metadata
library_name: transformers
license: apache-2.0
base_model: t5-base
tags:
- generated_from_trainer
model-index:
- name: results
results: []
results
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0138
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: 4
- eval_batch_size: 4
- 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: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2803 | 0.1605 | 500 | 1.1425 |
| 1.1981 | 0.3210 | 1000 | 1.1046 |
| 1.1875 | 0.4815 | 1500 | 1.0748 |
| 1.1374 | 0.6421 | 2000 | 1.0605 |
| 1.1433 | 0.8026 | 2500 | 1.0441 |
| 1.1091 | 0.9631 | 3000 | 1.0329 |
| 1.0569 | 1.1236 | 3500 | 1.0310 |
| 1.043 | 1.2841 | 4000 | 1.0207 |
| 1.0287 | 1.4446 | 4500 | 1.0209 |
| 1.0225 | 1.6051 | 5000 | 1.0164 |
| 1.0446 | 1.7657 | 5500 | 1.0193 |
| 1.0148 | 1.9262 | 6000 | 1.0138 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0