metadata
library_name: peft
license: mit
base_model: microsoft/Phi-4-mini-instruct
tags:
- generated_from_trainer
model-index:
- name: phi4-lora-xaji0y6d-1742307792
results: []
phi4-lora-xaji0y6d-1742307792
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: 17.2192
- Perplexity: 30074056.0078
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-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 |
|---|---|---|---|---|
| 5.712 | 0.0664 | 5 | 17.2155 | 29964122.9417 |
| 6.9157 | 0.1329 | 10 | 17.2185 | 30054100.7563 |
| 6.8786 | 0.1993 | 15 | 17.2190 | 30069467.4211 |
| 6.785 | 0.2658 | 20 | 17.2192 | 30074056.0078 |
Framework versions
- PEFT 0.14.0
- Transformers 4.48.2
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0