metadata
base_model: distilbert-base-uncased
library_name: peft
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
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: 0.9788
- Accuracy: {'accuracy': 0.887}
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 | 0.3110 | {'accuracy': 0.895} |
| 0.4325 | 2.0 | 500 | 0.4438 | {'accuracy': 0.883} |
| 0.4325 | 3.0 | 750 | 0.6263 | {'accuracy': 0.882} |
| 0.1901 | 4.0 | 1000 | 0.6301 | {'accuracy': 0.888} |
| 0.1901 | 5.0 | 1250 | 0.7492 | {'accuracy': 0.888} |
| 0.0615 | 6.0 | 1500 | 0.8813 | {'accuracy': 0.894} |
| 0.0615 | 7.0 | 1750 | 1.0208 | {'accuracy': 0.889} |
| 0.0231 | 8.0 | 2000 | 0.9440 | {'accuracy': 0.886} |
| 0.0231 | 9.0 | 2250 | 0.9579 | {'accuracy': 0.887} |
| 0.0074 | 10.0 | 2500 | 0.9788 | {'accuracy': 0.887} |
Framework versions
- PEFT 0.12.0
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1