qlora-Llama-2-7b-hf-TweetSumm
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the dialogstudio dataset. It achieves the following results on the evaluation set:
- Loss: 1.9484
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8058 | 1.0 | 55 | 1.8689 |
| 1.6983 | 2.0 | 110 | 1.8402 |
| 1.5008 | 3.0 | 165 | 1.8654 |
| 1.2814 | 4.0 | 220 | 1.9171 |
| 1.3227 | 5.0 | 275 | 1.9484 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
Model tree for vineetsharma/qlora-adapter-Llama-2-7b-hf-TweetSumm
Base model
meta-llama/Llama-2-7b-hf