Downloads · 30 days
6
2% of all-time downloads
t5-small-finetuned-booksum
mgundik/t5-small-finetuned-booksum
t5-small-finetuned-booksum is a machine learning model from mgundik. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
270
Public
Parameters
60.5M
5.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors242 MB · 99%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Jul 28, 2024
- Updated
- Oct 3, 2024
- SHA
- f43aa4e4
Base models
Datasets
Model card
From the Hugging Face model README
<!-- 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-booksum
This model is a fine-tuned version of t5-small on an booksum dataset. It achieves the following results on the evaluation set:
- Loss: 3.3115
- Rouge1: 20.5085
- Rouge2: 2.9908
- Rougel: 13.8508
- Rougelsum: 18.4822
- Gen Len: 228.1577
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 3.7585 | 1.0 | 600 | 3.3969 | 17.6639 | 2.5697 | 12.3838 | 15.9802 | 307.0236 |
| 3.5518 | 2.0 | 1200 | 3.3526 | 20.0469 | 2.9053 | 13.6055 | 18.0492 | 248.2581 |
| 3.5108 | 3.0 | 1800 | 3.3318 | 20.0243 | 2.8879 | 13.5558 | 17.9889 | 245.3416 |
| 3.4798 | 4.0 | 2400 | 3.3202 | 20.1501 | 2.9346 | 13.6819 | 18.1977 | 232.3801 |
| 3.4542 | 5.0 | 3000 | 3.3134 | 20.6061 | 3.0311 | 13.9844 | 18.5832 | 217.8302 |
| 3.453 | 6.0 | 3600 | 3.3115 | 20.5085 | 2.9908 | 13.8508 | 18.4822 | 228.1577 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Created
- Jul 28, 2024
- Updated
- Oct 3, 2024