m2m100_412M_informal

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: 0.2969
• Bleu: 48.6053

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
4.1894	0.3720	500	0.3953	39.7522
0.3656	0.7440	1000	0.3265	45.0800
0.3271	1.1161	1500	0.3129	46.5153
0.2974	1.4881	2000	0.3073	47.4622
0.2953	1.8601	2500	0.3016	47.8121
0.2756	2.2321	3000	0.3008	48.1509
0.2671	2.6042	3500	0.2979	48.5266
0.263	2.9762	4000	0.2969	48.6053

Framework versions

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