metadata
license: apache-2.0
base_model: google/mt5-small
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: mt5-small-task1-dataset2
results: []
mt5-small-task1-dataset2
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: 1.1512
- Accuracy: 0.176
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 |
|---|---|---|---|---|
| 10.1566 | 1.0 | 250 | 2.1729 | 0.012 |
| 2.7222 | 2.0 | 500 | 1.8375 | 0.004 |
| 2.2156 | 3.0 | 750 | 1.6780 | 0.068 |
| 1.9891 | 4.0 | 1000 | 1.4901 | 0.098 |
| 1.7951 | 5.0 | 1250 | 1.4195 | 0.116 |
| 1.6179 | 6.0 | 1500 | 1.2971 | 0.136 |
| 1.5252 | 7.0 | 1750 | 1.2543 | 0.152 |
| 1.4486 | 8.0 | 2000 | 1.2054 | 0.162 |
| 1.3957 | 9.0 | 2250 | 1.1865 | 0.182 |
| 1.3609 | 10.0 | 2500 | 1.1656 | 0.176 |
| 1.3395 | 11.0 | 2750 | 1.1589 | 0.176 |
| 1.3295 | 12.0 | 3000 | 1.1512 | 0.176 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0