mt5-small-finetuned-1.1.1
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: 0.1156
- Rouge1: 47.5979
- Rouge2: 44.6327
- Rougel: 47.3923
- Rougelsum: 47.3901
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 0.5174 | 1.0 | 1161 | 0.1334 | 47.5928 | 44.6262 | 47.3883 | 47.3864 |
| 0.1345 | 2.0 | 2322 | 0.1156 | 47.5979 | 44.6327 | 47.3923 | 47.3901 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.2
- Tokenizers 0.12.1