|
--- |
|
base_model: microsoft/Phi-3-mini-4k-instruct |
|
library_name: peft |
|
license: mit |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: question-generator |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# question-generator |
|
|
|
This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.4475 |
|
|
|
## 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: 0.0005 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.8852 | 0.08 | 50 | 1.7072 | |
|
| 1.6036 | 0.16 | 100 | 1.4856 | |
|
| 1.5186 | 0.24 | 150 | 1.4662 | |
|
| 1.4822 | 0.32 | 200 | 1.4603 | |
|
| 1.5035 | 0.4 | 250 | 1.4578 | |
|
| 1.4813 | 0.48 | 300 | 1.4558 | |
|
| 1.4878 | 0.56 | 350 | 1.4534 | |
|
| 1.4765 | 0.64 | 400 | 1.4523 | |
|
| 1.4803 | 0.72 | 450 | 1.4485 | |
|
| 1.4925 | 0.8 | 500 | 1.4478 | |
|
| 1.49 | 0.88 | 550 | 1.4467 | |
|
| 1.4888 | 0.96 | 600 | 1.4461 | |
|
| 1.4732 | 1.04 | 650 | 1.4470 | |
|
| 1.4677 | 1.12 | 700 | 1.4476 | |
|
| 1.4402 | 1.2 | 750 | 1.4475 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.42.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
