metadata
library_name: transformers
license: apache-2.0
base_model: T5-small
tags:
- generated_from_trainer
model-index:
- name: T5-OM
results: []
T5-OM
This model is a fine-tuned version of T5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0065
- Quadruple Accuracy: 0.3182
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Quadruple Accuracy |
|---|---|---|---|---|
| 0.0528 | 1.0 | 468 | 0.0192 | 0.0138 |
| 0.0133 | 2.0 | 936 | 0.0091 | 0.2658 |
| 0.0169 | 3.0 | 1404 | 0.0077 | 0.2579 |
| 0.0115 | 4.0 | 1872 | 0.0072 | 0.2885 |
| 0.0104 | 5.0 | 2340 | 0.0069 | 0.3211 |
| 0.0078 | 6.0 | 2808 | 0.0067 | 0.3211 |
| 0.0094 | 7.0 | 3276 | 0.0066 | 0.3142 |
| 0.0072 | 8.0 | 3744 | 0.0065 | 0.3113 |
| 0.0084 | 9.0 | 4212 | 0.0065 | 0.3152 |
| 0.0064 | 10.0 | 4680 | 0.0065 | 0.3182 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0