<!-- 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-cnn-news-finetuned-NO3
This model is a fine-tuned version of shivaniNK8/mt5-small-finetuned-cnn-news on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3662
- Rouge1: 0.4503
- Rouge2: 0.3143
- Rougel: 0.4357
- Rougelsum: 0.4395
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 |
|---|---|---|---|---|---|---|---|
| 3.5817 | 1.0 | 200 | 1.5691 | 0.4010 | 0.2702 | 0.3946 | 0.3942 |
| 2.735 | 2.0 | 400 | 1.4498 | 0.4577 | 0.3209 | 0.4473 | 0.4513 |
| 2.4035 | 3.0 | 600 | 1.3992 | 0.4843 | 0.3540 | 0.4738 | 0.4770 |
| 2.1905 | 4.0 | 800 | 1.3886 | 0.4427 | 0.3071 | 0.4285 | 0.4313 |
| 2.0849 | 5.0 | 1000 | 1.3743 | 0.4480 | 0.3096 | 0.4315 | 0.4356 |
| 2.0322 | 6.0 | 1200 | 1.3741 | 0.4567 | 0.3191 | 0.4410 | 0.4445 |
| 1.9513 | 7.0 | 1400 | 1.3693 | 0.4560 | 0.3183 | 0.4415 | 0.4445 |
| 1.943 | 8.0 | 1600 | 1.3662 | 0.4503 | 0.3143 | 0.4357 | 0.4395 |
Framework versions
- Transformers 4.27.3
- Pytorch 2.0.0+cu117
- Datasets 2.10.1
- Tokenizers 0.13.2
