metadata
license: other
base_model: facebook/opt-iml-1.3b
tags:
- generated_from_trainer
model-index:
- name: sql-OPT-IML-Spider
results: []
sql-OPT-IML-Spider
This model is a fine-tuned version of facebook/opt-iml-1.3b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6240
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 200
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.4167 | 2.76 | 20 | 3.3131 |
| 2.822 | 5.52 | 40 | 2.6244 |
| 1.8781 | 8.28 | 60 | 1.7491 |
| 1.1619 | 11.03 | 80 | 1.3205 |
| 0.7079 | 13.79 | 100 | 1.0339 |
| 0.4644 | 16.55 | 120 | 0.8472 |
| 0.3597 | 19.31 | 140 | 0.7265 |
| 0.3092 | 22.07 | 160 | 0.6580 |
| 0.2789 | 24.83 | 180 | 0.6310 |
| 0.2646 | 27.59 | 200 | 0.6240 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0