Update training logs at step 1000

training_logs.jsonl

@@ -20,3 +20,24 @@
 {"step": 475, "epoch": 0.2996845425867508, "time": "2026-07-08 22:08:10", "logs": {"loss": 0.10785533905029297, "grad_norm": 0.18726640939712524, "learning_rate": 1.495268138801262e-05, "epoch": 0.2996845425867508}}
 {"step": 500, "epoch": 0.31545741324921134, "time": "2026-07-08 22:08:33", "logs": {"loss": 0.08045989990234376, "grad_norm": 7.849733829498291, "learning_rate": 1.574132492113565e-05, "epoch": 0.31545741324921134}}
 {"step": 500, "epoch": 0.31545741324921134, "time": "2026-07-08 22:09:29", "logs": {"eval_loss": 0.11268972605466843, "eval_accuracy": 0.9766561514195583, "eval_precision": 0.9654959950708565, "eval_recall": 0.9886435331230284, "eval_f1": 0.976932668329177, "eval_runtime": 56.1856, "eval_samples_per_second": 56.42, "eval_steps_per_second": 3.542, "epoch": 0.31545741324921134}}
+{"step": 525, "epoch": 0.3312302839116719, "time": "2026-07-08 22:10:07", "logs": {"loss": 0.12939174652099608, "grad_norm": 7.707481861114502, "learning_rate": 1.6529968454258676e-05, "epoch": 0.3312302839116719}}
+{"step": 550, "epoch": 0.3470031545741325, "time": "2026-07-08 22:10:31", "logs": {"loss": 0.14456929206848146, "grad_norm": 1.8563039302825928, "learning_rate": 1.7318611987381703e-05, "epoch": 0.3470031545741325}}
+{"step": 575, "epoch": 0.3627760252365931, "time": "2026-07-08 22:10:53", "logs": {"loss": 0.09543749809265137, "grad_norm": 9.819541931152344, "learning_rate": 1.8107255520504733e-05, "epoch": 0.3627760252365931}}
+{"step": 600, "epoch": 0.3785488958990536, "time": "2026-07-08 22:11:15", "logs": {"loss": 0.11727660179138183, "grad_norm": 2.0916662216186523, "learning_rate": 1.889589905362776e-05, "epoch": 0.3785488958990536}}
+{"step": 625, "epoch": 0.3943217665615142, "time": "2026-07-08 22:11:38", "logs": {"loss": 0.1419176959991455, "grad_norm": 4.153768539428711, "learning_rate": 1.968454258675079e-05, "epoch": 0.3943217665615142}}
+{"step": 650, "epoch": 0.41009463722397477, "time": "2026-07-08 22:12:01", "logs": {"loss": 0.0911902904510498, "grad_norm": 0.3790145814418793, "learning_rate": 1.999965897496297e-05, "epoch": 0.41009463722397477}}
+{"step": 675, "epoch": 0.42586750788643535, "time": "2026-07-08 22:12:23", "logs": {"loss": 0.14416172981262207, "grad_norm": 5.445947170257568, "learning_rate": 1.9997575017301754e-05, "epoch": 0.42586750788643535}}
+{"step": 700, "epoch": 0.4416403785488959, "time": "2026-07-08 22:12:46", "logs": {"loss": 0.14161142349243164, "grad_norm": 0.33051055669784546, "learning_rate": 1.999359695467383e-05, "epoch": 0.4416403785488959}}
+{"step": 725, "epoch": 0.45741324921135645, "time": "2026-07-08 22:13:09", "logs": {"loss": 0.13508522033691406, "grad_norm": 1.2220453023910522, "learning_rate": 1.998772554074878e-05, "epoch": 0.45741324921135645}}
+{"step": 750, "epoch": 0.47318611987381703, "time": "2026-07-08 22:13:31", "logs": {"loss": 0.14012475967407226, "grad_norm": 16.0678768157959, "learning_rate": 1.9979961887903783e-05, "epoch": 0.47318611987381703}}
+{"step": 775, "epoch": 0.4889589905362776, "time": "2026-07-08 22:13:54", "logs": {"loss": 0.08824824333190918, "grad_norm": 9.829991340637207, "learning_rate": 1.9970307467012862e-05, "epoch": 0.4889589905362776}}
+{"step": 800, "epoch": 0.5047318611987381, "time": "2026-07-08 22:14:16", "logs": {"loss": 0.14100438117980957, "grad_norm": 0.48923227190971375, "learning_rate": 1.9958764107168226e-05, "epoch": 0.5047318611987381}}
+{"step": 825, "epoch": 0.5205047318611987, "time": "2026-07-08 22:14:39", "logs": {"loss": 0.09922822952270507, "grad_norm": 10.579341888427734, "learning_rate": 1.994533399533373e-05, "epoch": 0.5205047318611987}}
+{"step": 850, "epoch": 0.5362776025236593, "time": "2026-07-08 22:15:02", "logs": {"loss": 0.09808570861816407, "grad_norm": 0.25369012355804443, "learning_rate": 1.9930019675930546e-05, "epoch": 0.5362776025236593}}
+{"step": 875, "epoch": 0.5520504731861199, "time": "2026-07-08 22:15:24", "logs": {"loss": 0.08875894546508789, "grad_norm": 0.5847018361091614, "learning_rate": 1.99128240503551e-05, "epoch": 0.5520504731861199}}
+{"step": 900, "epoch": 0.5678233438485805, "time": "2026-07-08 22:15:47", "logs": {"loss": 0.11056282043457032, "grad_norm": 0.4339558482170105, "learning_rate": 1.9893750376429396e-05, "epoch": 0.5678233438485805}}
+{"step": 925, "epoch": 0.583596214511041, "time": "2026-07-08 22:16:10", "logs": {"loss": 0.09730767250061036, "grad_norm": 2.8855783939361572, "learning_rate": 1.9872802267783777e-05, "epoch": 0.583596214511041}}
+{"step": 950, "epoch": 0.5993690851735016, "time": "2026-07-08 22:16:33", "logs": {"loss": 0.10335501670837402, "grad_norm": 6.300772666931152, "learning_rate": 1.9849983693172324e-05, "epoch": 0.5993690851735016}}
+{"step": 975, "epoch": 0.6151419558359621, "time": "2026-07-08 22:16:55", "logs": {"loss": 0.06983193874359131, "grad_norm": 0.1946100890636444, "learning_rate": 1.9825298975720938e-05, "epoch": 0.6151419558359621}}
+{"step": 1000, "epoch": 0.6309148264984227, "time": "2026-07-08 22:17:18", "logs": {"loss": 0.06307486057281494, "grad_norm": 0.05659753456711769, "learning_rate": 1.97987527921083e-05, "epoch": 0.6309148264984227}}
+{"step": 1000, "epoch": 0.6309148264984227, "time": "2026-07-08 22:18:14", "logs": {"eval_loss": 0.10372021794319153, "eval_accuracy": 0.9788643533123028, "eval_precision": 0.9645042839657283, "eval_recall": 0.9943217665615142, "eval_f1": 0.9791860826343585, "eval_runtime": 56.2004, "eval_samples_per_second": 56.405, "eval_steps_per_second": 3.541, "epoch": 0.6309148264984227}}