Qwen3-0.6B_10ep_lora_v0
This model is a fine-tuned version of Qwen/Qwen3-0.6B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0171
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: 0.0002
- train_batch_size: 2
- eval_batch_size: 2
- seed: 3407
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- 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
- lr_scheduler_warmup_steps: 20
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0048 | 1.0 | 388 | 0.0191 |
| 0.005 | 2.0 | 776 | 0.0152 |
| 0.004 | 3.0 | 1164 | 0.0144 |
| 0.0049 | 4.0 | 1552 | 0.0126 |
| 0.0033 | 5.0 | 1940 | 0.0151 |
| 0.0021 | 6.0 | 2328 | 0.0142 |
| 0.0032 | 7.0 | 2716 | 0.0127 |
| 0.0036 | 8.0 | 3104 | 0.0145 |
| 0.0019 | 9.0 | 3492 | 0.0157 |
| 0.002 | 10.0 | 3880 | 0.0171 |
Framework versions
- PEFT 0.18.0
- Transformers 4.57.3
- Pytorch 2.4.0
- Datasets 4.4.1
- Tokenizers 0.22.1
- Downloads last month
- 1