metadata
license: other
base_model: microsoft/phi-1_5
tags:
- generated_from_trainer
model-index:
- name: phi-1_5-finetuned-SQL
results: []
phi-1_5-finetuned-SQL
This model is a fine-tuned version of microsoft/phi-1_5 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4282
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 1500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.4485 | 0.4 | 100 | 2.0478 |
| 2.0521 | 0.8 | 200 | 1.9223 |
| 1.9626 | 1.2 | 300 | 1.8386 |
| 1.8707 | 1.6 | 400 | 1.7702 |
| 1.79 | 2.0 | 500 | 1.7149 |
| 1.7197 | 2.4 | 600 | 1.6567 |
| 1.6904 | 2.8 | 700 | 1.6055 |
| 1.6379 | 3.2 | 800 | 1.5583 |
| 1.5794 | 3.6 | 900 | 1.5267 |
| 1.5977 | 4.0 | 1000 | 1.4928 |
| 1.4773 | 4.4 | 1100 | 1.4638 |
| 1.5185 | 4.8 | 1200 | 1.4446 |
| 1.4476 | 5.2 | 1300 | 1.4337 |
| 1.4321 | 5.6 | 1400 | 1.4287 |
| 1.4393 | 6.0 | 1500 | 1.4282 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1