activations: Tanh
batch_size: 16
class_identifier: unified_metric
cross_entropy_weights: null
dropout: 0.1
encoder_learning_rate: 1.0693928308577897e-05
encoder_model: XLM-RoBERTa
error_labels:
- minor
- major
final_activation: null
hidden_sizes:
- 3072
- 1024
input_segments:
- mt
- src
keep_embeddings_frozen: true
layer_norm: true
layer_transformation: sparsemax
layerwise_decay: 0.95
learning_rate: 0.00010802282446961044
load_pretrained_weights: true
local_files_only: false
loss: mse
loss_lambda: 0.65
nr_frozen_epochs: 0.3
optimizer: AdamW
pretrained_model: microsoft/infoxlm-large
sent_layer: mix
train_data:
- data/data-42-final/train.csv
validation_data:
- data/data-42-final/val.csv
warmup_steps: 0
word_layer: 24
word_level_training: false