t5-base_cola_dense
This model is a fine-tuned version of t5-base on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6351
- Accuracy: 0.6913
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: 32
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- num_epochs: 1
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
Accuracy |
| 0.6331 |
0.07 |
10 |
0.6263 |
0.6855 |
| 0.626 |
0.15 |
20 |
0.6247 |
0.6826 |
| 0.6412 |
0.22 |
30 |
0.6240 |
0.6865 |
| 0.6497 |
0.3 |
40 |
0.6210 |
0.6874 |
| 0.6226 |
0.37 |
50 |
0.6213 |
0.6874 |
| 0.6183 |
0.45 |
60 |
0.6198 |
0.6894 |
| 0.6034 |
0.52 |
70 |
0.6202 |
0.6894 |
| 0.5802 |
0.6 |
80 |
0.6219 |
0.6913 |
| 0.6005 |
0.67 |
90 |
0.6261 |
0.6913 |
| 0.6178 |
0.75 |
100 |
0.6331 |
0.6922 |
| 0.5887 |
0.82 |
110 |
0.6344 |
0.6913 |
| 0.6492 |
0.9 |
120 |
0.6371 |
0.6913 |
| 0.6333 |
0.97 |
130 |
0.6376 |
0.6913 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
