metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Finetuned_FLAN-T5_VALUE_adapterfusion_lr5e-5_bs64
results: []
Finetuned_FLAN-T5_VALUE_adapterfusion_lr5e-5_bs64
This model is a fine-tuned version of liuyanchen1015/FLAN-T5_GLUE_finetuning_lr3e-4 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0879
- Accuracy: 0.8776
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0597 | 0.07 | 1000 | 0.0890 | 0.8752 |
| 0.055 | 0.14 | 2000 | 0.0886 | 0.8768 |
| 0.0545 | 0.2 | 3000 | 0.0870 | 0.8746 |
| 0.0526 | 0.27 | 4000 | 0.0881 | 0.8756 |
| 0.0515 | 0.34 | 5000 | 0.0876 | 0.8756 |
| 0.0501 | 0.41 | 6000 | 0.0885 | 0.8788 |
| 0.0497 | 0.47 | 7000 | 0.0908 | 0.8756 |
| 0.0498 | 0.54 | 8000 | 0.0899 | 0.8776 |
| 0.0509 | 0.61 | 9000 | 0.0902 | 0.8754 |
| 0.0504 | 0.68 | 10000 | 0.0898 | 0.8736 |
| 0.049 | 0.74 | 11000 | 0.0879 | 0.8734 |
| 0.0494 | 0.81 | 12000 | 0.0878 | 0.8746 |
| 0.0477 | 0.88 | 13000 | 0.0883 | 0.8766 |
| 0.0498 | 0.95 | 14000 | 0.0879 | 0.8776 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.0+cu117
- Datasets 2.10.1
- Tokenizers 0.12.1