sunsuimiao-v1
This model is a fine-tuned version of /data/X-D-Lab/med-llava/llama3/llama3-chinese-chat/Llama3-8B-Chinese-Chat on the sunsimiao35w dataset. It achieves the following results on the evaluation set:
- Loss: 1.1195
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
- trainbatchsize: 4
- evalbatchsize: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradientaccumulationsteps: 6
- totaltrainbatch_size: 96
- totalevalbatch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lrschedulertype: cosine
- lrschedulerwarmup_steps: 0.1
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1332 | 0.7619 | 2500 | 1.1341 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.0+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1
评论