metadata
library_name: transformers
license: mit
base_model: sophiebui/ru-en_mtmodel
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: ru-en_mtmodel_v1
results: []
ru-en_mtmodel_v1
This model is a fine-tuned version of sophiebui/ru-en_mtmodel on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1134
- Bleu: 43.1972
- Gen Len: 30.6216
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 226 | 1.2067 | 39.6459 | 30.2432 |
| No log | 2.0 | 452 | 1.1232 | 40.3147 | 30.8649 |
| 1.2106 | 3.0 | 678 | 1.1134 | 43.1972 | 30.6216 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1