<!-- 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-large-extraction-cnndm_4000-summary
This model is a fine-tuned version of google/flan-t5-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6681
- Rouge1: 28.6624
- Rouge2: 12.5675
- Rougel: 26.6805
- Rougelsum: 26.6607
- Gen Len: 18.994
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: 16
- eval_batch_size: 48
- seed: 1799
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.1095 | 0.8 | 200 | 1.7556 | 27.9008 | 12.4161 | 25.8249 | 25.8684 | 18.992 |
| 1.8546 | 1.6 | 400 | 1.6915 | 28.4006 | 12.5811 | 26.5641 | 26.5743 | 18.994 |
| 1.7663 | 2.4 | 600 | 1.6969 | 28.8189 | 13.0589 | 27.1139 | 27.1228 | 18.996 |
| 1.708 | 3.2 | 800 | 1.6820 | 28.2072 | 12.2821 | 26.3357 | 26.3362 | 18.986 |
| 1.65 | 4.0 | 1000 | 1.6681 | 28.6624 | 12.5675 | 26.6805 | 26.6607 | 18.994 |
| 1.6055 | 4.8 | 1200 | 1.6746 | 28.9578 | 12.5802 | 26.8603 | 26.8992 | 18.994 |
| 1.5773 | 5.6 | 1400 | 1.6783 | 28.7343 | 12.7636 | 26.8363 | 26.8085 | 18.972 |
| 1.5395 | 6.4 | 1600 | 1.6923 | 28.9076 | 12.8719 | 26.772 | 26.7952 | 18.998 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1
