metadata
license: mit
base_model: facebook/bart-large-cnn
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: attainment_bart_summarization
results: []
attainment_bart_summarization
This model is a fine-tuned version of facebook/bart-large-cnn on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3648
- Rouge1: 0.593
- Rouge2: 0.5676
- Rougel: 0.5797
- Rougelsum: 0.5816
- Gen Len: 66.7368
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 38 | 0.3416 | 0.5952 | 0.5638 | 0.5657 | 0.5659 | 66.4737 |
| No log | 2.0 | 76 | 0.2780 | 0.5992 | 0.5733 | 0.5777 | 0.5776 | 66.7237 |
| No log | 3.0 | 114 | 0.3348 | 0.593 | 0.5632 | 0.5719 | 0.5734 | 66.5921 |
| No log | 4.0 | 152 | 0.3648 | 0.593 | 0.5676 | 0.5797 | 0.5816 | 66.7368 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3