metadata
library_name: peft
license: other
base_model: microsoft/Phi-3-mini-4k-instruct
tags:
- llama-factory
- lora
- generated_from_trainer
model-index:
- name: lora
results: []
lora
This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on the flock_task4_tranning dataset. It achieves the following results on the evaluation set:
- Loss: 1.1499
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: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- total_eval_batch_size: 2
- optimizer: Use adamw_torch 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: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0681 | 0.0501 | 50 | 1.2795 |
| 1.0394 | 0.1002 | 100 | 1.2304 |
| 0.9251 | 0.1502 | 150 | 1.2384 |
| 1.0063 | 0.2003 | 200 | 1.2121 |
| 0.9905 | 0.2504 | 250 | 1.2024 |
| 0.9761 | 0.3005 | 300 | 1.1887 |
| 0.8606 | 0.3505 | 350 | 1.1863 |
| 0.9137 | 0.4006 | 400 | 1.1841 |
| 0.9647 | 0.4507 | 450 | 1.1794 |
| 0.9091 | 0.5008 | 500 | 1.1720 |
| 0.8968 | 0.5508 | 550 | 1.1639 |
| 0.9193 | 0.6009 | 600 | 1.1597 |
| 0.8827 | 0.6510 | 650 | 1.1622 |
| 0.895 | 0.7011 | 700 | 1.1525 |
| 0.9329 | 0.7511 | 750 | 1.1563 |
| 0.8991 | 0.8012 | 800 | 1.1525 |
| 0.8639 | 0.8513 | 850 | 1.1508 |
| 0.8723 | 0.9014 | 900 | 1.1498 |
| 0.9658 | 0.9514 | 950 | 1.1497 |
Framework versions
- PEFT 0.12.0
- Transformers 4.48.3
- Pytorch 2.6.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0