Qwen3-4B-Base-hatebr
This model is a fine-tuned version of Qwen/Qwen3-4B-Base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4172
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 |
|---|---|---|---|
| 1.0726 | 1.0 | 1120 | 1.0040 |
| 0.8636 | 2.0 | 2240 | 1.0105 |
| 0.6744 | 3.0 | 3360 | 1.0873 |
| 0.5317 | 4.0 | 4480 | 1.1658 |
| 0.4498 | 5.0 | 5600 | 1.2691 |
| 0.3701 | 6.0 | 6720 | 1.3453 |
| 0.319 | 7.0 | 7840 | 1.3971 |
| 0.334 | 8.0 | 8960 | 1.4172 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- -
Model tree for g-assismoraes/Qwen3-4B-Base-hatebr
Base model
Qwen/Qwen3-4B-Base