metadata
base_model: microsoft/Phi-3-mini-4k-instruct
library_name: peft
license: mit
tags:
- generated_from_trainer
model-index:
- name: phi3-mini-4k-adapter_3
results: []
phi3-mini-4k-adapter_3
This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1650
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: 0.0002
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- training_steps: 200
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 9.3301 | 0.9091 | 10 | 7.3651 |
| 0.24 | 1.8182 | 20 | 0.2340 |
| 0.1173 | 2.7273 | 30 | 0.1572 |
| 0.0836 | 3.6364 | 40 | 0.1480 |
| 0.0681 | 4.5455 | 50 | 0.1554 |
| 0.0607 | 5.4545 | 60 | 0.1496 |
| 0.0555 | 6.3636 | 70 | 0.1650 |
Framework versions
- PEFT 0.11.1
- Transformers 4.43.1
- Pytorch 2.4.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1