llama2_instruct_generation
This model is a fine-tuned version of NousResearch/Llama-2-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7527
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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 80
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9475 | 0.0 | 20 | 1.8132 |
| 1.7993 | 0.0 | 40 | 1.7797 |
| 1.8766 | 0.0 | 60 | 1.7642 |
| 1.849 | 0.01 | 80 | 1.7527 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
Model tree for kamakani/llama2_instruct_generation
Base model
NousResearch/Llama-2-7b-hf