<!-- 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
This model is a fine-tuned version of google/flan-t5-base on the cnn_dailymail dataset. It achieves the following results on the evaluation set:
- Loss: 1.5842
- Rouge1: 40.8655
- Rouge2: 18.8212
- Rougel: 28.4085
- Rougelsum: 37.7559
- Gen Len: 103.5229
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: 0.0001
- train_batch_size: 256
- eval_batch_size: 256
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 512
- total_eval_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
1.9056 | 1.0 | 561 | 1.6271 | 40.3084 | 18.4219 | 27.9883 | 37.1807 | 104.5203 |
1.8419 | 2.0 | 1122 | 1.5991 | 40.7552 | 18.6806 | 28.3825 | 37.6533 | 100.3285 |
1.8091 | 3.0 | 1683 | 1.5842 | 40.8655 | 18.8212 | 28.4085 | 37.7559 | 103.5229 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2