metadata
license: mit
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: microsoft/phi-1_5
model-index:
- name: phi-1_5-finetuned-question-generation
results: []
phi-1_5-finetuned-question-generation
This model is a fine-tuned version of microsoft/phi-1_5 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9079
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: 8
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.0206 | 0.28 | 100 | 2.8708 |
| 2.8007 | 0.56 | 200 | 2.6294 |
| 2.5551 | 0.85 | 300 | 2.4552 |
| 2.3554 | 1.13 | 400 | 2.2903 |
| 2.2233 | 1.41 | 500 | 2.1771 |
| 2.1114 | 1.69 | 600 | 2.0850 |
| 2.0211 | 1.97 | 700 | 2.0163 |
| 1.8995 | 2.25 | 800 | 1.9635 |
| 1.835 | 2.54 | 900 | 1.9226 |
| 1.81 | 2.82 | 1000 | 1.9079 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2