|
|
--- |
|
|
license: apache-2.0 |
|
|
library_name: peft |
|
|
tags: |
|
|
- trl |
|
|
- sft |
|
|
- generated_from_trainer |
|
|
base_model: Deci/DeciLM-7B |
|
|
datasets: |
|
|
- generator |
|
|
model-index: |
|
|
- name: deci7bit-lora-sql |
|
|
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. --> |
|
|
|
|
|
# deci7bit-lora-sql |
|
|
|
|
|
This model is a fine-tuned version of [Deci/DeciLM-7B](https://huggingface.co/Deci/DeciLM-7B) on the generator dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.3593 |
|
|
|
|
|
## 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: 0.0003 |
|
|
- train_batch_size: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 1399 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 32 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_steps: 100 |
|
|
- training_steps: 500 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 0.7841 | 0.06 | 20 | 0.5204 | |
|
|
| 0.4837 | 0.11 | 40 | 0.4376 | |
|
|
| 0.4325 | 0.17 | 60 | 0.4122 | |
|
|
| 0.4112 | 0.23 | 80 | 0.4029 | |
|
|
| 0.4028 | 0.28 | 100 | 0.3925 | |
|
|
| 0.3958 | 0.34 | 120 | 0.3855 | |
|
|
| 0.3895 | 0.4 | 140 | 0.3816 | |
|
|
| 0.3818 | 0.45 | 160 | 0.3784 | |
|
|
| 0.3753 | 0.51 | 180 | 0.3756 | |
|
|
| 0.3722 | 0.56 | 200 | 0.3734 | |
|
|
| 0.3687 | 0.62 | 220 | 0.3702 | |
|
|
| 0.3678 | 0.68 | 240 | 0.3665 | |
|
|
| 0.3636 | 0.73 | 260 | 0.3627 | |
|
|
| 0.3582 | 0.79 | 280 | 0.3580 | |
|
|
| 0.3594 | 0.85 | 300 | 0.3593 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.9.0 |
|
|
- Transformers 4.38.2 |
|
|
- Pytorch 2.1.0+cu118 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.15.2 |
