full-finetune-llama7b-chat-asst
This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9478
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-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 64
- total_train_batch_size: 64
- total_eval_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9093 | 0.31 | 52 | 0.8238 |
| 0.5019 | 1.31 | 104 | 0.9478 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.1.0.dev20230809
- Datasets 2.14.4
- Tokenizers 0.13.3