metadata
license: apache-2.0
base_model: riotu-lab/ArabianGPT-03B
tags:
- generated_from_trainer
metrics:
- bleu
- rouge
model-index:
- name: res_nw_irq_03
results: []
res_nw_irq_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: 0.9735
- Bleu: 0.3759
- Rouge1: 0.5621
- Rouge2: 0.3073
- Rougel: 0.5603
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 |
|---|---|---|---|---|---|---|---|
| 1.1923 | 1.0 | 1057 | 0.9735 | 0.3759 | 0.5621 | 0.3073 | 0.5603 |
| 0.3956 | 2.0 | 2114 | 1.2529 | 0.4146 | 0.6342 | 0.3777 | 0.6330 |
| 0.2578 | 3.0 | 3171 | 1.1432 | 0.4178 | 0.6356 | 0.3887 | 0.6341 |
| 0.1771 | 4.0 | 4228 | 1.3314 | 0.4209 | 0.6564 | 0.4083 | 0.6546 |
| 0.1337 | 5.0 | 5285 | 1.3444 | 0.4256 | 0.6508 | 0.4061 | 0.6495 |
| 0.1118 | 6.0 | 6342 | 1.3693 | 0.4248 | 0.6534 | 0.4079 | 0.6523 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1