metadata
license: mit
base_model: philschmid/bart-large-cnn-samsum
tags:
- generated_from_trainer
model-index:
- name: bart-original
results: []
bart-original
This model is a fine-tuned version of philschmid/bart-large-cnn-samsum on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7637
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7047 | 0.99 | 16 | 1.2455 |
| 1.1189 | 1.98 | 32 | 0.8783 |
| 0.9025 | 2.97 | 48 | 0.7032 |
| 0.661 | 3.95 | 64 | 0.6342 |
| 0.7341 | 4.94 | 80 | 0.6271 |
| 0.5526 | 5.99 | 97 | 0.6232 |
| 0.4139 | 6.98 | 113 | 0.6405 |
| 0.518 | 7.97 | 129 | 0.6887 |
| 0.3311 | 8.96 | 145 | 0.7313 |
| 0.196 | 9.88 | 160 | 0.7637 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3