<!-- 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-base-gecid23
This model is a fine-tuned version of google/mt5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3423
- Rouge1: 62.9275
- Rouge2: 55.4729
- Rougel: 62.8494
- Rougelsum: 62.8231
- Gen Len: 18.7516
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: 0.001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adafactor
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.7349 | 0.25 | 221 | 0.5029 | 60.0872 | 50.8003 | 59.9688 | 59.9497 | 18.7546 |
| 0.602 | 0.5 | 442 | 0.4185 | 61.5359 | 53.0163 | 61.4213 | 61.3965 | 18.7503 |
| 0.5027 | 0.75 | 663 | 0.3669 | 62.5794 | 54.8058 | 62.4677 | 62.4481 | 18.7516 |
| 0.4217 | 1.0 | 884 | 0.3423 | 62.9275 | 55.4729 | 62.8494 | 62.8231 | 18.7516 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
