metadata
license: apache-2.0
base_model: riotu-lab/ArabianGPT-01B
tags:
- generated_from_trainer
metrics:
- bleu
- rouge
model-index:
- name: res_nw_irq
results: []
res_nw_irq
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: 1.0817
- Bleu: 0.3500
- Rouge1: 0.5071
- Rouge2: 0.2486
- Rougel: 0.5048
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 |
|---|---|---|---|---|---|---|---|
| 1.7995 | 1.0 | 1057 | 1.1332 | 0.3157 | 0.4552 | 0.2017 | 0.4531 |
| 0.5906 | 2.0 | 2114 | 1.0817 | 0.3500 | 0.5071 | 0.2486 | 0.5048 |
| 0.484 | 3.0 | 3171 | 1.1038 | 0.3592 | 0.5330 | 0.2737 | 0.5303 |
| 0.4017 | 4.0 | 4228 | 1.1117 | 0.3665 | 0.5471 | 0.2915 | 0.5449 |
| 0.3357 | 5.0 | 5285 | 1.1361 | 0.3695 | 0.5552 | 0.3010 | 0.5533 |
| 0.2832 | 6.0 | 6342 | 1.1257 | 0.3721 | 0.5607 | 0.3089 | 0.5584 |
| 0.2404 | 7.0 | 7399 | 1.1581 | 0.3740 | 0.5622 | 0.3102 | 0.5600 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1