|
--- |
|
base_model: deepseek-ai/deepseek-math-7b-base |
|
library_name: peft |
|
license: other |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: phi-3-mini-LoRA |
|
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. --> |
|
|
|
# phi-3-mini-LoRA |
|
|
|
This model is a fine-tuned version of [deepseek-ai/deepseek-math-7b-base](https://huggingface.co/deepseek-ai/deepseek-math-7b-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4014 |
|
|
|
## 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: 1 |
|
- eval_batch_size: 1 |
|
- 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: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.4522 | 0.07 | 500 | 0.4533 | |
|
| 0.4512 | 0.14 | 1000 | 0.4301 | |
|
| 0.4386 | 0.21 | 1500 | 0.4199 | |
|
| 0.4268 | 0.28 | 2000 | 0.4144 | |
|
| 0.4167 | 0.35 | 2500 | 0.4104 | |
|
| 0.3955 | 0.42 | 3000 | 0.4092 | |
|
| 0.436 | 0.49 | 3500 | 0.4062 | |
|
| 0.3912 | 0.55 | 4000 | 0.4057 | |
|
| 0.425 | 0.62 | 4500 | 0.4036 | |
|
| 0.4066 | 0.69 | 5000 | 0.4026 | |
|
| 0.3963 | 0.76 | 5500 | 0.4016 | |
|
| 0.3862 | 0.83 | 6000 | 0.4019 | |
|
| 0.3902 | 0.9 | 6500 | 0.4015 | |
|
| 0.4364 | 0.97 | 7000 | 0.4014 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.8.2 |
|
- Transformers 4.38.0 |
|
- Pytorch 2.2.1 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.2 |
