<!-- 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. -->
flan-t5-base-cars-descriptions
This model is a fine-tuned version of google/flan-t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0593
- Rouge1: 20.1849
- Rouge2: 13.35
- Rougel: 17.2099
- Rougelsum: 19.1768
- 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: 5e-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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 28 | 1.2595 | 20.734 | 13.4047 | 17.7078 | 19.8711 | 19.0 |
No log | 2.0 | 56 | 1.1428 | 20.3005 | 13.3213 | 17.3211 | 19.4145 | 19.0 |
No log | 3.0 | 84 | 1.0879 | 19.9129 | 13.4509 | 17.4589 | 18.9792 | 19.0 |
No log | 4.0 | 112 | 1.0694 | 20.4726 | 13.6707 | 17.3821 | 19.5606 | 19.0 |
No log | 5.0 | 140 | 1.0593 | 20.1849 | 13.35 | 17.2099 | 19.1768 | 19.0 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1