<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
mt5-small-finetuned-18jan-3
This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6115
- Rouge1: 7.259
- Rouge2: 0.3667
- Rougel: 7.1595
- Rougelsum: 7.156
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: 0.0002
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
---|---|---|---|---|---|---|---|
7.1947 | 1.0 | 60 | 3.1045 | 5.91 | 0.8583 | 5.8687 | 5.8123 |
3.8567 | 2.0 | 120 | 2.7744 | 8.0065 | 0.4524 | 8.0204 | 7.85 |
3.4346 | 3.0 | 180 | 2.7319 | 7.5954 | 0.4524 | 7.5204 | 7.4833 |
3.219 | 4.0 | 240 | 2.6736 | 8.5329 | 0.3333 | 8.487 | 8.312 |
3.0836 | 5.0 | 300 | 2.6583 | 8.3405 | 0.5667 | 8.2003 | 8.0543 |
2.9713 | 6.0 | 360 | 2.6516 | 8.8421 | 0.1667 | 8.7597 | 8.6754 |
2.9757 | 7.0 | 420 | 2.6369 | 8.04 | 0.3667 | 8.0018 | 7.8489 |
2.8321 | 8.0 | 480 | 2.6215 | 6.8739 | 0.3667 | 6.859 | 6.7917 |
2.794 | 9.0 | 540 | 2.6090 | 7.0738 | 0.4167 | 7.0232 | 6.9619 |
2.7695 | 10.0 | 600 | 2.6115 | 7.259 | 0.3667 | 7.1595 | 7.156 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2