prism-v0-pretrain-1
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: 6.2010
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.9787 | 0.2803 | 1000 | 6.7248 |
| 6.6153 | 0.5606 | 2000 | 6.4486 |
| 6.6127 | 0.8410 | 3000 | 6.3316 |
| 6.1481 | 1.1211 | 4000 | 6.2661 |
| 6.1624 | 1.4014 | 5000 | 6.2257 |
| 6.3045 | 1.6817 | 6000 | 6.2059 |
| 6.4292 | 1.9621 | 7000 | 6.2010 |
Framework versions
- Transformers 4.55.2
- Pytorch 2.4.0a0+07cecf4168.nv24.05
- Datasets 4.0.0
- Tokenizers 0.21.4
- Downloads last month
- 1