llama3.1-full-girlfriend-v2
This model is a fine-tuned version of /home/llama/zxl_2024/model/Meta-Llama-3.1-8B-Instruct on the output_girl_all dataset. It achieves the following results on the evaluation set:
- Loss: 1.0679
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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 64
- 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: 0.06
- lr_scheduler_warmup_steps: 20
- num_epochs: 6.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6434 | 5.7143 | 200 | 1.0674 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 7
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.