<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bart-model2-0810
This model is a fine-tuned version of theojolliffe/bart-model2-1409 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2627
- Rouge1: 58.8322
- Rouge2: 56.2696
- Rougel: 58.8934
- Rougelsum: 58.3106
- Gen Len: 19.2222
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 169 | 0.3839 | 53.2948 | 45.0992 | 52.1785 | 53.8143 | 18.0 |
| No log | 2.0 | 338 | 0.3099 | 55.227 | 49.17 | 55.1602 | 55.6483 | 17.8889 |
| 0.3831 | 3.0 | 507 | 0.2566 | 56.6535 | 52.9359 | 56.1953 | 56.0607 | 18.8889 |
| 0.3831 | 4.0 | 676 | 0.2627 | 58.8322 | 56.2696 | 58.8934 | 58.3106 | 19.2222 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.2
- Tokenizers 0.12.1
