Downloads · 30 days
5
2% of all-time downloads
NASca-finetuned-diego-4-amb-metriques-anonim
dtorber/NASca-finetuned-diego-4-amb-metriques-anonim
NASca-finetuned-diego-4-amb-metriques-anonim is a summarization model from dtorber. Use it when you need a shorter version of a longer text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
273
Public
Repo size
28.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.7 GB · 100%
At a glance
- Task
- Summarization
- Library
- transformers
- Model type
- bart
- Access
- Public
- Created
- Mar 3, 2023
- Updated
- Mar 6, 2023
- SHA
- 902539ad
Try a prompt
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. -->
NASca-finetuned-diego-4-amb-metriques-anonim
This model is a fine-tuned version of ELiRF/NASCA on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8164
- Rouge1: 0.3868
- Rouge2: 0.3690
- Rougel: 0.3815
- Rougelsum: 0.3820
- Classificacio Format Correcte: 0.0
- Classificacio Recall: 0.0
- Classificacio Precision: 0.0
- Classificacio F1: 0.0
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: 1.3739167643078955e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Classificacio Format Correcte | Classificacio Recall | Classificacio Precision | Classificacio F1 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.3365 | 1.0 | 159149 | 1.7901 | 0.3859 | 0.3681 | 0.3806 | 0.3812 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.3045 | 2.0 | 318298 | 1.7997 | 0.3864 | 0.3686 | 0.3811 | 0.3816 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.3045 | 3.0 | 477447 | 1.8067 | 0.3866 | 0.3688 | 0.3812 | 0.3818 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.2534 | 4.0 | 636596 | 1.8133 | 0.3869 | 0.3692 | 0.3816 | 0.3822 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.3103 | 5.0 | 795745 | 1.8164 | 0.3868 | 0.3690 | 0.3815 | 0.3820 | 0.0 | 0.0 | 0.0 | 0.0 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.9.0
- Tokenizers 0.13.2
- Task
- Summarization
- Library
- transformers
- Type
- bart
- Created
- Mar 3, 2023
- Updated
- Mar 6, 2023