bart-model
This model is a fine-tuned version of philschmid/bart-large-cnn-samsum on the None dataset.
It achieves the following results on the evaluation set:
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- 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: 500
- num_epochs: 10
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
| 1.487 |
0.8 |
10 |
1.2019 |
| 1.3092 |
1.61 |
20 |
0.9905 |
| 1.0316 |
2.41 |
30 |
0.7841 |
| 0.8111 |
3.22 |
40 |
0.6587 |
| 0.7191 |
4.02 |
50 |
0.5964 |
| 0.5906 |
4.82 |
60 |
0.5613 |
| 0.5351 |
5.63 |
70 |
0.5393 |
| 0.4696 |
6.43 |
80 |
0.5429 |
| 0.4249 |
7.24 |
90 |
0.5287 |
| 0.3619 |
8.04 |
100 |
0.5577 |
| 0.3303 |
8.84 |
110 |
0.5794 |
| 0.2718 |
9.65 |
120 |
0.6169 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
