|
--- |
|
license: gemma |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: google/gemma-7b-it |
|
model-index: |
|
- name: spider-gemma7b-it |
|
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. --> |
|
|
|
# spider-gemma7b-it |
|
|
|
This model is a fine-tuned version of [google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1600 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant |
|
- lr_scheduler_warmup_ratio: 0.03 |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.4778 | 0.16 | 100 | 0.4999 | |
|
| 0.2964 | 0.33 | 200 | 0.3364 | |
|
| 0.2383 | 0.49 | 300 | 0.2924 | |
|
| 0.2077 | 0.65 | 400 | 0.2551 | |
|
| 0.1909 | 0.82 | 500 | 0.2283 | |
|
| 0.1831 | 0.98 | 600 | 0.2188 | |
|
| 0.1595 | 1.14 | 700 | 0.1855 | |
|
| 0.1566 | 1.31 | 800 | 0.1779 | |
|
| 0.1581 | 1.47 | 900 | 0.1706 | |
|
| 0.1507 | 1.63 | 1000 | 0.1679 | |
|
| 0.1515 | 1.8 | 1100 | 0.1689 | |
|
| 0.1514 | 1.96 | 1200 | 0.1600 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.8.2 |
|
- Transformers 4.38.0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.2 |
