barto_exp1_10partition_modelo_asl15000

This model is a fine-tuned version of vgaraujov/bart-base-spanish on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.2796
• eval_model_preparation_time: 0.0321
• eval_bleu_msl: 0
• eval_bleu_1_msl: 0.7850
• eval_bleu_2_msl: 0.6829
• eval_bleu_3_msl: 0.6097
• eval_bleu_4_msl: 0.5306
• eval_ter_msl: 26.7477
• eval_bleu_asl: 0
• eval_bleu_1_asl: 0.9851
• eval_bleu_2_asl: 0.9729
• eval_bleu_3_asl: 0.9569
• eval_bleu_4_asl: 0.9376
• eval_ter_asl: 1.8219
• eval_runtime: 19.8245
• eval_samples_per_second: 75.664
• eval_steps_per_second: 1.211
• epoch: 10.3093
• step: 3866

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: 0.0001
• train_batch_size: 32
• eval_batch_size: 64
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 30
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.57.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1