rinkorn's picture
Training complete
5a84b08 verified
|
raw
history blame
1.37 kB
---
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-en-ru
tags:
- translation
- generated_from_trainer
datasets:
- opus100
model-index:
- name: marian-finetuned-opus100-en-to-ru
results: []
---
<!-- 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. -->
# marian-finetuned-opus100-en-to-ru
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ru](https://huggingface.co/Helsinki-NLP/opus-mt-en-ru) on the opus100 dataset.
It achieves the following results on the evaluation set:
- eval_loss: 1.6450
- eval_bleu: 33.5411
- eval_runtime: 173.5096
- eval_samples_per_second: 57.634
- eval_steps_per_second: 0.905
- step: 0
## 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: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.1+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0