bart-large-mnli-aitools-alln
This model is a fine-tuned version of facebook/bart-large-mnli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1724
- Accuracy: 0.9701
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.02 | 50 | 0.2765 | 0.9701 |
| No log | 0.03 | 100 | 0.2424 | 0.9701 |
| No log | 0.05 | 150 | 0.2133 | 0.9701 |
| No log | 0.07 | 200 | 0.1323 | 0.9701 |
| No log | 0.09 | 250 | 0.1962 | 0.9701 |
| No log | 0.1 | 300 | 0.2699 | 0.9701 |
| No log | 0.12 | 350 | 0.2045 | 0.9701 |
| No log | 0.14 | 400 | 0.2044 | 0.9701 |
| No log | 0.16 | 450 | 0.1970 | 0.9701 |
| 0.1812 | 0.17 | 500 | 0.1724 | 0.9701 |
| 0.1812 | 0.19 | 550 | 0.2018 | 0.9701 |
| 0.1812 | 0.21 | 600 | 0.1632 | 0.9701 |
| 0.1812 | 0.23 | 650 | 0.1745 | 0.9701 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2