Llama Summarization
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the scitldr dataset. It achieves the following results on the evaluation set:
- Loss: 2.1108
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: 0.0002
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.0965 | 0.25 | 500 | 2.1496 |
| 2.0523 | 0.5 | 1000 | 2.1275 |
| 2.0824 | 0.75 | 1500 | 2.1108 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 7
Inference API (serverless) does not yet support peft models for this pipeline type.
Model tree for pkbiswas/Llama-2-7b-Summarization-QLoRa
Base model
meta-llama/Llama-2-7b-hf