<!-- 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-7n
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: 0.2440
- Accuracy: 0.9653
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 | 0.08 | 50 | 0.3695 | 0.8819 |
No log | 0.15 | 100 | 0.5887 | 0.8819 |
No log | 0.23 | 150 | 0.4348 | 0.8819 |
No log | 0.31 | 200 | 0.5770 | 0.8819 |
No log | 0.38 | 250 | 0.3552 | 0.9306 |
No log | 0.46 | 300 | 0.2887 | 0.9306 |
No log | 0.54 | 350 | 0.3606 | 0.9444 |
No log | 0.62 | 400 | 0.3048 | 0.9444 |
No log | 0.69 | 450 | 0.3399 | 0.9028 |
0.4278 | 0.77 | 500 | 0.3600 | 0.9236 |
0.4278 | 0.85 | 550 | 0.3100 | 0.9375 |
0.4278 | 0.92 | 600 | 0.3624 | 0.9444 |
0.4278 | 1.0 | 650 | 0.3367 | 0.9444 |
0.4278 | 1.08 | 700 | 0.2593 | 0.9444 |
0.4278 | 1.15 | 750 | 0.3215 | 0.9236 |
0.4278 | 1.23 | 800 | 0.3484 | 0.9306 |
0.4278 | 1.31 | 850 | 0.3628 | 0.9167 |
0.4278 | 1.38 | 900 | 0.3267 | 0.9444 |
0.4278 | 1.46 | 950 | 0.3527 | 0.9375 |
0.2206 | 1.54 | 1000 | 0.3661 | 0.9306 |
0.2206 | 1.62 | 1050 | 0.2522 | 0.9514 |
0.2206 | 1.69 | 1100 | 0.3929 | 0.9167 |
0.2206 | 1.77 | 1150 | 0.2960 | 0.9306 |
0.2206 | 1.85 | 1200 | 0.2918 | 0.9444 |
0.2206 | 1.92 | 1250 | 0.2746 | 0.9514 |
0.2206 | 2.0 | 1300 | 0.2954 | 0.9583 |
0.2206 | 2.08 | 1350 | 0.2634 | 0.9375 |
0.2206 | 2.15 | 1400 | 0.3141 | 0.9514 |
0.2206 | 2.23 | 1450 | 0.2427 | 0.9514 |
0.1761 | 2.31 | 1500 | 0.2440 | 0.9653 |
0.1761 | 2.38 | 1550 | 0.2204 | 0.9653 |
0.1761 | 2.46 | 1600 | 0.2171 | 0.9653 |
0.1761 | 2.54 | 1650 | 0.2676 | 0.9583 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2