Davlan/xlm-roberta-large-finetuned-luganda

<!-- 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. -->

lug_xlmr

This model is a fine-tuned version of models/lug_xlmr/ on an unknown dataset. It achieves the following results on the evaluation set:

• —eval_loss: 0.8414
• —eval_runtime: 10.7925
• —evalsamplesper_second: 32.245
• —evalstepsper_second: 4.077
• —step: 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: 5e-05
• —trainbatchsize: 5
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 10
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —num_epochs: 3.0

Framework versions

• —Transformers 4.21.1
• —Pytorch 1.7.1+cu110
• —Datasets 1.16.1
• —Tokenizers 0.12.1