qwen-1.5-0.5b-sft-v1.0
This model is a fine-tuned version of Qwen/Qwen1.5-0.5B on the HuggingFaceH4/deita-6k-v0-sft dataset. It achieves the following results on the evaluation set:
- Loss: 1.2566
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: 16
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3015 | 1.0 | 237 | 1.2711 |
| 1.2352 | 2.0 | 474 | 1.2562 |
| 1.1719 | 3.0 | 711 | 1.2566 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1