elmamounedieye/results

nllb-wol-fr

This model is a fine-tuned version of nllb-200-1.3B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1455
• Bleu: 26.4785
• Ter: 66.6786
• Meteor: 0.4869

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Use OptimizerNames.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: 7
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Ter	Meteor
0.1089	1.0	5750	0.1009	21.0097	80.5941	0.4550
0.0719	2.0	11500	0.1005	22.6329	75.9288	0.4713
0.041	3.0	17250	0.1092	25.7456	68.2373	0.4748
0.0221	4.0	23000	0.1222	25.5689	68.6435	0.4757
0.0125	5.0	28750	0.1330	26.1980	66.2813	0.4780
0.0061	6.0	34500	0.1417	27.1850	64.7119	0.4835
0.0057	7.0	40250	0.1455	26.4785	66.6786	0.4869

Framework versions

• Transformers 4.50.0
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1