m2m100_418M_tq_fr_new_data

This model is a fine-tuned version of heisenberg1337/m2m100_418M_tq_fr_1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7732
• Bleu: 5.0521

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-06
• train_batch_size: 12
• eval_batch_size: 12
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 96
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 60

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
0.7993	1.69	100	0.7767	4.9208
0.7761	3.38	200	0.7743	4.7089
0.7723	5.06	300	0.7726	4.8445
0.7585	6.75	400	0.7720	4.8352
0.7468	8.44	500	0.7732	5.1454
0.7331	10.13	600	0.7744	4.8311
0.7301	11.81	700	0.7732	5.0521

Framework versions

• Transformers 4.32.0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.13.3