sibyl/BART-large-commongen

<!-- 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. -->

BART-large-commongen

This model is a fine-tuned version of facebook/bart-large on the gem dataset. It achieves the following results on the evaluation set:

• —Loss: 1.1409
• —Spice: 0.4009

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
• —trainbatchsize: 32
• —evalbatchsize: 32
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 1000
• —training_steps: 6317

Training results

Framework versions

• —Transformers 4.9.2
• —Pytorch 1.9.0+cu102
• —Datasets 1.11.1.dev0
• —Tokenizers 0.10.3