bart-large-cnn-small-xsum-3epochs
This model is a fine-tuned version of facebook/bart-large-cnn on the xsum dataset. It achieves the following results on the evaluation set:
- Loss: 1.9215
- Rouge1: 0.2948
- Rouge2: 0.102
- Rougel: 0.2136
- Rougelsum: 0.2237
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: 1.4899457508828423e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 16
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
---|---|---|---|---|---|---|---|
2.6493 | 0.64 | 8 | 2.3018 | 0.2072 | 0.038 | 0.1369 | 0.1665 |
2.1539 | 1.32 | 16 | 2.0677 | 0.2403 | 0.0689 | 0.165 | 0.1833 |
1.9295 | 1.96 | 24 | 1.9494 | 0.2779 | 0.0907 | 0.1998 | 0.209 |
1.7358 | 2.64 | 32 | 1.9215 | 0.2948 | 0.102 | 0.2136 | 0.2237 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu117
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.