metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
model-index:
- name: Bart_Complaint_V3
results: []
Bart_Complaint_V3
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1765
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: 5e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3153 | 1.0 | 212 | 0.2400 |
| 0.2527 | 2.0 | 424 | 0.2025 |
| 0.1983 | 3.0 | 636 | 0.1864 |
| 0.1487 | 4.0 | 848 | 0.1765 |
| 0.1399 | 5.0 | 1060 | 0.1768 |
| 0.1169 | 6.0 | 1272 | 0.1841 |
| 0.0955 | 7.0 | 1484 | 0.1861 |
| 0.0835 | 8.0 | 1696 | 0.2001 |
| 0.0695 | 9.0 | 1908 | 0.2039 |
| 0.054 | 10.0 | 2120 | 0.2093 |
Framework versions
- Transformers 4.41.1
- Pytorch 1.13.1+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1