xlmr-et-en-all_shuffled-1985-test1000

This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5701
• R Squared: 0.3139
• Mae: 0.5603
• Pearson R: 0.6172

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: 1985
• 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	438	0.5588	0.3274	0.5882	0.5760
0.7153	2.0	876	0.5470	0.3416	0.5515	0.6228
0.5105	3.0	1314	0.5701	0.3139	0.5603	0.6172

Framework versions

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