bart-large-mnli-aitools-3n
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: 0.2499
- Accuracy: 0.9583
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 | 0.15 | 50 | 0.3391 | 0.9028 |
No log | 0.31 | 100 | 0.5318 | 0.9028 |
No log | 0.46 | 150 | 0.3007 | 0.9444 |
No log | 0.62 | 200 | 0.9533 | 0.8611 |
No log | 0.77 | 250 | 0.2389 | 0.9583 |
No log | 0.92 | 300 | 0.2735 | 0.9444 |
No log | 1.08 | 350 | 0.3416 | 0.9444 |
No log | 1.23 | 400 | 0.2120 | 0.9583 |
No log | 1.38 | 450 | 0.2039 | 0.9583 |
0.3562 | 1.54 | 500 | 0.2499 | 0.9583 |
0.3562 | 1.69 | 550 | 0.2237 | 0.9583 |
0.3562 | 1.85 | 600 | 0.2532 | 0.9444 |
0.3562 | 2.0 | 650 | 0.2371 | 0.9444 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
- Downloads last month
- 2
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.