metadata
license: mit
base_model: facebook/bart-large-mnli
tags:
- generated_from_trainer
model-index:
- name: bart-large-mnli-finetuned-sensical
results: []
bart-large-mnli-finetuned-sensical
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: 0.0005
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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- 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 |
|---|---|---|---|
| 0.0687 | 1.0 | 61 | 0.0165 |
| 0.0047 | 2.0 | 122 | 0.0046 |
| 0.001 | 3.0 | 183 | 0.0009 |
| 0.0006 | 4.0 | 244 | 0.0004 |
| 0.0004 | 5.0 | 305 | 0.0005 |
| 0.0021 | 6.0 | 366 | 0.0006 |
| 0.0003 | 7.0 | 427 | 0.0006 |
| 0.0003 | 8.0 | 488 | 0.0006 |
| 0.0009 | 9.0 | 549 | 0.0007 |
| 0.0003 | 10.0 | 610 | 0.0005 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1