metadata
license: llama3
tags:
- alignment-handbook
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B-Instruct
datasets:
- princeton-nlp/llama3-ultrafeedback
model-index:
- name: llama-3-8b-instruct-simpo
results: []
llama-3-8b-instruct-simpo
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the princeton-nlp/llama3-ultrafeedback dataset.
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-06
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- total_eval_batch_size: 64
- 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
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+rocm6.0
- Datasets 2.19.2
- Tokenizers 0.19.1
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 24.71 |
| IFEval (0-Shot) | 73.47 |
| BBH (3-Shot) | 28.23 |
| MATH Lvl 5 (4-Shot) | 7.10 |
| GPQA (0-shot) | 5.37 |
| MuSR (0-shot) | 3.74 |
| MMLU-PRO (5-shot) | 30.37 |