metadata
license: apache-2.0
base_model: riotu-lab/ArabianGPT-03B
tags:
- generated_from_trainer
metrics:
- bleu
- rouge
model-index:
- name: res_nw_lev_03
results: []
res_nw_lev_03
This model is a fine-tuned version of riotu-lab/ArabianGPT-03B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3660
- Bleu: 0.4889
- Rouge1: 0.7442
- Rouge2: 0.5302
- Rougel: 0.7434
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 20.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Rouge1 | Rouge2 | Rougel |
|---|---|---|---|---|---|---|---|
| 0.6345 | 1.0 | 5062 | 0.4249 | 0.4054 | 0.6718 | 0.4168 | 0.6706 |
| 0.3258 | 2.0 | 10124 | 0.3824 | 0.4443 | 0.7135 | 0.4800 | 0.7124 |
| 0.2266 | 3.0 | 15186 | 0.3660 | 0.4889 | 0.7442 | 0.5302 | 0.7434 |
| 0.1702 | 4.0 | 20248 | 0.3713 | 0.5217 | 0.7592 | 0.5618 | 0.7584 |
| 0.1405 | 5.0 | 25310 | 0.3809 | 0.5411 | 0.7671 | 0.5785 | 0.7663 |
| 0.1253 | 6.0 | 30372 | 0.3939 | 0.5539 | 0.7718 | 0.5899 | 0.7710 |
| 0.1166 | 7.0 | 35434 | 0.3990 | 0.5536 | 0.7745 | 0.5942 | 0.7737 |
| 0.1107 | 8.0 | 40496 | 0.4050 | 0.5608 | 0.7770 | 0.5994 | 0.7763 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1