Update training logs at step 1500

training_logs.jsonl

@@ -41,3 +41,24 @@
 {"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}}
+{"step": 1025, "epoch": 0.6466876971608833, "time": "2026-07-08 22:18:51", "logs": {"loss": 0.07478074073791503, "grad_norm": 0.0960870087146759, "learning_rate": 1.977035017167984e-05, "epoch": 0.6466876971608833}}
+{"step": 1050, "epoch": 0.6624605678233438, "time": "2026-07-08 22:19:14", "logs": {"loss": 0.07338234424591064, "grad_norm": 2.863891124725342, "learning_rate": 1.974009649549489e-05, "epoch": 0.6624605678233438}}
+{"step": 1075, "epoch": 0.6782334384858044, "time": "2026-07-08 22:19:37", "logs": {"loss": 0.10608007431030274, "grad_norm": 0.3583734631538391, "learning_rate": 1.9707997495307232e-05, "epoch": 0.6782334384858044}}
+{"step": 1100, "epoch": 0.694006309148265, "time": "2026-07-08 22:19:59", "logs": {"loss": 0.07668295860290528, "grad_norm": 0.8535360097885132, "learning_rate": 1.9674059252479156e-05, "epoch": 0.694006309148265}}
+{"step": 1125, "epoch": 0.7097791798107256, "time": "2026-07-08 22:20:22", "logs": {"loss": 0.07370511531829833, "grad_norm": 0.4096319377422333, "learning_rate": 1.9638288196829303e-05, "epoch": 0.7097791798107256}}
+{"step": 1150, "epoch": 0.7255520504731862, "time": "2026-07-08 22:20:44", "logs": {"loss": 0.04484860897064209, "grad_norm": 0.10992075502872467, "learning_rate": 1.9600691105414523e-05, "epoch": 0.7255520504731862}}
+{"step": 1175, "epoch": 0.7413249211356467, "time": "2026-07-08 22:21:06", "logs": {"loss": 0.15258366584777833, "grad_norm": 4.087841510772705, "learning_rate": 1.9561275101245886e-05, "epoch": 0.7413249211356467}}
+{"step": 1200, "epoch": 0.7570977917981072, "time": "2026-07-08 22:21:29", "logs": {"loss": 0.12657273292541504, "grad_norm": 2.7859838008880615, "learning_rate": 1.95200476519392e-05, "epoch": 0.7570977917981072}}
+{"step": 1225, "epoch": 0.7728706624605678, "time": "2026-07-08 22:21:52", "logs": {"loss": 0.058558349609375, "grad_norm": 0.08890348672866821, "learning_rate": 1.9477016568300233e-05, "epoch": 0.7728706624605678}}
+{"step": 1250, "epoch": 0.7886435331230284, "time": "2026-07-08 22:22:14", "logs": {"loss": 0.08944664001464844, "grad_norm": 2.4231088161468506, "learning_rate": 1.9432190002844868e-05, "epoch": 0.7886435331230284}}
+{"step": 1275, "epoch": 0.804416403785489, "time": "2026-07-08 22:22:36", "logs": {"loss": 0.07989122390747071, "grad_norm": 0.15423132479190826, "learning_rate": 1.93855764482546e-05, "epoch": 0.804416403785489}}
+{"step": 1300, "epoch": 0.8201892744479495, "time": "2026-07-08 22:22:59", "logs": {"loss": 0.0904345703125, "grad_norm": 0.1543116569519043, "learning_rate": 1.933718473576751e-05, "epoch": 0.8201892744479495}}
+{"step": 1325, "epoch": 0.8359621451104101, "time": "2026-07-08 22:23:21", "logs": {"loss": 0.08953811645507813, "grad_norm": 0.2740912139415741, "learning_rate": 1.9287024033505156e-05, "epoch": 0.8359621451104101}}
+{"step": 1350, "epoch": 0.8517350157728707, "time": "2026-07-08 22:23:44", "logs": {"loss": 0.09112126350402833, "grad_norm": 0.06053502485156059, "learning_rate": 1.9235103844735587e-05, "epoch": 0.8517350157728707}}
+{"step": 1375, "epoch": 0.8675078864353313, "time": "2026-07-08 22:24:06", "logs": {"loss": 0.10066482543945313, "grad_norm": 3.397080898284912, "learning_rate": 1.9181434006072906e-05, "epoch": 0.8675078864353313}}
+{"step": 1400, "epoch": 0.8832807570977917, "time": "2026-07-08 22:24:29", "logs": {"loss": 0.06111194610595703, "grad_norm": 0.24578048288822174, "learning_rate": 1.9126024685613664e-05, "epoch": 0.8832807570977917}}
+{"step": 1425, "epoch": 0.8990536277602523, "time": "2026-07-08 22:24:51", "logs": {"loss": 0.07008316040039063, "grad_norm": 0.09262054413557053, "learning_rate": 1.9068886381010424e-05, "epoch": 0.8990536277602523}}
+{"step": 1450, "epoch": 0.9148264984227129, "time": "2026-07-08 22:25:14", "logs": {"loss": 0.14111000061035156, "grad_norm": 1.9535330533981323, "learning_rate": 1.9010029917482943e-05, "epoch": 0.9148264984227129}}
+{"step": 1475, "epoch": 0.9305993690851735, "time": "2026-07-08 22:25:36", "logs": {"loss": 0.07531814575195313, "grad_norm": 0.1983080357313156, "learning_rate": 1.894946644576724e-05, "epoch": 0.9305993690851735}}
+{"step": 1500, "epoch": 0.9463722397476341, "time": "2026-07-08 22:25:59", "logs": {"loss": 0.09356441497802734, "grad_norm": 0.09421352297067642, "learning_rate": 1.8887207440003028e-05, "epoch": 0.9463722397476341}}
+{"step": 1500, "epoch": 0.9463722397476341, "time": "2026-07-08 22:26:54", "logs": {"eval_loss": 0.07328534126281738, "eval_accuracy": 0.9782334384858045, "eval_precision": 0.9767295597484277, "eval_recall": 0.9798107255520505, "eval_f1": 0.9782677165354331, "eval_runtime": 55.7759, "eval_samples_per_second": 56.835, "eval_steps_per_second": 3.568, "epoch": 0.9463722397476341}}