en-ru_mtmodel_v1

This model is a fine-tuned version of sophiebui/en-ru_mtmodel on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8443
• Bleu: 44.9157
• Gen Len: 32.0811

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	226	0.9394	37.9005	31.5405
No log	2.0	452	0.8537	43.6072	32.3514
0.935	3.0	678	0.8400	46.3652	31.8108
0.935	4.0	904	0.8482	44.6002	31.973
0.4432	5.0	1130	0.8443	44.9157	32.0811

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1