metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: t5-base-asqa-ob
results: []
t5-base-asqa-ob
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2086
- Rougelsum: 11.8466
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: 0.0005
- 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
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rougelsum |
|---|---|---|---|---|
| No log | 1.0 | 355 | 1.7972 | 11.9539 |
| 1.9198 | 2.0 | 710 | 1.8071 | 12.2057 |
| 1.504 | 3.0 | 1065 | 1.8566 | 11.9288 |
| 1.504 | 4.0 | 1420 | 1.9225 | 11.9550 |
| 1.232 | 5.0 | 1775 | 2.0097 | 11.9038 |
| 1.0016 | 6.0 | 2130 | 2.0912 | 11.9418 |
| 1.0016 | 7.0 | 2485 | 2.2086 | 11.8466 |
Framework versions
- Transformers 4.23.0.dev0
- Pytorch 1.12.1+cu102
- Datasets 2.4.0
- Tokenizers 0.12.1