metadata
license: apache-2.0
base_model: google/mt5-small
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: mt5-small-task2-dataset1
results: []
mt5-small-task2-dataset1
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: 0.3301
- Accuracy: 0.714
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: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 7.9531 | 1.0 | 250 | 1.3804 | 0.474 |
| 1.8269 | 2.0 | 500 | 0.8424 | 0.552 |
| 1.0738 | 3.0 | 750 | 0.6419 | 0.606 |
| 0.7726 | 4.0 | 1000 | 0.5072 | 0.65 |
| 0.649 | 5.0 | 1250 | 0.4420 | 0.664 |
| 0.5479 | 6.0 | 1500 | 0.4009 | 0.672 |
| 0.4958 | 7.0 | 1750 | 0.3732 | 0.684 |
| 0.4437 | 8.0 | 2000 | 0.3576 | 0.716 |
| 0.4287 | 9.0 | 2250 | 0.3477 | 0.708 |
| 0.4016 | 10.0 | 2500 | 0.3378 | 0.716 |
| 0.3975 | 11.0 | 2750 | 0.3310 | 0.718 |
| 0.3818 | 12.0 | 3000 | 0.3301 | 0.714 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0