opus-mt-en-ru-finetuned

This model is a fine-tuned version of kazandaev/opus-mt-en-ru-finetuned on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7763
• Bleu: 41.0065
• Gen Len: 29.7548

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: 1e-06
• 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
0.6903	1.0	35147	0.7779	40.9223	29.7846
0.6999	2.0	70294	0.7776	40.8267	29.8421
0.7257	3.0	105441	0.7769	40.8549	29.8765
0.7238	4.0	140588	0.7763	41.0225	29.7129
0.7313	5.0	175735	0.7763	41.0065	29.7548

Framework versions

• Transformers 4.16.2
• Pytorch 1.10.0+cu111
• Datasets 1.18.3
• Tokenizers 0.11.0