metadata
library_name: transformers
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
metrics:
- sacrebleu
- rouge
model-index:
- name: bart-base-finetuned-w-data-augm-4e-5
results: []
bart-base-finetuned-w-data-augm-4e-5
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: 0.3985
- Sacrebleu: 89.8136
- Rouge1: 95.6369
- Rouge2: 91.8617
- Rougel: 94.6909
- Rougelsum: 94.6811
- Bertscore Precision: 0.9424
- Bertscore Recall: 0.9374
- Bertscore F1: 0.9399
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: 4.4252514647201465e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Sacrebleu | Rouge1 | Rouge2 | Rougel | Rougelsum | Bertscore Precision | Bertscore Recall | Bertscore F1 |
---|---|---|---|---|---|---|---|---|---|---|---|
0.1107 | 1.0 | 761 | 0.2850 | 90.5237 | 96.15 | 92.6707 | 95.2684 | 95.2821 | 0.9487 | 0.9425 | 0.9456 |
0.0435 | 2.0 | 1522 | 0.2695 | 91.4933 | 96.4613 | 93.4149 | 95.6712 | 95.6642 | 0.9515 | 0.9522 | 0.9518 |
0.0421 | 3.0 | 2283 | 0.2579 | 91.4926 | 96.4713 | 93.2669 | 95.7036 | 95.7071 | 0.9522 | 0.9505 | 0.9513 |
0.0233 | 4.0 | 3044 | 0.2717 | 91.8243 | 96.6369 | 93.443 | 95.8509 | 95.8593 | 0.9537 | 0.9521 | 0.9529 |
0.0327 | 5.0 | 3805 | 0.2804 | 92.095 | 96.6849 | 93.7485 | 95.9279 | 95.9247 | 0.9551 | 0.9526 | 0.9538 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1