<!-- 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-finetuned-policy
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4306
- Rouge1: 19.5603
- Rouge2: 13.5761
- Rougel: 17.9728
- Rougelsum: 18.3608
- Gen Len: 18.9529
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: 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: 4
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
1.7469 | 1.0 | 1400 | 1.5070 | 18.8697 | 12.8892 | 17.2714 | 17.6566 | 18.9629 |
1.6541 | 2.0 | 2800 | 1.4598 | 19.388 | 13.4242 | 17.7886 | 18.1717 | 18.9579 |
1.6321 | 3.0 | 4200 | 1.4420 | 19.5153 | 13.5437 | 17.9251 | 18.3107 | 18.955 |
1.604 | 4.0 | 5600 | 1.4306 | 19.5603 | 13.5761 | 17.9728 | 18.3608 | 18.9529 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3