Update training logs at step 3000

training_logs.jsonl

@@ -104,3 +104,24 @@
 {"step": 2475, "epoch": 1.5615141955835963, "time": "2026-07-08 22:43:03", "logs": {"loss": 0.02598174810409546, "grad_norm": 0.048296067863702774, "learning_rate": 1.5292654247255976e-05, "epoch": 1.5615141955835963}}
 {"step": 2500, "epoch": 1.5772870662460567, "time": "2026-07-08 22:43:26", "logs": {"loss": 0.06133613586425781, "grad_norm": 9.524810791015625, "learning_rate": 1.5175371427876462e-05, "epoch": 1.5772870662460567}}
 {"step": 2500, "epoch": 1.5772870662460567, "time": "2026-07-08 22:44:22", "logs": {"eval_loss": 0.07992753386497498, "eval_accuracy": 0.9826498422712934, "eval_precision": 0.9745657568238213, "eval_recall": 0.9911671924290221, "eval_f1": 0.9827963715983735, "eval_runtime": 55.9735, "eval_samples_per_second": 56.634, "eval_steps_per_second": 3.555, "epoch": 1.5772870662460567}}
+{"step": 2525, "epoch": 1.5930599369085172, "time": "2026-07-08 22:45:00", "logs": {"loss": 0.05316779613494873, "grad_norm": 0.015798641368746758, "learning_rate": 1.5057108101052978e-05, "epoch": 1.5930599369085172}}
+{"step": 2550, "epoch": 1.608832807570978, "time": "2026-07-08 22:45:23", "logs": {"loss": 0.04096637725830078, "grad_norm": 1.9981679916381836, "learning_rate": 1.4937886672534355e-05, "epoch": 1.608832807570978}}
+{"step": 2575, "epoch": 1.6246056782334386, "time": "2026-07-08 22:45:46", "logs": {"loss": 0.11973735809326172, "grad_norm": 14.948141098022461, "learning_rate": 1.4817729729587951e-05, "epoch": 1.6246056782334386}}
+{"step": 2600, "epoch": 1.640378548895899, "time": "2026-07-08 22:46:08", "logs": {"loss": 0.07024142742156983, "grad_norm": 10.006237030029297, "learning_rate": 1.4696660036720366e-05, "epoch": 1.640378548895899}}
+{"step": 2625, "epoch": 1.6561514195583595, "time": "2026-07-08 22:46:31", "logs": {"loss": 0.05831857681274414, "grad_norm": 2.659205436706543, "learning_rate": 1.4574700531364538e-05, "epoch": 1.6561514195583595}}
+{"step": 2650, "epoch": 1.6719242902208202, "time": "2026-07-08 22:46:53", "logs": {"loss": 0.012276544570922851, "grad_norm": 0.023404600098729134, "learning_rate": 1.445187431953413e-05, "epoch": 1.6719242902208202}}
+{"step": 2675, "epoch": 1.687697160883281, "time": "2026-07-08 22:47:15", "logs": {"loss": 0.04452509880065918, "grad_norm": 0.05033299699425697, "learning_rate": 1.4328204671445906e-05, "epoch": 1.687697160883281}}
+{"step": 2700, "epoch": 1.7034700315457414, "time": "2026-07-08 22:47:39", "logs": {"loss": 0.03908012628555298, "grad_norm": 0.008091382682323456, "learning_rate": 1.4203715017111077e-05, "epoch": 1.7034700315457414}}
+{"step": 2725, "epoch": 1.7192429022082019, "time": "2026-07-08 22:48:01", "logs": {"loss": 0.07871007442474365, "grad_norm": 0.8330066800117493, "learning_rate": 1.4078428941896308e-05, "epoch": 1.7192429022082019}}
+{"step": 2750, "epoch": 1.7350157728706623, "time": "2026-07-08 22:48:23", "logs": {"loss": 0.05369951725006104, "grad_norm": 0.20014899969100952, "learning_rate": 1.3952370182055332e-05, "epoch": 1.7350157728706623}}
+{"step": 2775, "epoch": 1.750788643533123, "time": "2026-07-08 22:48:46", "logs": {"loss": 0.06861288547515869, "grad_norm": 5.281189918518066, "learning_rate": 1.3825562620231962e-05, "epoch": 1.750788643533123}}
+{"step": 2800, "epoch": 1.7665615141955837, "time": "2026-07-08 22:49:09", "logs": {"loss": 0.0692290210723877, "grad_norm": 13.993217468261719, "learning_rate": 1.3698030280935365e-05, "epoch": 1.7665615141955837}}
+{"step": 2825, "epoch": 1.7823343848580442, "time": "2026-07-08 22:49:31", "logs": {"loss": 0.0943898868560791, "grad_norm": 0.19194826483726501, "learning_rate": 1.356979732598847e-05, "epoch": 1.7823343848580442}}
+{"step": 2850, "epoch": 1.7981072555205047, "time": "2026-07-08 22:49:54", "logs": {"loss": 0.05583916664123535, "grad_norm": 0.24530774354934692, "learning_rate": 1.3440888049950352e-05, "epoch": 1.7981072555205047}}
+{"step": 2875, "epoch": 1.8138801261829653, "time": "2026-07-08 22:50:16", "logs": {"loss": 0.06628149509429931, "grad_norm": 23.30782699584961, "learning_rate": 1.3311326875513473e-05, "epoch": 1.8138801261829653}}
+{"step": 2900, "epoch": 1.8296529968454258, "time": "2026-07-08 22:50:39", "logs": {"loss": 0.08753268241882324, "grad_norm": 5.725240230560303, "learning_rate": 1.3181138348876637e-05, "epoch": 1.8296529968454258}}
+{"step": 2925, "epoch": 1.8454258675078865, "time": "2026-07-08 22:51:01", "logs": {"loss": 0.04335375308990479, "grad_norm": 3.2451798915863037, "learning_rate": 1.305034713509457e-05, "epoch": 1.8454258675078865}}
+{"step": 2950, "epoch": 1.861198738170347, "time": "2026-07-08 22:51:24", "logs": {"loss": 0.08735511779785156, "grad_norm": 8.147355079650879, "learning_rate": 1.2918978013404961e-05, "epoch": 1.861198738170347}}
+{"step": 2975, "epoch": 1.8769716088328074, "time": "2026-07-08 22:51:46", "logs": {"loss": 0.04033580780029297, "grad_norm": 0.31234487891197205, "learning_rate": 1.2787055872533867e-05, "epoch": 1.8769716088328074}}
+{"step": 3000, "epoch": 1.8927444794952681, "time": "2026-07-08 22:52:09", "logs": {"loss": 0.07418310165405273, "grad_norm": 2.878502368927002, "learning_rate": 1.2654605705980394e-05, "epoch": 1.8927444794952681}}
+{"step": 3000, "epoch": 1.8927444794952681, "time": "2026-07-08 22:53:05", "logs": {"eval_loss": 0.09431762993335724, "eval_accuracy": 0.9823343848580441, "eval_precision": 0.9716224552745218, "eval_recall": 0.9936908517350158, "eval_f1": 0.982532751091703, "eval_runtime": 55.9884, "eval_samples_per_second": 56.619, "eval_steps_per_second": 3.554, "epoch": 1.8927444794952681}}