metadata
base_model: meta-llama/Llama-2-7b-hf
library_name: peft
license: llama2
tags:
- generated_from_trainer
model-index:
- name: outputs
results: []
outputs
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: 1.3676
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: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.2385 | 0.0134 | 10 | 2.4588 |
| 1.9987 | 0.0267 | 20 | 1.7020 |
| 1.3144 | 0.0401 | 30 | 1.5073 |
| 1.1871 | 0.0535 | 40 | 1.4545 |
| 1.1943 | 0.0668 | 50 | 1.4239 |
| 1.2441 | 0.0802 | 60 | 1.4004 |
| 1.3645 | 0.0936 | 70 | 1.3822 |
| 1.2 | 0.1069 | 80 | 1.3748 |
| 1.1308 | 0.1203 | 90 | 1.3696 |
| 1.1587 | 0.1336 | 100 | 1.3676 |
Framework versions
- PEFT 0.12.1.dev0
- Transformers 4.45.0.dev0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1