article2KW_test1_barthez-orangesum-title_finetuned_for_summurization
This model is a fine-tuned version of moussaKam/barthez-orangesum-title on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2895
- Rouge1: 0.2048
- Rouge2: 0.0600
- Rougel: 0.2053
- Rougelsum: 0.2057
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: 5.6e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 0.4512 | 1.0 | 3368 | 0.3433 | 0.2030 | 0.0642 | 0.2037 | 0.2033 |
| 0.3162 | 2.0 | 6736 | 0.3051 | 0.2109 | 0.0681 | 0.2110 | 0.2111 |
| 0.264 | 3.0 | 10104 | 0.2895 | 0.2048 | 0.0600 | 0.2053 | 0.2057 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0
- Datasets 2.3.2
- Tokenizers 0.11.0