metadata
license: apache-2.0
base_model: facebook/bart-large
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: BART-finetuned-on-training-knowledge
results: []
BART-finetuned-on-training-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: 2.5236
- Bleu: 3.9928
- Gen Len: 19.3964
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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 2.4789 | 1.0 | 1679 | 2.2752 | 2.7071 | 19.0929 |
| 2.1071 | 2.0 | 3358 | 2.2473 | 3.2957 | 19.5661 |
| 1.7995 | 3.0 | 5037 | 2.2643 | 3.4993 | 19.0268 |
| 1.5704 | 4.0 | 6716 | 2.3137 | 3.5091 | 19.4946 |
| 1.3954 | 5.0 | 8395 | 2.3795 | 3.7311 | 19.6589 |
| 1.223 | 6.0 | 10074 | 2.4577 | 3.874 | 19.3554 |
| 1.1262 | 7.0 | 11753 | 2.5236 | 3.9928 | 19.3964 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.13.0
- Tokenizers 0.14.1