CNN/DailyMail Pointwise Sentence Scorer Run
- model_size:
base - model_name:
BAAI/bge-m3 - resolved_model_name:
/lustre/fsmisc/dataset/HuggingFace_Models/BAAI/bge-m3 - target_mode:
model_balanced - target_field:
salience_score_model_balanced - loss_type:
mse - score_transform:
identity - article_balanced:
False - multihead:
False - multihead_names:
[] - score_aggregation:
scalar - eval_loss_semantics:
mse - input_field:
model_input_text - train_file:
data/CNN_DM/representative_subset/salience_generation/recovery_f2_all6/sentence_scorer_data/modernbert_pointwise/train.jsonl - dev_file:
data/CNN_DM/representative_subset/salience_generation/recovery_f2_all6/sentence_scorer_data/modernbert_pointwise/dev.jsonl - train_rows:
59643 - dev_rows:
6793 - train_articles:
1000 - dev_articles:
200 - max_length:
4608 - attn_implementation:
eager - learning_rate:
1e-05 - weight_decay:
0.01 - num_train_epochs:
3.0 - warmup_ratio:
0.06 - per_device_train_batch_size:
1 - per_device_eval_batch_size:
2 - gradient_accumulation_steps:
16 - effective_train_batch_size:
16 - eval_strategy:
steps - save_strategy:
steps - early_stopping_patience:
5 - bf16:
True - fp16:
False - gradient_checkpointing:
True
Eval Metrics
- epoch:
2.3068926781013697 - eval_article_ndcg_at_3:
0.8912648201819963 - eval_article_ndcg_at_5:
0.8810350116689233 - eval_article_spearman:
0.6913812102325307 - eval_loss:
0.03421084210276604 - eval_mae:
0.13758335639960514 - eval_mse:
0.03421084379263475 - eval_pearson:
0.7992694624484324 - eval_rmse:
0.18496173602298058 - eval_runtime:
136.7425 - eval_samples_per_second:
49.677 - eval_spearman:
0.7975893083370461 - eval_steps_per_second:
24.842