metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart
results: []
bart
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2484
- Rouge1: 0.2698
- Rouge2: 0.2581
- Rougel: 0.2698
- Rougelsum: 0.2698
- Gen Len: 20.0
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 3 | 1.6226 | 0.0826 | 0.0 | 0.0661 | 0.0661 | 20.0 |
| No log | 2.0 | 6 | 1.4712 | 0.256 | 0.2439 | 0.256 | 0.256 | 20.0 |
| No log | 3.0 | 9 | 1.3444 | 0.2698 | 0.2581 | 0.2698 | 0.2698 | 20.0 |
| No log | 4.0 | 12 | 1.2484 | 0.2698 | 0.2581 | 0.2698 | 0.2698 | 20.0 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0