jl_qa_model
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6818
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 250 | 3.1817 |
| 3.3291 | 2.0 | 500 | 2.2826 |
| 3.3291 | 3.0 | 750 | 1.8554 |
| 1.6879 | 4.0 | 1000 | 1.6810 |
| 1.6879 | 5.0 | 1250 | 1.6160 |
| 1.1445 | 6.0 | 1500 | 1.6017 |
| 1.1445 | 7.0 | 1750 | 1.6483 |
| 0.9086 | 8.0 | 2000 | 1.6421 |
| 0.9086 | 9.0 | 2250 | 1.6738 |
| 0.7701 | 10.0 | 2500 | 1.6818 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1
- Downloads last month
- 9
Model tree for freongas/jl_qa_model
Base model
distilbert/distilbert-base-uncased