<!-- 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. -->
qa_references_all
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: 4.0348
- Rouge1: 0.1188
- Rouge2: 0.0107
- Rougel: 0.0976
- Rougelsum: 0.098
- Gen Len: 19.0
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 357 | 6.1510 | 0.0604 | 0.0063 | 0.0548 | 0.0546 | 18.8222 |
| 12.6296 | 2.0 | 714 | 4.1645 | 0.1128 | 0.0106 | 0.0986 | 0.0984 | 19.0 |
| 5.7722 | 3.0 | 1071 | 4.0653 | 0.1261 | 0.0125 | 0.1054 | 0.1055 | 19.0 |
| 5.7722 | 4.0 | 1428 | 4.0452 | 0.1219 | 0.0109 | 0.0991 | 0.0993 | 19.0 |
| 5.3698 | 5.0 | 1785 | 4.0348 | 0.1188 | 0.0107 | 0.0976 | 0.098 | 19.0 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
