<!-- 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-e6
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: 0.4903
- Rouge1: 66.541
- Rouge2: 62.0799
- Rougel: 65.123
- Rougelsum: 66.0849
- 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: 6
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 409 | 0.4982 | 64.0814 | 56.458 | 61.787 | 62.5761 | 20.0 |
0.5699 | 2.0 | 818 | 0.4216 | 65.1935 | 59.1949 | 63.3361 | 64.071 | 20.0 |
0.1953 | 3.0 | 1227 | 0.4284 | 66.1645 | 61.4297 | 64.8168 | 65.4799 | 20.0 |
0.1025 | 4.0 | 1636 | 0.4722 | 65.4591 | 60.807 | 64.1694 | 64.8935 | 20.0 |
0.0765 | 5.0 | 2045 | 0.5023 | 65.8001 | 61.49 | 64.7804 | 65.6771 | 20.0 |
0.0765 | 6.0 | 2454 | 0.4903 | 66.541 | 62.0799 | 65.123 | 66.0849 | 20.0 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1