metadata
license: llama3.1
library_name: peft
tags:
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
model-index:
- name: flippa-v6
results: []
flippa-v6
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5640
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: 1e-05
- train_batch_size: 3
- eval_batch_size: 3
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9009 | 1.0 | 500 | 1.9374 |
| 1.6797 | 2.0 | 1000 | 1.7561 |
| 1.5561 | 3.0 | 1500 | 1.6929 |
| 1.5276 | 4.0 | 2000 | 1.6550 |
| 1.5116 | 5.0 | 2500 | 1.6310 |
| 1.465 | 6.0 | 3000 | 1.6144 |
| 1.4707 | 7.0 | 3500 | 1.6029 |
| 1.4412 | 8.0 | 4000 | 1.5939 |
| 1.4494 | 9.0 | 4500 | 1.5857 |
| 1.4433 | 10.0 | 5000 | 1.5791 |
| 1.4348 | 11.0 | 5500 | 1.5734 |
| 1.4185 | 12.0 | 6000 | 1.5696 |
| 1.404 | 13.0 | 6500 | 1.5665 |
| 1.4087 | 14.0 | 7000 | 1.5648 |
| 1.4268 | 15.0 | 7500 | 1.5640 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 20.55 |
| IFEval (0-Shot) | 34.39 |
| BBH (3-Shot) | 29.99 |
| MATH Lvl 5 (4-Shot) | 12.69 |
| GPQA (0-shot) | 5.70 |
| MuSR (0-shot) | 10.88 |
| MMLU-PRO (5-shot) | 29.64 |