Qwen3-4B-SFT-science-1e-5
This model is a fine-tuned version of Qwen/Qwen3-4B on the dolci_science_train dataset. It achieves the following results on the evaluation set:
- Loss: 0.6778
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: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- total_eval_batch_size: 8
- 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: cosine
- lr_scheduler_warmup_steps: 0.05
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8065 | 0.2985 | 230 | 0.7250 |
| 0.6763 | 0.5969 | 460 | 0.7040 |
| 0.7030 | 0.8954 | 690 | 0.6914 |
| 0.6122 | 1.1933 | 920 | 0.6877 |
| 0.6361 | 1.4918 | 1150 | 0.6827 |
| 0.6499 | 1.7903 | 1380 | 0.6778 |
| 0.5879 | 2.0882 | 1610 | 0.6838 |
| 0.5390 | 2.3867 | 1840 | 0.6826 |
| 0.6058 | 2.6852 | 2070 | 0.6820 |
| 0.6097 | 2.9836 | 2300 | 0.6816 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2