Phi-3-mini-4k-instruct
This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on the LangGPT_community, the LangGPT_alpaca and the LangGPT_seed datasets.
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 5.0
Training results
Framework versions
- PEFT 0.10.0
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 25.55 |
| IFEval (0-Shot) | 50.21 |
| BBH (3-Shot) | 36.61 |
| MATH Lvl 5 (4-Shot) | 13.14 |
| GPQA (0-shot) | 10.51 |
| MuSR (0-shot) | 9.65 |
| MMLU-PRO (5-shot) | 33.17 |
- Downloads last month
- 10
Model tree for sci-m-wang/Phi-3-mini-4k-instruct-sa-v0.1
Base model
microsoft/Phi-3-mini-4k-instruct