m2m100_fr_wo_news_13_jan

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: 0.4778
• Bleu: 53.1145
• Gen Len: 18.5607

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: 8
• eval_batch_size: 8
• 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: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
0.8958	0.5468	10000	0.8148	36.0438	18.6073
0.596	1.0936	20000	0.6546	42.8013	18.4654
0.5381	1.6404	30000	0.5667	46.9194	18.5301
0.3531	2.1872	40000	0.5123	50.3914	18.6265
0.3292	2.7340	50000	0.4778	53.1151	18.5479

Framework versions

• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.2.0
• Tokenizers 0.20.3