xlmr-ne-en-train_shuffled-1986-test2000

This model is a fine-tuned version of xlm-roberta-base on the wmt20_mlqe_task1 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5106
• R Squared: 0.2714
• Mae: 0.5502
• Pearson R: 0.6939

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
• train_batch_size: 16
• eval_batch_size: 16
• seed: 1986
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	R Squared	Mae	Pearson R
No log	1.0	375	0.4648	0.3368	0.5563	0.6413
0.7538	2.0	750	0.3918	0.4409	0.4969	0.6785
0.5265	3.0	1125	0.5106	0.2714	0.5502	0.6939

Framework versions

• Transformers 4.34.1
• Pytorch 2.0.1+cu117
• Datasets 2.14.6
• Tokenizers 0.14.1