{ "spec": "3068abfcdad808f4fdda1962499e9aa5b82b3c882dfe8151753cba55df57783b", "method": "encoder", "source": "answerdotai/ModernBERT-large", "fine_tuned_from": null, "dataset": "/home/nicks/rz4/data/ragzilla4", "kinds": [ "relevant" ], "kind_targets": { "relevant": "subset" }, "skipped": {}, "training": { "epochs": 1, "learning_rate": 3e-05, "head_learning_rate": 0.0001, "batch_size": null, "batch_tokens": 32768, "world_size": 8, "steps": 2602, "loss": "focal", "focal_gamma": 2.0, "focal_alpha": 0.5, "brier": 0.1, "warmup": 0.05, "weight_decay": 0.01, "layout": "packed", "head": "mlp", "attention": "sdpa", "gradient_checkpointing": false, "max_length": 8192, "max_chars": 4000, "train_rows": 585506, "seed": 7, "history": [ { "step": 1000, "epoch": 1, "loss": 0.03816812379019601, "decisions": 2000, "decisions_per_second": 52.4, "relevant": { "kept_right": 1611, "wrongly_kept": 254, "wrongly_dropped": 995, "dropped_right": 14906 } }, { "step": 2000, "epoch": 1, "loss": 0.026384400313771848, "decisions": 2000, "decisions_per_second": 52.4, "relevant": { "kept_right": 1727, "wrongly_kept": 307, "wrongly_dropped": 879, "dropped_right": 14853 } }, { "step": 2602, "epoch": 1, "loss": 0.02924899397707618, "decisions": 2000, "decisions_per_second": 52.7, "relevant": { "kept_right": 1738, "wrongly_kept": 281, "wrongly_dropped": 868, "dropped_right": 14879 } } ], "seconds": 5884.5 }, "exported_from": "/home/nicks/rz4/runs/ragzilla4-raw" }