metadata
tags:
- translation
- generated_from_trainer
metrics:
- bleu
model-index:
- name: en2arCkptfromgendata_02
results: []
en2arCkptfromgendata_02
This model is a fine-tuned version of Shularp/en2arCkptfromgendata_01 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4830
- Bleu: 37.6862
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 |
|---|---|---|---|---|
| 0.5739 | 1.0 | 38 | 1.4830 | 37.6862 |
| 0.5953 | 2.0 | 76 | 1.4830 | 37.6862 |
| 0.5959 | 3.0 | 114 | 1.4830 | 37.6862 |
| 0.586 | 4.0 | 152 | 1.4830 | 37.6862 |
| 0.6381 | 5.0 | 190 | 1.4830 | 37.6862 |
| 0.6583 | 6.0 | 228 | 1.4830 | 37.6862 |
| 0.6627 | 7.0 | 266 | 1.4830 | 37.6862 |
| 0.7228 | 8.0 | 304 | 1.4830 | 37.6862 |
| 0.6493 | 9.0 | 342 | 1.4830 | 37.6862 |
| 0.6138 | 10.0 | 380 | 1.4830 | 37.6862 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3