metadata
license: llama3.1
library_name: transformers
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer
base_model: meta-llama/Llama-3.1-8B
datasets:
- argilla-warehouse/magpie-ultra-v1.0
model-index:
- name: Llama-3.1-8B-MagPie-Ultra
results: []
Llama-3.1-8B-MagPie-Ultra
This model is a fine-tuned version of meta-llama/Llama-3.1-8B on the argilla-warehouse/magpie-ultra-v1.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5915
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5939 | 0.9998 | 1002 | 0.5915 |
Framework versions
- Transformers 4.45.0
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 19.46 |
| IFEval (0-Shot) | 57.57 |
| BBH (3-Shot) | 23.52 |
| MATH Lvl 5 (4-Shot) | 5.36 |
| GPQA (0-shot) | 2.24 |
| MuSR (0-shot) | 4.25 |
| MMLU-PRO (5-shot) | 23.82 |