my_awesome_opus_books_model_m2m100

This model is a fine-tuned version of facebook/m2m100_418M on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.7192
• Bleu: 22.3585
• Gen Len: 35.9279

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: 32
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
2.0986	1.0	2337	1.9254	19.3694	36.3489
1.8708	2.0	4674	1.8318	20.6503	36.5202
1.737	3.0	7011	1.7828	21.2433	36.4866
1.6257	4.0	9348	1.7539	21.6358	36.1006
1.5325	5.0	11685	1.7314	21.6898	35.7656
1.4575	6.0	14022	1.7253	22.0772	35.8757
1.4069	7.0	16359	1.7197	22.1575	35.8489
1.3612	8.0	18696	1.7187	22.3019	36.1213
1.316	9.0	21033	1.7177	22.3979	36.083
1.2842	10.0	23370	1.7192	22.3585	35.9279

Framework versions

• Transformers 4.52.4
• Pytorch 2.7.1+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1