Downloads · 30 days
25
25% of all-time downloads
bart-bart-base-cnn-dailymail-seed42
tomvoelker/bart-bart-base-cnn-dailymail-seed42
bart-bart-base-cnn-dailymail-seed42 is a machine learning model from tomvoelker. 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
100
Public
Parameters
139M
6.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors558 MB · 99%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- bart
- Access
- Public
- Created
- Mar 13, 2025
- Updated
- Mar 14, 2025
- SHA
- 78151ad5
Base models
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-bart-base-cnn-dailymail-seed42
This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6899
- Rouge1: 0.4175
- Rouge2: 0.1965
- Rougel: 0.2901
- Rougelsum: 0.3909
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: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 2.1413 | 0.2229 | 2000 | 1.8550 | 0.4075 | 0.1884 | 0.2728 | 0.3798 |
| 2.0645 | 0.4458 | 4000 | 1.7928 | 0.4093 | 0.1896 | 0.2815 | 0.3828 |
| 2.0157 | 0.6687 | 6000 | 1.7686 | 0.4119 | 0.1912 | 0.2831 | 0.3849 |
| 2.0001 | 0.8916 | 8000 | 1.7570 | 0.4109 | 0.1901 | 0.2817 | 0.3831 |
| 1.936 | 1.1145 | 10000 | 1.7417 | 0.4129 | 0.1920 | 0.2843 | 0.3863 |
| 1.9241 | 1.3374 | 12000 | 1.7246 | 0.4166 | 0.1955 | 0.2877 | 0.3901 |
| 1.9136 | 1.5603 | 14000 | 1.7175 | 0.4147 | 0.1937 | 0.2860 | 0.3879 |
| 1.9219 | 1.7832 | 16000 | 1.7117 | 0.4152 | 0.1944 | 0.2879 | 0.3886 |
| 1.9081 | 2.0061 | 18000 | 1.7020 | 0.4158 | 0.1947 | 0.2888 | 0.3896 |
| 1.8703 | 2.2290 | 20000 | 1.7004 | 0.4158 | 0.1948 | 0.2872 | 0.3890 |
| 1.862 | 2.4519 | 22000 | 1.6940 | 0.4176 | 0.1959 | 0.2888 | 0.3910 |
| 1.8521 | 2.6748 | 24000 | 1.6919 | 0.4170 | 0.1958 | 0.2897 | 0.3903 |
| 1.8641 | 2.8977 | 26000 | 1.6899 | 0.4175 | 0.1965 | 0.2901 | 0.3909 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1
- Library
- transformers
- Type
- bart
- License
- apache-2.0
- Created
- Mar 13, 2025
- Updated
- Mar 14, 2025