activations: Tanh
batch_size: 4
class_identifier: regression_metric
dropout: 0.1
encoder_learning_rate: 1.0e-06
encoder_model: XLM-RoBERTa
final_activation: null
hidden_sizes:
- 3072
- 1024
keep_embeddings_frozen: true
layer: mix
layer_norm: false
layer_transformation: sparsemax
layerwise_decay: 0.95
learning_rate: 1.5e-05
loss: mse
nr_frozen_epochs: 0.3
optimizer: AdamW
pool: avg
pretrained_model: xlm-roberta-large
train_data:
- data/1720-da.csv
validation_data:
- data/wmt-ende-newstest2021.csv
- data/wmt-enru-newstest2021.csv
- data/wmt-zhen-newstest2021.csv