9a276f23b527d73f386662a21630ac2d

This model is a fine-tuned version of google/mt5-large on the Helsinki-NLP/opus_books [en-pt] dataset. It achieves the following results on the evaluation set:

• Loss: 26.9283
• Data Size: 0.125
• Epoch Runtime: 10.0441
• Bleu: 0.0222

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
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Bleu
No log	0	0	21.7681	0	2.1128	0.0410
No log	1	35	22.6730	0.0078	2.6055	0.0335
No log	2	70	23.1894	0.0156	3.9717	0.0321
No log	3	105	26.2846	0.0312	6.0363	0.0232
No log	4	140	27.3712	0.0625	7.9466	0.0288
No log	5	175	26.9283	0.125	10.0441	0.0222

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.2.0
• Tokenizers 0.22.1