bart-large-mnli_17082023T112818
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: 0.4287
- Accuracy: 0.9420
- F1: 0.9569
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
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
No log | 1.0 | 142 | 0.2864 | 0.8831 | 0.9196 |
No log | 2.0 | 284 | 0.2190 | 0.9350 | 0.9490 |
No log | 3.0 | 426 | 0.2682 | 0.9411 | 0.9594 |
0.204 | 4.0 | 568 | 0.3283 | 0.9367 | 0.9448 |
0.204 | 5.0 | 710 | 0.3400 | 0.9429 | 0.9592 |
0.204 | 5.99 | 852 | 0.4590 | 0.9341 | 0.9536 |
0.204 | 6.99 | 994 | 0.3945 | 0.9473 | 0.9611 |
0.0103 | 8.0 | 1137 | 0.4355 | 0.9394 | 0.9561 |
0.0103 | 9.0 | 1279 | 0.4277 | 0.9420 | 0.9574 |
0.0103 | 9.99 | 1420 | 0.4287 | 0.9420 | 0.9569 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.2
- Downloads last month
- 5