|
--- |
|
license: apache-2.0 |
|
base_model: tiiuae/falcon-7b |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- spider |
|
model-index: |
|
- name: falcon-7b_spider |
|
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. --> |
|
|
|
# falcon-7b_spider |
|
|
|
This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on the spider dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1837 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 87.5 |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.5561 | 0.11 | 100 | 0.3692 | |
|
| 0.0 | 0.23 | 200 | 0.2534 | |
|
| 0.0628 | 0.34 | 300 | 0.2348 | |
|
| 0.6081 | 0.46 | 400 | 0.2310 | |
|
| 0.0024 | 0.57 | 500 | 0.2218 | |
|
| 0.0136 | 0.69 | 600 | 0.2256 | |
|
| 0.1526 | 0.8 | 700 | 0.2140 | |
|
| 0.1417 | 0.91 | 800 | 0.2158 | |
|
| 0.2736 | 1.03 | 900 | 0.1880 | |
|
| 0.2429 | 1.14 | 1000 | 0.1947 | |
|
| 0.1635 | 1.26 | 1100 | 0.1861 | |
|
| 0.2204 | 1.37 | 1200 | 0.1755 | |
|
| 0.1207 | 1.49 | 1300 | 0.1952 | |
|
| 0.1663 | 1.6 | 1400 | 0.1821 | |
|
| 0.2023 | 1.71 | 1500 | 0.1901 | |
|
| 0.0429 | 1.83 | 1600 | 0.1892 | |
|
| 0.1651 | 1.94 | 1700 | 0.1847 | |
|
| 0.0447 | 2.06 | 1800 | 0.1781 | |
|
| 0.0184 | 2.17 | 1900 | 0.1808 | |
|
| 0.0392 | 2.29 | 2000 | 0.2112 | |
|
| 0.1474 | 2.4 | 2100 | 0.1800 | |
|
| 0.1859 | 2.51 | 2200 | 0.1754 | |
|
| 0.3717 | 2.63 | 2300 | 0.1736 | |
|
| 0.2106 | 2.74 | 2400 | 0.1767 | |
|
| 0.0798 | 2.86 | 2500 | 0.1700 | |
|
| 0.2165 | 2.97 | 2600 | 0.1868 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.0.dev0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
