<!-- 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. -->
trainingthemodel
This model is a fine-tuned version of abdalrahmanshahrour/arabartsummarization on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2622
- Rouge1: 0.1194
- Rouge2: 0.0483
- Rougel: 0.0975
- Rougelsum: 0.0977
- 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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 154 | 2.7120 | 0.1178 | 0.0452 | 0.0966 | 0.0966 | 20.0 |
| No log | 2.0 | 308 | 2.4175 | 0.1202 | 0.0482 | 0.0995 | 0.0998 | 20.0 |
| No log | 3.0 | 462 | 2.3151 | 0.1181 | 0.0468 | 0.0963 | 0.0966 | 20.0 |
| 3.034 | 4.0 | 616 | 2.2622 | 0.1194 | 0.0483 | 0.0975 | 0.0977 | 20.0 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
