m2m100_418M_de_formal

This model is a fine-tuned version of facebook/m2m100_418M on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3616
• Bleu: 40.1795

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: 32
• eval_batch_size: 8
• 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
• lr_scheduler_warmup_steps: 500
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
4.0084	0.3551	500	0.4763	29.8731
0.4476	0.7102	1000	0.3983	34.9967
0.4079	1.0653	1500	0.3831	37.2874
0.3623	1.4205	2000	0.3744	38.4223
0.3564	1.7756	2500	0.3691	39.2808
0.3434	2.1307	3000	0.3661	39.6976
0.3227	2.4858	3500	0.3630	40.0068
0.3196	2.8409	4000	0.3616	40.1795

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0