ffsouza/tiny-mbart-length-128-learning_rate-2e-05-weight_decay-0.01-finetuned-en-to-ro

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

tiny-mbart-length-128-learningrate-2e-05-weightdecay-0.01-finetuned-en-to-ro

This model is a fine-tuned version of sshleifer/tiny-mbart on the wmt16enropreprocessed dataset. It achieves the following results on the evaluation set:

• —Loss: 8.4656
• —Bleu: 0.0
• —Gen Len: 20.0

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: 2e-05
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —num_epochs: 1
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.12.5
• —Pytorch 1.10.0+cu102
• —Datasets 1.15.1
• —Tokenizers 0.10.3