<!-- 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. -->
t5-small-nsbs2
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.9627
- Rouge1: 13.1375
- Rouge2: 2.2388
- Rougel: 12.5358
- Rougelsum: 12.5667
- 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: 0.02
- 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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 100 | 5.7579 | 9.9822 | 0.5909 | 9.6984 | 9.7494 | 19.0 |
No log | 2.0 | 200 | 5.9612 | 12.9227 | 2.1532 | 12.3116 | 12.3476 | 19.0 |
No log | 3.0 | 300 | 5.8949 | 15.7023 | 2.4116 | 15.252 | 15.3069 | 13.94 |
No log | 4.0 | 400 | 5.9386 | 12.9227 | 2.1532 | 12.3116 | 12.3476 | 19.0 |
4.8867 | 5.0 | 500 | 5.9627 | 13.1375 | 2.2388 | 12.5358 | 12.5667 | 19.0 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3