metadata
library_name: peft
license: mit
base_model: microsoft/Phi-4-mini-instruct
tags:
- generated_from_trainer
model-index:
- name: phi4-lora-xaji0y6d-1742299723
results: []
phi4-lora-xaji0y6d-1742299723
This model is a fine-tuned version of microsoft/Phi-4-mini-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 25.3528
- Perplexity: 102470071639.741
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Use adamw_hf with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Perplexity |
|---|---|---|---|---|
| 2.0923 | 1.3195 | 50 | 19.9230 | 449198544.2945 |
| 0.0841 | 2.6389 | 100 | 24.5671 | 46702980507.7979 |
| 0.0374 | 3.9584 | 150 | 25.3528 | 102470071639.741 |
Framework versions
- PEFT 0.14.0
- Transformers 4.48.2
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0