results_lora_qkv
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: 0.2122
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2603 | 1.0 | 3750 | 0.2527 |
| 0.2341 | 2.0 | 7500 | 0.2274 |
| 0.2238 | 3.0 | 11250 | 0.2183 |
| 0.2125 | 4.0 | 15000 | 0.2137 |
| 0.2048 | 5.0 | 18750 | 0.2122 |
Framework versions
- PEFT 0.13.2
- Transformers 4.45.2
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 1
Model tree for asm3515/distilbert-agnews-lora
Base model
distilbert/distilbert-base-uncased