res_nw_eg
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: 0.7316
- Bleu: 0.2459
- Rouge1: 0.6017
- Rouge2: 0.3519
- Rougel: 0.5983
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 |
---|---|---|---|---|---|---|---|
1.1436 | 1.0 | 7107 | 0.8277 | 0.1900 | 0.5212 | 0.2576 | 0.5169 |
0.7508 | 2.0 | 14214 | 0.7543 | 0.2214 | 0.5674 | 0.3108 | 0.5636 |
0.6471 | 3.0 | 21321 | 0.7338 | 0.2375 | 0.5881 | 0.3356 | 0.5845 |
0.5713 | 4.0 | 28428 | 0.7316 | 0.2459 | 0.6017 | 0.3519 | 0.5983 |
0.5097 | 5.0 | 35535 | 0.7390 | 0.2475 | 0.6058 | 0.3572 | 0.6022 |
0.4573 | 6.0 | 42642 | 0.7483 | 0.2503 | 0.6103 | 0.3618 | 0.6066 |
0.4118 | 7.0 | 49749 | 0.7636 | 0.2494 | 0.6106 | 0.3634 | 0.6070 |
0.3725 | 8.0 | 56856 | 0.7796 | 0.2507 | 0.6127 | 0.3660 | 0.6089 |
0.3375 | 9.0 | 63963 | 0.7974 | 0.2491 | 0.6112 | 0.3654 | 0.6074 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 0
Model tree for nlparabic/res_nw_eg
Base model
riotu-lab/ArabianGPT-01B
Finetuned
this model