metadata
license: apache-2.0
base_model: google/mt5-base
tags:
- generated_from_trainer
datasets:
- tiagoblima/du-qg-squadv1_pt
model-index:
- name: mt5_base-qg-ap-oficial
results: []
mt5_base-qg-ap-oficial
This model is a fine-tuned version of google/mt5-base on the tiagoblima/du-qg-squadv1_pt dataset. It achieves the following results on the evaluation set:
- Loss: 1.3846
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: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6703 | 1.0 | 2367 | 1.4647 |
| 1.4897 | 2.0 | 4734 | 1.4201 |
| 1.3982 | 3.0 | 7101 | 1.3960 |
| 1.3304 | 4.0 | 9468 | 1.3853 |
| 1.2909 | 5.0 | 11835 | 1.3846 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0