cspl_translation

This model is a fine-tuned version of facebook/bart-large on qanastek/EMEA-V3, "cs-pl". It achieves the following results on the evaluation set:

• Loss: 0.5057
• Bleu: 6.0589
• Gen Len: 17.9412

Model description

Fine-tuned model for Czech to Polish translation

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: 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: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
0.6935	1.0	20158	0.6522	5.4056	18.0813
0.5478	2.0	40316	0.5442	5.7921	18.0018
0.4513	3.0	60474	0.5057	6.0589	17.9412

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3