metadata
library_name: transformers
license: apache-2.0
base_model: t5-base
tags:
- generated_from_trainer
model-index:
- name: confidence-feedback
results: []
confidence-feedback
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9663
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: Use OptimizerNames.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 |
|---|---|---|---|
| 2.5697 | 1.0 | 201 | 2.3225 |
| 2.3371 | 2.0 | 402 | 2.1718 |
| 2.1322 | 3.0 | 603 | 2.1028 |
| 1.9953 | 4.0 | 804 | 2.0633 |
| 1.9157 | 5.0 | 1005 | 2.0371 |
| 1.8617 | 6.0 | 1206 | 2.0340 |
| 1.7933 | 7.0 | 1407 | 2.0254 |
| 1.7534 | 8.0 | 1608 | 2.0297 |
| 1.6639 | 9.0 | 1809 | 2.0330 |
| 1.6649 | 10.0 | 2010 | 2.0324 |
Framework versions
- Transformers 4.54.1
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.4