trainingthemodel3
This model is a fine-tuned version of abdalrahmanshahrour/AraBART-summ on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6417
- Rouge1: 0.1136
- Rouge2: 0.0429
- Rougel: 0.0938
- Rougelsum: 0.0936
- 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: 5
- eval_batch_size: 5
- 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 | 31 | 2.9297 | 0.1141 | 0.0449 | 0.0941 | 0.0942 | 20.0 |
| No log | 2.0 | 62 | 2.7345 | 0.1099 | 0.0426 | 0.0908 | 0.0908 | 20.0 |
| No log | 3.0 | 93 | 2.6680 | 0.1123 | 0.0428 | 0.093 | 0.0929 | 20.0 |
| No log | 4.0 | 124 | 2.6417 | 0.1136 | 0.0429 | 0.0938 | 0.0936 | 20.0 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3