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: 0.9695
- Accuracy: 0.448
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 |
|---|---|---|---|---|
| 9.5046 | 1.0 | 250 | 2.3331 | 0.114 |
| 2.4331 | 2.0 | 500 | 1.7122 | 0.12 |
| 1.8836 | 3.0 | 750 | 1.5107 | 0.21 |
| 1.6365 | 4.0 | 1000 | 1.4237 | 0.208 |
| 1.4737 | 5.0 | 1250 | 1.2627 | 0.316 |
| 1.3361 | 6.0 | 1500 | 1.1837 | 0.37 |
| 1.1998 | 7.0 | 1750 | 1.1045 | 0.408 |
| 1.1317 | 8.0 | 2000 | 1.0488 | 0.404 |
| 1.0612 | 9.0 | 2250 | 1.0142 | 0.42 |
| 1.0265 | 10.0 | 2500 | 0.9925 | 0.422 |
| 1.009 | 11.0 | 2750 | 0.9708 | 0.446 |
| 0.9898 | 12.0 | 3000 | 0.9695 | 0.448 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0