metadata
license: mit
base_model: facebook/bart-large-mnli
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: bart-large-mnli_17082023T115544
results: []
bart-large-mnli_17082023T115544
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: 0.4791
- Accuracy: 0.9394
- F1: 0.9528
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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 | 0.2605 | 0.9095 | 0.9307 |
| No log | 2.0 | 284 | 0.2664 | 0.9183 | 0.9389 |
| No log | 2.99 | 426 | 0.2562 | 0.9315 | 0.9467 |
| 0.193 | 4.0 | 569 | 0.3992 | 0.9315 | 0.9458 |
| 0.193 | 5.0 | 711 | 0.4185 | 0.9315 | 0.9441 |
| 0.193 | 6.0 | 853 | 0.4918 | 0.9306 | 0.9462 |
| 0.193 | 6.99 | 995 | 0.4584 | 0.9385 | 0.9526 |
| 0.0101 | 8.0 | 1138 | 0.4611 | 0.9367 | 0.9503 |
| 0.0101 | 9.0 | 1280 | 0.4739 | 0.9385 | 0.9518 |
| 0.0101 | 9.98 | 1420 | 0.4791 | 0.9394 | 0.9528 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3