activations: Tanh
batch_size: 4
class_identifier: unified_metric
continuous_word_labels: false
dropout: 0.15
encoder_learning_rate: 1.0e-05
encoder_model: RoBERTa
final_activation: null
hidden_sizes:
- 384
initalize_pretrained_unified_weights: true
input_segments:
- edit_id_simplified
- edit_id_original
keep_embeddings_frozen: true
layer: mix
layer_norm: true
layer_transformation: sparsemax
layerwise_decay: 0.95
learning_rate: 3.1e-05
load_pretrained_weights: true
loss: mse
loss_lambda: 0.9
nr_frozen_epochs: 0.3
optimizer: AdamW
pool: avg
pretrained_model: roberta-large
score_target: lens_score
sent_layer: mix
span_targets:
- edit_id_simplified
- edit_id_original
span_tokens:
- bad
warmup_steps: 0
word_layer: 24
word_level_training: true
word_weights:
- 0.1
- 0.9