metadata
language:
- en
license: mit
tags:
- generated_from_trainer
datasets:
- cuad
model-index:
- name: T5-base-cuad-3
results: []
T5-base-cuad-3
This model is a fine-tuned version of t5-base on the cuad dataset. It achieves the following results on the evaluation set:
- Loss: 0.4275
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: 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.5632 | 1.0 | 1398 | 0.4593 |
0.5098 | 2.0 | 2796 | 0.4428 |
0.4718 | 3.0 | 4194 | 0.4349 |
0.4459 | 4.0 | 5592 | 0.4313 |
0.4363 | 5.0 | 6990 | 0.4304 |
0.4077 | 6.0 | 8388 | 0.4275 |
0.4159 | 7.0 | 9786 | 0.4282 |
0.4024 | 8.0 | 11184 | 0.4276 |
0.4002 | 9.0 | 12582 | 0.4279 |
0.3962 | 10.0 | 13980 | 0.4283 |
Framework versions
- Transformers 4.16.0.dev0
- Pytorch 1.10.0+cu111
- Datasets 1.17.0
- Tokenizers 0.10.3