Qwen3-1.7B-Base-hatebr
This model is a fine-tuned version of Qwen/Qwen3-1.7B-Base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1372
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1335 | 1.0 | 1120 | 1.0516 |
| 1.0071 | 2.0 | 2240 | 1.0458 |
| 0.9027 | 3.0 | 3360 | 1.0606 |
| 0.8604 | 4.0 | 4480 | 1.0885 |
| 0.8579 | 5.0 | 5600 | 1.1040 |
| 0.8267 | 6.0 | 6720 | 1.1251 |
| 0.7888 | 7.0 | 7840 | 1.1319 |
| 0.829 | 8.0 | 8960 | 1.1372 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 2
Model tree for g-assismoraes/Qwen3-1.7B-Base-hatebr
Base model
Qwen/Qwen3-1.7B-Base