Update training logs at step 6000

training_logs.jsonl

@@ -230,3 +230,24 @@
 {"step": 5475, "epoch": 3.454258675078864, "time": "2026-07-08 15:06:41", "logs": {"loss": 0.05405607223510742, "grad_norm": 0.287876158952713, "learning_rate": 1.1153180215879078e-06, "epoch": 3.454258675078864}}
 {"step": 5500, "epoch": 3.470031545741325, "time": "2026-07-08 15:07:04", "logs": {"loss": 0.026213862895965577, "grad_norm": 0.5554311871528625, "learning_rate": 1.0529914376748452e-06, "epoch": 3.470031545741325}}
 {"step": 5500, "epoch": 3.470031545741325, "time": "2026-07-08 15:08:06", "logs": {"eval_loss": 0.06463239341974258, "eval_accuracy": 0.9861198738170347, "eval_precision": 0.9788688626476072, "eval_recall": 0.9936908517350158, "eval_f1": 0.9862241703193487, "eval_runtime": 61.7345, "eval_samples_per_second": 51.349, "eval_steps_per_second": 3.223, "epoch": 3.470031545741325}}
+{"step": 5525, "epoch": 3.4858044164037856, "time": "2026-07-08 15:08:47", "logs": {"loss": 0.001186341941356659, "grad_norm": 0.03855282813310623, "learning_rate": 9.923599221484403e-07, "epoch": 3.4858044164037856}}
+{"step": 5550, "epoch": 3.501577287066246, "time": "2026-07-08 15:09:12", "logs": {"loss": 0.04292780876159668, "grad_norm": 0.09590687602758408, "learning_rate": 9.334349620397465e-07, "epoch": 3.501577287066246}}
+{"step": 5575, "epoch": 3.5173501577287065, "time": "2026-07-08 15:09:35", "logs": {"loss": 0.0397885537147522, "grad_norm": 0.039906103163957596, "learning_rate": 8.76227721061913e-07, "epoch": 3.5173501577287065}}
+{"step": 5600, "epoch": 3.5331230283911674, "time": "2026-07-08 15:09:58", "logs": {"loss": 0.015554320812225342, "grad_norm": 0.009204396046698093, "learning_rate": 8.207490374951232e-07, "epoch": 3.5331230283911674}}
+{"step": 5625, "epoch": 3.548895899053628, "time": "2026-07-08 15:10:22", "logs": {"loss": 0.031379334926605225, "grad_norm": 5.533051490783691, "learning_rate": 7.670094221332369e-07, "epoch": 3.548895899053628}}
+{"step": 5650, "epoch": 3.5646687697160884, "time": "2026-07-08 15:10:46", "logs": {"loss": 0.030727083683013915, "grad_norm": 0.017078593373298645, "learning_rate": 7.150190562924442e-07, "epoch": 3.5646687697160884}}
+{"step": 5675, "epoch": 3.580441640378549, "time": "2026-07-08 15:11:09", "logs": {"loss": 0.002584594190120697, "grad_norm": 0.01333980169147253, "learning_rate": 6.647877898823463e-07, "epoch": 3.580441640378549}}
+{"step": 5700, "epoch": 3.5962145110410093, "time": "2026-07-08 15:11:33", "logs": {"loss": 0.01648117184638977, "grad_norm": 0.033404573798179626, "learning_rate": 6.163251395398295e-07, "epoch": 3.5962145110410093}}
+{"step": 5725, "epoch": 3.61198738170347, "time": "2026-07-08 15:11:57", "logs": {"loss": 0.05104788303375244, "grad_norm": 0.02266419120132923, "learning_rate": 5.696402868260787e-07, "epoch": 3.61198738170347}}
+{"step": 5750, "epoch": 3.6277602523659307, "time": "2026-07-08 15:12:20", "logs": {"loss": 0.0016559384763240813, "grad_norm": 0.020101038739085197, "learning_rate": 5.247420764870681e-07, "epoch": 3.6277602523659307}}
+{"step": 5775, "epoch": 3.643533123028391, "time": "2026-07-08 15:12:43", "logs": {"loss": 0.01459729552268982, "grad_norm": 30.076658248901367, "learning_rate": 4.816390147778716e-07, "epoch": 3.643533123028391}}
+{"step": 5800, "epoch": 3.6593059936908516, "time": "2026-07-08 15:13:07", "logs": {"loss": 0.015124108791351318, "grad_norm": 0.02200201340019703, "learning_rate": 4.4033926785109095e-07, "epoch": 3.6593059936908516}}
+{"step": 5825, "epoch": 3.6750788643533125, "time": "2026-07-08 15:13:30", "logs": {"loss": 0.034863491058349606, "grad_norm": 4.121751308441162, "learning_rate": 4.0085066020973505e-07, "epoch": 3.6750788643533125}}
+{"step": 5850, "epoch": 3.690851735015773, "time": "2026-07-08 15:13:54", "logs": {"loss": 0.04830181121826172, "grad_norm": 0.0162983238697052, "learning_rate": 3.631806732248067e-07, "epoch": 3.690851735015773}}
+{"step": 5875, "epoch": 3.7066246056782335, "time": "2026-07-08 15:14:18", "logs": {"loss": 0.005567395091056824, "grad_norm": 0.07747267186641693, "learning_rate": 3.273364437179216e-07, "epoch": 3.7066246056782335}}
+{"step": 5900, "epoch": 3.722397476340694, "time": "2026-07-08 15:14:41", "logs": {"loss": 0.03307506322860718, "grad_norm": 0.06429196149110794, "learning_rate": 2.933247626091751e-07, "epoch": 3.722397476340694}}
+{"step": 5925, "epoch": 3.7381703470031544, "time": "2026-07-08 15:15:05", "logs": {"loss": 0.08351734161376953, "grad_norm": 1.322525143623352, "learning_rate": 2.611520736305739e-07, "epoch": 3.7381703470031544}}
+{"step": 5950, "epoch": 3.753943217665615, "time": "2026-07-08 15:15:28", "logs": {"loss": 0.02155515432357788, "grad_norm": 0.010082464665174484, "learning_rate": 2.308244721052233e-07, "epoch": 3.753943217665615}}
+{"step": 5975, "epoch": 3.769716088328076, "time": "2026-07-08 15:15:52", "logs": {"loss": 0.05890011787414551, "grad_norm": 0.6019063591957092, "learning_rate": 2.02347703792527e-07, "epoch": 3.769716088328076}}
+{"step": 6000, "epoch": 3.7854889589905363, "time": "2026-07-08 15:16:15", "logs": {"loss": 0.050057473182678225, "grad_norm": 9.324341773986816, "learning_rate": 1.757271637996183e-07, "epoch": 3.7854889589905363}}
+{"step": 6000, "epoch": 3.7854889589905363, "time": "2026-07-08 15:17:17", "logs": {"eval_loss": 0.06628032773733139, "eval_accuracy": 0.9854889589905362, "eval_precision": 0.9776536312849162, "eval_recall": 0.9936908517350158, "eval_f1": 0.9856070087609512, "eval_runtime": 61.662, "eval_samples_per_second": 51.409, "eval_steps_per_second": 3.227, "epoch": 3.7854889589905363}}