metadata
license: apache-2.0
base_model: google/mt5-small
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: mt5-small-task1-dataset3
results: []
mt5-small-task1-dataset3
This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8026
- Accuracy: 0.52
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: 5.6e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 9.7282 | 1.0 | 250 | 2.3106 | 0.118 |
| 2.3916 | 2.0 | 500 | 1.7098 | 0.128 |
| 1.8578 | 3.0 | 750 | 1.5425 | 0.198 |
| 1.6283 | 4.0 | 1000 | 1.4055 | 0.216 |
| 1.4748 | 5.0 | 1250 | 1.3024 | 0.282 |
| 1.2899 | 6.0 | 1500 | 1.1393 | 0.388 |
| 1.1631 | 7.0 | 1750 | 1.0190 | 0.434 |
| 1.0565 | 8.0 | 2000 | 0.9458 | 0.456 |
| 0.9747 | 9.0 | 2250 | 0.9052 | 0.488 |
| 0.9119 | 10.0 | 2500 | 0.8731 | 0.514 |
| 0.8752 | 11.0 | 2750 | 0.8279 | 0.516 |
| 0.8356 | 12.0 | 3000 | 0.8263 | 0.524 |
| 0.8132 | 13.0 | 3250 | 0.8125 | 0.52 |
| 0.8113 | 14.0 | 3500 | 0.8037 | 0.52 |
| 0.8075 | 15.0 | 3750 | 0.8026 | 0.52 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0