metadata
library_name: transformers
license: apache-2.0
base_model: google/mt5-small
tags:
- summarization
- generated_from_trainer
model-index:
- name: mt5-small-finetuned-amazon-en-es
results: []
mt5-small-finetuned-amazon-en-es
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: 2.0229
- Bertscore Precision: 0.7189
- Bertscore Recall: 0.6939
- Bertscore F1: 0.7056
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: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Bertscore Precision | Bertscore Recall | Bertscore F1 |
|---|---|---|---|---|---|---|
| 2.5119 | 1.0 | 1557 | 2.2031 | 0.711 | 0.6852 | 0.6972 |
| 2.5009 | 2.0 | 3114 | 2.1234 | 0.7154 | 0.6875 | 0.7005 |
| 2.4158 | 3.0 | 4671 | 2.0854 | 0.7165 | 0.6914 | 0.7032 |
| 2.3603 | 4.0 | 6228 | 2.0629 | 0.7166 | 0.6911 | 0.703 |
| 2.3206 | 5.0 | 7785 | 2.0451 | 0.7191 | 0.6934 | 0.7054 |
| 2.2938 | 6.0 | 9342 | 2.0328 | 0.718 | 0.6934 | 0.7049 |
| 2.2718 | 7.0 | 10899 | 2.0253 | 0.7191 | 0.6944 | 0.706 |
| 2.2622 | 8.0 | 12456 | 2.0229 | 0.7189 | 0.6939 | 0.7056 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.7.1+cu118
- Datasets 2.14.6
- Tokenizers 0.21.1