metadata
library_name: transformers
license: apache-2.0
base_model: moussaKam/AraBART
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: my_model_summ
results: []
my_model_summ
This model is a fine-tuned version of moussaKam/AraBART on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4884
- Rouge1: 0.0175
- Rouge2: 0.0117
- Rougel: 0.0175
- Rougelsum: 0.0171
- 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 25 | 0.6333 | 0.0175 | 0.0117 | 0.0175 | 0.0171 | 19.49 |
| No log | 2.0 | 50 | 0.5445 | 0.0175 | 0.0117 | 0.0175 | 0.0171 | 19.66 |
| No log | 3.0 | 75 | 0.4939 | 0.0175 | 0.0117 | 0.0175 | 0.0171 | 20.0 |
| No log | 4.0 | 100 | 0.4884 | 0.0175 | 0.0117 | 0.0175 | 0.0171 | 20.0 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0