metadata
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: []
phi-3-mini-LoRA
This model is a fine-tuned version of 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