metadata
base_model: microsoft/Phi-3.5-mini-instruct
library_name: peft
license: mit
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Phi-3.5-mini-instruct-qlora
results: []
Phi-3.5-mini-instruct-qlora
This model is a fine-tuned version of microsoft/Phi-3.5-mini-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8569
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 0
- 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: 0.01
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6558 | 0.3333 | 10 | 1.4457 |
| 1.2244 | 0.6667 | 20 | 1.1363 |
| 1.0198 | 1.0 | 30 | 1.0057 |
| 0.92 | 1.3333 | 40 | 0.9328 |
| 0.8365 | 1.6667 | 50 | 0.8991 |
| 0.7908 | 2.0 | 60 | 0.8744 |
| 0.7432 | 2.3333 | 70 | 0.8794 |
| 0.7421 | 2.6667 | 80 | 0.8692 |
| 0.739 | 3.0 | 90 | 0.8599 |
| 0.6996 | 3.3333 | 100 | 0.8603 |
| 0.7016 | 3.6667 | 110 | 0.8560 |
| 0.7205 | 4.0 | 120 | 0.8569 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.4.0
- Datasets 3.0.2
- Tokenizers 0.20.0