bart-large-mnli-aitools
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: 0.1230
- Accuracy: 0.9722
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 | 0.31 | 50 | 0.5212 | 0.8611 |
No log | 0.61 | 100 | 0.5397 | 0.8333 |
No log | 0.92 | 150 | 0.0322 | 0.9722 |
No log | 1.23 | 200 | 0.6025 | 0.8611 |
No log | 1.53 | 250 | 0.0708 | 0.9722 |
No log | 1.84 | 300 | 0.3260 | 0.9444 |
No log | 2.15 | 350 | 0.0014 | 1.0 |
No log | 2.45 | 400 | 0.0017 | 1.0 |
No log | 2.76 | 450 | 0.0375 | 0.9722 |
0.3402 | 3.07 | 500 | 0.1230 | 0.9722 |
0.3402 | 3.37 | 550 | 0.0077 | 1.0 |
0.3402 | 3.68 | 600 | 0.1569 | 0.9722 |
0.3402 | 3.99 | 650 | 0.0721 | 0.9722 |
0.3402 | 4.29 | 700 | 0.1426 | 0.9722 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
- Downloads last month
- 4
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.