metadata
base_model: meta-llama/Llama-3.1-8B-Instruct
library_name: peft
license: llama3.1
tags:
- generated_from_trainer
model-index:
- name: Llama-3.1-8B-Instruct-contracts-Finetuning
results: []
Llama-3.1-8B-Instruct-contracts-Finetuning
This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.5752
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: 2.5e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- training_steps: 6000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.0322 | 0.0024 | 500 | 5.8889 |
| 5.9047 | 0.0048 | 1000 | 5.7508 |
| 5.8849 | 0.0073 | 1500 | 5.7206 |
| 5.8508 | 0.0097 | 2000 | 5.6745 |
| 5.7946 | 0.0121 | 2500 | 5.6536 |
| 5.8142 | 0.0145 | 3000 | 5.6447 |
| 5.715 | 0.0170 | 3500 | 5.6192 |
| 5.7378 | 0.0194 | 4000 | 5.6052 |
| 5.702 | 0.0218 | 4500 | 5.5940 |
| 5.6464 | 0.0242 | 5000 | 5.5837 |
| 5.6911 | 0.0266 | 5500 | 5.5782 |
| 5.749 | 0.0291 | 6000 | 5.5752 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.1
- Pytorch 2.4.0+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1