metadata
license: apache-2.0
base_model: riotu-lab/ArabianGPT-01B
tags:
- generated_from_trainer
metrics:
- bleu
- rouge
model-index:
- name: res_nw_gulf
results: []
res_nw_gulf
This model is a fine-tuned version of riotu-lab/ArabianGPT-01B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4179
- Bleu: 0.4093
- Rouge1: 0.6309
- Rouge2: 0.3587
- Rougel: 0.6298
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 |
|---|---|---|---|---|---|---|---|
| 1.8893 | 1.0 | 836 | 0.4815 | 0.3818 | 0.5345 | 0.2557 | 0.5335 |
| 0.4211 | 2.0 | 1672 | 0.4301 | 0.3947 | 0.5886 | 0.3084 | 0.5877 |
| 0.3307 | 3.0 | 2508 | 0.4181 | 0.4098 | 0.6130 | 0.3382 | 0.6119 |
| 0.2641 | 4.0 | 3344 | 0.4179 | 0.4093 | 0.6309 | 0.3587 | 0.6298 |
| 0.2135 | 5.0 | 4180 | 0.4242 | 0.4125 | 0.6373 | 0.3691 | 0.6359 |
| 0.1765 | 6.0 | 5016 | 0.4300 | 0.4156 | 0.6466 | 0.3830 | 0.6453 |
| 0.1492 | 7.0 | 5852 | 0.4348 | 0.4188 | 0.6460 | 0.3852 | 0.6449 |
| 0.1293 | 8.0 | 6688 | 0.4431 | 0.4190 | 0.6493 | 0.3895 | 0.6482 |
| 0.1155 | 9.0 | 7524 | 0.4497 | 0.4202 | 0.6498 | 0.3905 | 0.6488 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1