millid-medium-v1 / training_log.jsonl
byamasupatrick's picture
MillID medium, step 56000
8377b1e verified
Raw History Blame Contribute Delete
3.17 kB
{"step": 2000, "loss": 1.86789, "macro_f1": 0.79235, "top1_accuracy": 0.79797, "top3_accuracy": 0.92062}
{"step": 4000, "loss": 1.50355, "macro_f1": 0.8932, "top1_accuracy": 0.89507, "top3_accuracy": 0.96682}
{"step": 6000, "loss": 1.37135, "macro_f1": 0.91384, "top1_accuracy": 0.91522, "top3_accuracy": 0.97436}
{"step": 8000, "loss": 1.28554, "macro_f1": 0.92505, "top1_accuracy": 0.92703, "top3_accuracy": 0.97825}
{"step": 10000, "loss": 1.27827, "macro_f1": 0.92703, "top1_accuracy": 0.92841, "top3_accuracy": 0.97841}
{"step": 12000, "loss": 1.20079, "macro_f1": 0.93424, "top1_accuracy": 0.93555, "top3_accuracy": 0.98061}
{"step": 14000, "loss": 1.21474, "macro_f1": 0.93586, "top1_accuracy": 0.93728, "top3_accuracy": 0.98181}
{"step": 16000, "loss": 1.16406, "macro_f1": 0.94008, "top1_accuracy": 0.94114, "top3_accuracy": 0.98294}
{"step": 18000, "loss": 1.18302, "macro_f1": 0.9409, "top1_accuracy": 0.94234, "top3_accuracy": 0.98426}
{"step": 20000, "loss": 1.19716, "macro_f1": 0.94238, "top1_accuracy": 0.94378, "top3_accuracy": 0.98297}
{"step": 22000, "loss": 1.15475, "macro_f1": 0.94574, "top1_accuracy": 0.94695, "top3_accuracy": 0.98413}
{"step": 24000, "loss": 1.13328, "macro_f1": 0.94524, "top1_accuracy": 0.94642, "top3_accuracy": 0.98517}
{"step": 26000, "loss": 1.14454, "macro_f1": 0.94883, "top1_accuracy": 0.95016, "top3_accuracy": 0.98542}
{"step": 28000, "loss": 1.13161, "macro_f1": 0.94798, "top1_accuracy": 0.94893, "top3_accuracy": 0.98564}
{"step": 30000, "loss": 1.13735, "macro_f1": 0.94964, "top1_accuracy": 0.95098, "top3_accuracy": 0.98633}
{"step": 32000, "loss": 1.13146, "macro_f1": 0.95158, "top1_accuracy": 0.95267, "top3_accuracy": 0.98668}
{"step": 34000, "loss": 1.11926, "macro_f1": 0.95274, "top1_accuracy": 0.95403, "top3_accuracy": 0.98686}
{"step": 36000, "loss": 1.15683, "macro_f1": 0.95348, "top1_accuracy": 0.95478, "top3_accuracy": 0.98781}
{"step": 38000, "loss": 1.14514, "macro_f1": 0.95557, "top1_accuracy": 0.95676, "top3_accuracy": 0.98749}
{"step": 40000, "loss": 1.12537, "macro_f1": 0.95683, "top1_accuracy": 0.95814, "top3_accuracy": 0.98844}
{"step": 42000, "loss": 1.16073, "macro_f1": 0.95802, "top1_accuracy": 0.95912, "top3_accuracy": 0.98913}
{"step": 44000, "loss": 1.11823, "macro_f1": 0.95665, "top1_accuracy": 0.9578, "top3_accuracy": 0.98906}
{"step": 46000, "loss": 1.13981, "macro_f1": 0.95912, "top1_accuracy": 0.96037, "top3_accuracy": 0.98919}
{"step": 48000, "loss": 1.10609, "macro_f1": 0.96015, "top1_accuracy": 0.96128, "top3_accuracy": 0.98976}
{"step": 50000, "loss": 1.09781, "macro_f1": 0.96095, "top1_accuracy": 0.96207, "top3_accuracy": 0.99029}
{"step": 52000, "loss": 1.09539, "macro_f1": 0.96094, "top1_accuracy": 0.96223, "top3_accuracy": 0.99042}
{"step": 54000, "loss": 1.11826, "macro_f1": 0.96193, "top1_accuracy": 0.96308, "top3_accuracy": 0.99035}
{"step": 56000, "loss": 1.08251, "macro_f1": 0.96248, "top1_accuracy": 0.96377, "top3_accuracy": 0.99038}
{"step": 58000, "loss": 1.10651, "macro_f1": 0.96167, "top1_accuracy": 0.96279, "top3_accuracy": 0.99086}
{"step": 60000, "loss": 1.09734, "macro_f1": 0.96245, "top1_accuracy": 0.96352, "top3_accuracy": 0.99117}