Downloads · 30 days
2
3% of all-time downloads
mbart_cnn_summarization_10K_8ep_2e-5_batch_8_warmup_saved_best
NastasiaM/mbart_cnn_summarization_10K_8ep_2e-5_batch_8_warmup_saved_best
mbart_cnn_summarization_10K_8ep_2e-5_batch_8_warmup_saved_best is a machine learning model from NastasiaM. 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 mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
69
Public
Parameters
1.4B
5.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.5 GB · 100%
At a glance
- Library
- transformers
- License
- mit
- Model type
- mbart
- Access
- Public
- Created
- Feb 28, 2026
- Updated
- Feb 28, 2026
- SHA
- 8914e822
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. -->
mbart_cnn_summarization_10K_8ep_2e-5_batch_8_warmup_saved_best
This model is a fine-tuned version of facebook/mbart-large-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.2865
- Rouge1: 41.1204
- Rouge2: 18.6858
- Rougel: 28.4884
- Rougelsum: 28.4915
- Gen Len: 77.089
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: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.05
- num_epochs: 15
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 3.4520 | 1.0 | 1250 | 3.1659 | 39.6508 | 18.0291 | 27.4136 | 27.3941 | 76.862 |
| 3.0821 | 2.0 | 2500 | 3.0391 | 40.4357 | 18.3155 | 27.6329 | 27.6126 | 86.341 |
| 2.8080 | 3.0 | 3750 | 3.0241 | 41.4921 | 19.2759 | 28.6341 | 28.6781 | 78.653 |
| 2.6076 | 4.0 | 5000 | 3.0542 | 42.1783 | 19.6305 | 29.2396 | 29.2321 | 88.248 |
| 2.4447 | 5.0 | 6250 | 3.0983 | 41.428 | 19.1174 | 28.9005 | 28.8947 | 76.52 |
| 2.3084 | 6.0 | 7500 | 3.1595 | 42.6034 | 20.0312 | 29.6046 | 29.6165 | 87.527 |
| 2.1912 | 7.0 | 8750 | 3.2251 | 41.8653 | 19.4398 | 29.3454 | 29.3675 | 80.351 |
| 2.0989 | 8.0 | 10000 | 3.2865 | 41.1204 | 18.6858 | 28.4884 | 28.4915 | 77.089 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.6.1
- Tokenizers 0.22.2
- Library
- transformers
- Type
- mbart
- License
- mit
- Created
- Feb 28, 2026
- Updated
- Feb 28, 2026