metadata
license: apache-2.0
base_model: tiiuae/falcon-7b
tags:
- generated_from_trainer
datasets:
- spider
model-index:
- name: falcon_qlora_sql_r2
results: []
falcon_qlora_sql_r2
This model is a fine-tuned version of tiiuae/falcon-7b on the spider dataset. It achieves the following results on the evaluation set:
- Loss: 0.1735
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 43.7
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2993 | 0.23 | 100 | 0.2863 |
| 0.8003 | 0.46 | 200 | 0.3358 |
| 0.1872 | 0.68 | 300 | 0.2424 |
| 0.1267 | 0.91 | 400 | 0.2362 |
| 0.2214 | 1.14 | 500 | 0.2564 |
| 0.2885 | 1.37 | 600 | 0.2187 |
| 0.1654 | 1.6 | 700 | 0.1988 |
| 0.1633 | 1.83 | 800 | 0.2062 |
| 0.0381 | 2.05 | 900 | 0.1868 |
| 0.0633 | 2.28 | 1000 | 0.1767 |
| 0.163 | 2.51 | 1100 | 0.1861 |
| 0.1718 | 2.74 | 1200 | 0.1875 |
| 0.1743 | 2.97 | 1300 | 0.1854 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3