metadata
library_name: transformers
license: apache-2.0
base_model: google/t5-v1_1-large
tags:
- generated_from_trainer
model-index:
- name: QGC2
results: []
QGC2
This model is a fine-tuned version of google/t5-v1_1-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5302
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAFACTOR and the args are: No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.9372 | 0.0925 | 200 | 3.9831 |
| 6.6356 | 0.1850 | 400 | 5.5394 |
| 4.9934 | 0.2775 | 600 | 3.9748 |
| 1.2719 | 0.3700 | 800 | 2.3928 |
| 0.4698 | 0.4625 | 1000 | 2.5047 |
| 0.3714 | 0.5550 | 1200 | 2.5249 |
| 0.4314 | 0.6475 | 1400 | 2.4641 |
| 0.3454 | 0.7401 | 1600 | 2.4906 |
| 0.3313 | 0.8326 | 1800 | 2.5153 |
| 0.2904 | 0.9251 | 2000 | 2.5302 |
Framework versions
- Transformers 4.50.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1