qwen2.5-0.5b-sft-25-2
This model is a fine-tuned version of Qwen/Qwen2.5-0.5B on the hZzy/SFT_new_mix dataset. It achieves the following results on the evaluation set:
- Loss: 2.4173
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: 5e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 3
- gradient_accumulation_steps: 8
- total_train_batch_size: 192
- total_eval_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.4072 | 0.9982 | 483 | 2.4292 |
| 2.3391 | 1.9964 | 966 | 2.4173 |
Framework versions
- Transformers 4.42.0
- Pytorch 2.3.0+cu121
- Datasets 3.2.0
- Tokenizers 0.19.1
- Downloads last month
- 44
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.