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: 0.9904
- Accuracy: {'accuracy': 0.899}
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 | 0.5709 | {'accuracy': 0.837} |
0.4386 | 2.0 | 500 | 0.4510 | {'accuracy': 0.871} |
0.4386 | 3.0 | 750 | 0.6571 | {'accuracy': 0.887} |
0.1891 | 4.0 | 1000 | 0.6197 | {'accuracy': 0.894} |
0.1891 | 5.0 | 1250 | 0.7688 | {'accuracy': 0.897} |
0.0683 | 6.0 | 1500 | 0.8231 | {'accuracy': 0.892} |
0.0683 | 7.0 | 1750 | 0.8949 | {'accuracy': 0.901} |
0.0136 | 8.0 | 2000 | 0.9553 | {'accuracy': 0.896} |
0.0136 | 9.0 | 2250 | 1.0202 | {'accuracy': 0.892} |
0.0067 | 10.0 | 2500 | 0.9904 | {'accuracy': 0.899} |
Framework versions
- PEFT 0.9.0
- Transformers 4.39.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.15.2
- Downloads last month
- 1
Model tree for MomoSen/distilbert-base-uncased-lora-text-classification
Base model
distilbert/distilbert-base-uncased