# CNN/DailyMail ModernBERT Pointwise Run

- model_size: `large`
- model_name: `answerdotai/ModernBERT-large`
- resolved_model_name: `/lustre/fsmisc/dataset/HuggingFace_Models/answerdotai/ModernBERT-large`
- target_mode: `model_balanced`
- target_field: `salience_score_model_balanced`
- 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: `4096`
- learning_rate: `2e-05`
- weight_decay: `0.01`
- num_train_epochs: `3.0`
- warmup_ratio: `0.06`
- per_device_train_batch_size: `2`
- per_device_eval_batch_size: `2`
- gradient_accumulation_steps: `8`
- effective_train_batch_size: `16`
- eval_strategy: `epoch`
- save_strategy: `epoch`
- early_stopping_patience: `2`
- bf16: `True`
- fp16: `False`
- gradient_checkpointing: `True`

## Eval Metrics

- epoch: `3.0`
- eval_article_ndcg_at_3: `0.9210334527568008`
- eval_article_ndcg_at_5: `0.91633834365026`
- eval_article_spearman: `0.7742035575368817`
- eval_loss: `0.022096654400229454`
- eval_mae: `0.10976211726665497`
- eval_pearson: `0.8568720334438967`
- eval_rmse: `0.1486494345775639`
- eval_runtime: `132.4829`
- eval_samples_per_second: `51.275`
- eval_spearman: `0.856351157285778`
- eval_steps_per_second: `25.641`