<!-- 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. -->
xsum_and_billsum_and_samsum_old_modern
This model is a fine-tuned version of psin/xsum_and_billsum_and_samsum_old on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.7596
- Rouge1: 0.0878
- Rouge2: 0.0206
- Rougel: 0.0683
- Rougelsum: 0.0686
- Gen Len: 19.0
- Precision: 0.1201
- Recall: -0.2057
- F1: -0.0
- Hashcode: roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.28.1)-rescaled
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: 8
- eval_batch_size: 8
- seed: 72
- 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 | Precision | Recall | F1 | Hashcode |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 26 | 3.7703 | 0.0825 | 0.0174 | 0.0661 | 0.0661 | 19.0 | 0.1104 | -0.2075 | -0.0 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.28.1)-rescaled |
| No log | 2.0 | 52 | 3.7653 | 0.0862 | 0.0191 | 0.0673 | 0.0675 | 19.0 | 0.1233 | -0.2065 | -0.0 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.28.1)-rescaled |
| No log | 3.0 | 78 | 3.7619 | 0.0872 | 0.0195 | 0.068 | 0.0684 | 19.0 | 0.1172 | -0.2082 | -0.0 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.28.1)-rescaled |
| No log | 4.0 | 104 | 3.7608 | 0.0877 | 0.0202 | 0.068 | 0.0684 | 19.0 | 0.1169 | -0.209 | -0.0 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.28.1)-rescaled |
| No log | 5.0 | 130 | 3.7600 | 0.0876 | 0.0206 | 0.0685 | 0.0687 | 19.0 | 0.1146 | -0.2074 | -0.0 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.28.1)-rescaled |
| No log | 6.0 | 156 | 3.7596 | 0.0878 | 0.0206 | 0.0683 | 0.0686 | 19.0 | 0.1201 | -0.2057 | -0.0 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.28.1)-rescaled |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
