|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: google/flan-t5-xl |
|
model-index: |
|
- name: flan-t5-xl-spider-dict_qpl-20240304-v3 |
|
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. --> |
|
|
|
# flan-t5-xl-spider-dict_qpl-20240304-v3 |
|
|
|
This model is a fine-tuned version of [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Execution Accuracy: 67.9884 |
|
- Loss: 0.0904 |
|
|
|
## 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: 1 |
|
- eval_batch_size: 8 |
|
- seed: 1 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 16 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Execution Accuracy | Validation Loss | |
|
|:-------------:|:-----:|:------:|:------------------:|:---------------:| |
|
| 0.068 | 1.0 | 6555 | 39.4584 | 0.0767 | |
|
| 0.0432 | 2.0 | 13110 | 52.9981 | 0.0608 | |
|
| 0.033 | 3.0 | 19665 | 60.3482 | 0.0612 | |
|
| 0.0297 | 4.0 | 26220 | 62.8627 | 0.0589 | |
|
| 0.0213 | 5.0 | 32775 | 64.1199 | 0.0605 | |
|
| 0.0188 | 6.0 | 39330 | 64.3133 | 0.0619 | |
|
| 0.0166 | 7.0 | 45885 | 66.441 | 0.0611 | |
|
| 0.0162 | 8.0 | 52440 | 65.8607 | 0.0669 | |
|
| 0.0109 | 9.0 | 58995 | 68.9555 | 0.0666 | |
|
| 0.0101 | 10.0 | 65550 | 68.1818 | 0.0736 | |
|
| 0.0085 | 11.0 | 72105 | 68.0851 | 0.0764 | |
|
| 0.0069 | 12.0 | 78660 | 69.0522 | 0.0801 | |
|
| 0.0068 | 13.0 | 85215 | 69.2456 | 0.0884 | |
|
| 0.0052 | 14.0 | 91770 | 70.793 | 0.0883 | |
|
| 0.0039 | 15.0 | 98325 | 70.5029 | 0.0936 | |
|
| 0.005 | 16.0 | 104880 | 67.9884 | 0.0904 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.9.0 |
|
- Transformers 4.38.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
