BART-finetuned-on-training-without-knowledge
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: 2.2844
- Bleu: 2.829
- Gen Len: 19.3589
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: 3
- eval_batch_size: 3
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 2.6072 | 1.0 | 1679 | 2.3674 | 2.3478 | 19.8107 |
| 2.2177 | 2.0 | 3358 | 2.2844 | 2.829 | 19.3589 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.13.0
- Tokenizers 0.14.1
- Downloads last month
- 5
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for louistichelman/BART-finetuned-on-training-without-knowledge
Base model
facebook/bart-large