metadata
license: apache-2.0
base_model: google/mt5-small
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: mt5-small-task3-dataset3
results: []
mt5-small-task3-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: 1.4565
- Accuracy: 0.124
- Mse: 2.0170
- Log-distance: 0.7037
- S Score: 0.4680
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 | Mse | Log-distance | S Score |
|---|---|---|---|---|---|---|---|
| 3.3423 | 1.0 | 250 | 1.5914 | 0.074 | 2.3687 | 0.6693 | 0.4992 |
| 2.3267 | 2.0 | 500 | 1.6213 | 0.102 | 2.6627 | 0.7153 | 0.4836 |
| 1.8968 | 3.0 | 750 | 1.4707 | 0.118 | 2.0674 | 0.7576 | 0.4228 |
| 1.7414 | 4.0 | 1000 | 1.4367 | 0.124 | 2.0643 | 0.7534 | 0.4236 |
| 1.6639 | 5.0 | 1250 | 1.4493 | 0.12 | 2.0268 | 0.7079 | 0.4624 |
| 1.6088 | 6.0 | 1500 | 1.4538 | 0.116 | 1.9955 | 0.6762 | 0.4924 |
| 1.5823 | 7.0 | 1750 | 1.4565 | 0.124 | 2.0170 | 0.7037 | 0.4680 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0