<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bart-large-mnli-aitools-9n
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: 0.1279
- Accuracy: 0.9778
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 | 0.06 | 50 | 0.3407 | 0.9111 |
No log | 0.12 | 100 | 0.4275 | 0.9111 |
No log | 0.18 | 150 | 0.3695 | 0.9111 |
No log | 0.25 | 200 | 0.5053 | 0.9111 |
No log | 0.31 | 250 | 0.4133 | 0.9111 |
No log | 0.37 | 300 | 0.1484 | 0.9389 |
No log | 0.43 | 350 | 0.4724 | 0.9222 |
No log | 0.49 | 400 | 0.3731 | 0.9389 |
No log | 0.55 | 450 | 0.2616 | 0.95 |
0.4158 | 0.62 | 500 | 0.3245 | 0.9444 |
0.4158 | 0.68 | 550 | 0.1754 | 0.9611 |
0.4158 | 0.74 | 600 | 0.2185 | 0.9611 |
0.4158 | 0.8 | 650 | 0.1815 | 0.9667 |
0.4158 | 0.86 | 700 | 0.1974 | 0.95 |
0.4158 | 0.92 | 750 | 0.2370 | 0.9667 |
0.4158 | 0.98 | 800 | 0.1629 | 0.9722 |
0.4158 | 1.05 | 850 | 0.1581 | 0.9778 |
0.4158 | 1.11 | 900 | 0.0895 | 0.9778 |
0.4158 | 1.17 | 950 | 0.1237 | 0.9778 |
0.2081 | 1.23 | 1000 | 0.1279 | 0.9778 |
0.2081 | 1.29 | 1050 | 0.1284 | 0.9778 |
0.2081 | 1.35 | 1100 | 0.1418 | 0.9722 |
0.2081 | 1.41 | 1150 | 0.1998 | 0.9667 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2