Downloads · 30 days
5
21% of all-time downloads
bart-large-fine-tuned-large_
goharava/bart-large-fine-tuned-large_
bart-large-fine-tuned-large_ is a machine learning model from goharava. 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
24
Public
Repo size
3.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.6 GB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- bart
- Access
- Public
- Created
- Nov 1, 2022
- Updated
- Nov 1, 2022
- SHA
- 590ca035
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. -->
bart-large-finetuned-large
This model is a fine-tuned version of facebook/bart-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6397
- Rouge1: 88.2870
- Rouge2: 26.4705
- Rougel: 88.1924
- Rougelsum: 88.3415
- Gen Len: 6.0323
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 121 | 0.8676 | 67.7680 | 19.6386 | 67.5697 | 67.5758 | 6.2774 |
| No log | 2.0 | 242 | 0.6661 | 73.6309 | 21.6079 | 73.2496 | 73.5335 | 5.3957 |
| No log | 3.0 | 363 | 0.6649 | 82.6362 | 21.4663 | 82.3944 | 82.6107 | 5.6624 |
| No log | 4.0 | 484 | 0.6598 | 86.4811 | 25.3580 | 86.1949 | 86.3580 | 5.7914 |
| 0.5135 | 5.0 | 605 | 0.8032 | 86.0334 | 25.1510 | 85.8895 | 85.9038 | 6.5634 |
| 0.5135 | 6.0 | 726 | 0.6981 | 88.0139 | 25.6152 | 87.9025 | 87.9932 | 6.3591 |
| 0.5135 | 7.0 | 847 | 0.6991 | 88.7421 | 25.6469 | 88.5959 | 88.7255 | 6.3376 |
| 0.5135 | 8.0 | 968 | 0.5995 | 88.9180 | 26.9917 | 88.6984 | 88.8878 | 5.8538 |
| 0.1613 | 9.0 | 1089 | 0.5973 | 88.5923 | 26.7081 | 88.4593 | 88.6287 | 5.8387 |
| 0.1613 | 10.0 | 1210 | 0.6397 | 88.2870 | 26.4705 | 88.1924 | 88.3415 | 6.0323 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1
- Library
- transformers
- Type
- bart
- License
- apache-2.0
- Created
- Nov 1, 2022
- Updated
- Nov 1, 2022