rlqaf
This model is a fine-tuned version of facebook/bart-base on the samsum dataset. It achieves the following results on the evaluation set:
- Loss: 0.5315
- Rouge1: 0.4864
- Rouge2: 0.2554
- Rougel: 0.4099
- Rougelsum: 0.4099
- Gen Len: 18.2457
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- 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 |
|---|---|---|---|---|---|---|---|---|
| 0.5336 | 4.34 | 500 | 0.5418 | 0.4838 | 0.2529 | 0.4106 | 0.4104 | 18.2751 |
| 0.4117 | 8.69 | 1000 | 0.5315 | 0.4864 | 0.2554 | 0.4099 | 0.4099 | 18.2457 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 1