metadata
library_name: peft
license: mit
base_model: microsoft/Phi-4-mini-instruct
tags:
- generated_from_trainer
model-index:
- name: phi4-lora-xaji0y6d-1742306687
results: []
phi4-lora-xaji0y6d-1742306687
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: 17.2338
- Perplexity: 30518534.8524
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: 3e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- 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: 0.15
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Perplexity |
|---|---|---|---|---|
| 5.7359 | 0.0664 | 5 | 17.2156 | 29967094.9946 |
| 6.77 | 0.1329 | 10 | 17.2293 | 30381179.4484 |
| 6.5826 | 0.1993 | 15 | 17.2174 | 30019325.4366 |
| 6.2712 | 0.2658 | 20 | 17.2338 | 30518534.8524 |
Framework versions
- PEFT 0.14.0
- Transformers 4.48.2
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0