t5_chv_ru_model

This model is a fine-tuned version of slone/nllb-210-v1 on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.6405
• eval_bleu: 20.8131
• eval_gen_len: 22.132
• eval_runtime: 142.5897
• eval_samples_per_second: 10.253
• eval_steps_per_second: 0.645
• epoch: 5.0
• step: 3125

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Framework versions

• Transformers 5.6.2
• Pytorch 2.5.1+cu121
• Datasets 4.8.5
• Tokenizers 0.22.2