mt5-small-finetuned-mt5-small
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: 2.4415
- Rouge1: 0.1099
- Rouge2: 0.0252
- Rougel: 0.1091
- Rougelsum: 0.1092
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
---|---|---|---|---|---|---|---|
2.9231 | 1.0 | 12500 | 2.6899 | 0.0981 | 0.0217 | 0.0975 | 0.0976 |
2.9124 | 2.0 | 25000 | 2.5725 | 0.0981 | 0.0214 | 0.0974 | 0.0974 |
2.7986 | 3.0 | 37500 | 2.5226 | 0.1053 | 0.0243 | 0.1047 | 0.1047 |
2.7205 | 4.0 | 50000 | 2.4882 | 0.1069 | 0.0245 | 0.1061 | 0.1062 |
2.6668 | 5.0 | 62500 | 2.4613 | 0.1112 | 0.0244 | 0.1104 | 0.1105 |
2.624 | 6.0 | 75000 | 2.4584 | 0.111 | 0.0254 | 0.1103 | 0.1103 |
2.5963 | 7.0 | 87500 | 2.4448 | 0.1093 | 0.0249 | 0.1085 | 0.1087 |
2.5776 | 8.0 | 100000 | 2.4415 | 0.1099 | 0.0252 | 0.1091 | 0.1092 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.0+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 8