<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
ar2enCkptfromgendata_02
This model is a fine-tuned version of Shularp/ar2enCkptfromgendata_01 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3127
- Bleu: 75.0762
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|---|---|---|---|---|
| 0.4027 | 1.0 | 151 | 0.2742 | 78.6168 |
| 0.2541 | 2.0 | 302 | 0.2781 | 78.3237 |
| 0.2319 | 3.0 | 453 | 0.2858 | 77.7606 |
| 0.1957 | 4.0 | 604 | 0.2937 | 76.5858 |
| 0.1372 | 5.0 | 755 | 0.2992 | 76.1158 |
| 0.1413 | 6.0 | 906 | 0.3047 | 75.7260 |
| 0.12 | 7.0 | 1057 | 0.3099 | 75.6321 |
| 0.1314 | 8.0 | 1208 | 0.3110 | 75.1247 |
| 0.0864 | 9.0 | 1359 | 0.3118 | 75.3267 |
| 0.0873 | 10.0 | 1510 | 0.3127 | 75.0762 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
