metadata
base_model: meta-llama/Llama-2-7b-hf
tags:
- generated_from_trainer
model-index:
- name: goatV10-QLORA
results: []
goatV10-QLORA
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3860
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4692 | 0.16 | 200 | 0.4549 |
| 0.4234 | 0.31 | 400 | 0.4144 |
| 0.3943 | 0.47 | 600 | 0.4011 |
| 0.4079 | 0.63 | 800 | 0.3922 |
| 0.4171 | 0.79 | 1000 | 0.3877 |
| 0.3983 | 0.94 | 1200 | 0.3861 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.0
- Datasets 2.12.0
- Tokenizers 0.13.3