 0.9005 | {'accuracy': 0.895} |
| 0.0208 | 8.0 | 2000 | 0.9932 | {'accuracy': 0.886} |
| 0.0208 | 9.0 | 2250 | 1.0083 | {'accuracy': 0.889} |
| 0.0044 | 10.0 | 2500 | 1.0117 | {'accuracy': 0.889} |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.0
- Datasets 2.18.0
- Tokenizers 0.15.2