Full_NVP2500

This model is a fine-tuned version of mika5883/Pretrained_ReCl8 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1406
• Bleu: 91.1196
• Gen Len: 23.5192

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: 3.83229e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	313	0.1551	90.3903	23.52
0.2682	2.0	626	0.1406	91.1196	23.5192

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2