metadata
license: apache-2.0
base_model: facebook/bart-large
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: model
results: []
model
This model is a fine-tuned version of facebook/bart-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9659
- Rouge1: 0.6514
- Rouge2: 0.5278
- Rougel: 0.6214
- Rougelsum: 0.6209
- Gen Len: 19.9082
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: 4
- eval_batch_size: 4
- 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 |
|---|---|---|---|---|---|---|---|---|
| 0.9746 | 1.0 | 3363 | 0.9969 | 0.6465 | 0.5254 | 0.6176 | 0.6175 | 19.9014 |
| 0.7439 | 2.0 | 6726 | 0.9272 | 0.6516 | 0.5291 | 0.6221 | 0.6216 | 19.8652 |
| 0.5953 | 3.0 | 10089 | 0.9432 | 0.6533 | 0.5293 | 0.6231 | 0.6228 | 19.8943 |
| 0.4824 | 4.0 | 13452 | 0.9659 | 0.6514 | 0.5278 | 0.6214 | 0.6209 | 19.9082 |
Framework versions
- Transformers 4.39.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2