encoder_decoder_es

• Loss: 7.8773
• Rouge2 Precision: 0.002
• Rouge2 Recall: 0.0116
• Rouge2 Fmeasure: 0.0034

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 0.003
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.12.3
• Pytorch 1.9.1
• Datasets 1.15.1
• Tokenizers 0.10.3