qwen3-finetuned-diary
This model is a fine-tuned version of Qwen/Qwen3.5-0.8B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.9201
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- 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 | 5 | 4.4457 |
| 4.4674 | 2.0 | 10 | 4.3243 |
| 4.4674 | 3.0 | 15 | 4.3421 |
| 3.4129 | 4.0 | 20 | 4.4691 |
| 3.4129 | 5.0 | 25 | 4.5758 |
| 2.7626 | 6.0 | 30 | 4.7098 |
| 2.7626 | 7.0 | 35 | 4.8079 |
| 2.3554 | 8.0 | 40 | 4.8748 |
| 2.3554 | 9.0 | 45 | 4.9105 |
| 2.2178 | 10.0 | 50 | 4.9201 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.13.0+cu130
- Datasets 5.0.1
- Tokenizers 0.23.1