metadata
license: apache-2.0
base_model: facebook/bart-large
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: my_bart_model
results: []
my_bart_model
This model is a fine-tuned version of facebook/bart-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3832
- Rouge1: 0.7947
- Rouge2: 0.6832
- Rougel: 0.7731
- Rougelsum: 0.7732
- Gen Len: 15.8956
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 |
|---|---|---|---|---|---|---|---|---|
| 0.4469 | 1.0 | 2185 | 0.4639 | 0.7605 | 0.6319 | 0.7345 | 0.7346 | 15.8928 |
| 0.3132 | 2.0 | 4370 | 0.4013 | 0.7766 | 0.6564 | 0.7516 | 0.7516 | 15.9322 |
| 0.2214 | 3.0 | 6555 | 0.3802 | 0.7878 | 0.6734 | 0.7656 | 0.7657 | 15.986 |
| 0.1673 | 4.0 | 8740 | 0.3832 | 0.7947 | 0.6832 | 0.7731 | 0.7732 | 15.8956 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1