dialogsum_6593_bart-base
This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3997
- Rouge1: 0.4226
- Rouge2: 0.2139
- Rougel: 0.3698
- Rougelsum: 0.37
- Gen Len: 19.86
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.3756 | 2.57 | 500 | 0.4106 | 0.4083 | 0.19 | 0.3536 | 0.3534 | 19.944 |
| 0.2843 | 5.14 | 1000 | 0.4048 | 0.422 | 0.2134 | 0.3678 | 0.3681 | 19.848 |
| 0.2561 | 7.7 | 1500 | 0.3997 | 0.4226 | 0.2139 | 0.3698 | 0.37 | 19.86 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.0.0+cu117
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 15