<!-- 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-model2-1510-e4
This model is a fine-tuned version of theojolliffe/bart-paraphrase-v4-e1-feedback on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4317
- Rouge1: 66.2469
- Rouge2: 61.9187
- Rougel: 64.975
- Rougelsum: 65.8105
- Gen Len: 20.0
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 | 409 | 0.4893 | 63.6678 | 55.1935 | 61.0167 | 62.2738 | 20.0 |
| 0.5697 | 2.0 | 818 | 0.4261 | 65.5028 | 59.8267 | 63.9004 | 64.5644 | 20.0 |
| 0.1918 | 3.0 | 1227 | 0.4179 | 66.7784 | 61.5052 | 64.3163 | 65.6703 | 20.0 |
| 0.098 | 4.0 | 1636 | 0.4317 | 66.2469 | 61.9187 | 64.975 | 65.8105 | 20.0 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1
