metadata
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: opus-mt-ru-en-finetuned
results: []
opus-mt-ru-en-finetuned
This model is a fine-tuned version of kazandaev/opus-mt-ru-en-finetuned on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1124
- Bleu: 39.6748
- Gen Len: 26.0628
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: 49
- eval_batch_size: 24
- 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 | Gen Len |
|---|---|---|---|---|---|
| 1.172 | 1.0 | 35147 | 1.2856 | 34.1563 | 26.1419 |
| 1.1403 | 2.0 | 70294 | 1.2595 | 34.8515 | 26.198 |
| 1.0997 | 3.0 | 105441 | 1.2305 | 35.7998 | 26.115 |
| 1.0711 | 4.0 | 140588 | 1.2111 | 36.5266 | 26.17 |
| 1.0392 | 5.0 | 175735 | 1.1953 | 36.9092 | 26.0507 |
| 1.0109 | 6.0 | 210882 | 1.1662 | 37.7652 | 26.0546 |
| 0.9878 | 7.0 | 246029 | 1.1542 | 38.4936 | 25.9766 |
| 0.9573 | 8.0 | 281176 | 1.1298 | 39.06 | 26.1242 |
| 0.9263 | 9.0 | 316323 | 1.1214 | 39.5778 | 26.0582 |
| 0.9132 | 10.0 | 351470 | 1.1124 | 39.6748 | 26.0628 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.0+cu111
- Datasets 1.18.3
- Tokenizers 0.11.0