Update training logs at step 1200

training_logs.jsonl

@@ -33,3 +33,20 @@
 {"step": 775, "epoch": 0.6270226537216829, "time": "2026-06-26 20:26:22", "logs": {"loss": 0.2888069725036621, "grad_norm": 18.441652297973633, "learning_rate": 1.980526179225785e-05, "epoch": 0.6270226537216829}}
 {"step": 800, "epoch": 0.6472491909385113, "time": "2026-06-26 20:26:45", "logs": {"loss": 0.29139081954956053, "grad_norm": 0.9691627621650696, "learning_rate": 1.97690750839913e-05, "epoch": 0.6472491909385113}}
 {"step": 800, "epoch": 0.6472491909385113, "time": "2026-06-26 20:27:20", "logs": {"eval_loss": 0.14249353110790253, "eval_accuracy": 0.965133906013138, "eval_precision": 0.967511371020143, "eval_recall": 0.9874005305039788, "eval_f1": 0.9773547751887102, "eval_runtime": 34.6417, "eval_samples_per_second": 57.128, "eval_steps_per_second": 3.58, "epoch": 0.6472491909385113}}
+{"step": 825, "epoch": 0.6674757281553398, "time": "2026-06-26 20:28:03", "logs": {"loss": 0.1711592674255371, "grad_norm": 7.6904096603393555, "learning_rate": 1.9729845375988694e-05, "epoch": 0.6674757281553398}}
+{"step": 850, "epoch": 0.6877022653721683, "time": "2026-06-26 20:28:26", "logs": {"loss": 0.2283180809020996, "grad_norm": 6.999588489532471, "learning_rate": 1.968758488803439e-05, "epoch": 0.6877022653721683}}
+{"step": 875, "epoch": 0.7079288025889967, "time": "2026-06-26 20:28:49", "logs": {"loss": 0.26335405349731444, "grad_norm": 6.149271488189697, "learning_rate": 1.9642306783979902e-05, "epoch": 0.7079288025889967}}
+{"step": 900, "epoch": 0.7281553398058253, "time": "2026-06-26 20:29:11", "logs": {"loss": 0.1903523635864258, "grad_norm": 9.907973289489746, "learning_rate": 1.959402516764339e-05, "epoch": 0.7281553398058253}}
+{"step": 925, "epoch": 0.7483818770226537, "time": "2026-06-26 20:29:34", "logs": {"loss": 0.1740720748901367, "grad_norm": 12.104832649230957, "learning_rate": 1.954275507841646e-05, "epoch": 0.7483818770226537}}
+{"step": 950, "epoch": 0.7686084142394822, "time": "2026-06-26 20:29:57", "logs": {"loss": 0.3097032928466797, "grad_norm": 2.8893074989318848, "learning_rate": 1.948851248657947e-05, "epoch": 0.7686084142394822}}
+{"step": 975, "epoch": 0.7888349514563107, "time": "2026-06-26 20:30:20", "logs": {"loss": 0.14465970993041993, "grad_norm": 0.07049937546253204, "learning_rate": 1.9431314288326925e-05, "epoch": 0.7888349514563107}}
+{"step": 1000, "epoch": 0.8090614886731392, "time": "2026-06-26 20:30:42", "logs": {"loss": 0.22320323944091797, "grad_norm": 18.34374237060547, "learning_rate": 1.9371178300504394e-05, "epoch": 0.8090614886731392}}
+{"step": 1025, "epoch": 0.8292880258899676, "time": "2026-06-26 20:31:05", "logs": {"loss": 0.09155179023742675, "grad_norm": 5.898121356964111, "learning_rate": 1.930812325505871e-05, "epoch": 0.8292880258899676}}
+{"step": 1050, "epoch": 0.8495145631067961, "time": "2026-06-26 20:31:28", "logs": {"loss": 0.28490724563598635, "grad_norm": 9.933682441711426, "learning_rate": 1.9242168793203088e-05, "epoch": 0.8495145631067961}}
+{"step": 1075, "epoch": 0.8697411003236246, "time": "2026-06-26 20:31:51", "logs": {"loss": 0.14135926246643066, "grad_norm": 0.8073019981384277, "learning_rate": 1.9173335459299025e-05, "epoch": 0.8697411003236246}}
+{"step": 1100, "epoch": 0.889967637540453, "time": "2026-06-26 20:32:14", "logs": {"loss": 0.2752204895019531, "grad_norm": 23.247236251831055, "learning_rate": 1.9101644694456873e-05, "epoch": 0.889967637540453}}
+{"step": 1125, "epoch": 0.9101941747572816, "time": "2026-06-26 20:32:36", "logs": {"loss": 0.14879122734069825, "grad_norm": 10.088881492614746, "learning_rate": 1.902711882985708e-05, "epoch": 0.9101941747572816}}
+{"step": 1150, "epoch": 0.93042071197411, "time": "2026-06-26 20:32:59", "logs": {"loss": 0.23470134735107423, "grad_norm": 0.5620437860488892, "learning_rate": 1.894978107979417e-05, "epoch": 0.93042071197411}}
+{"step": 1175, "epoch": 0.9506472491909385, "time": "2026-06-26 20:33:22", "logs": {"loss": 0.19982004165649414, "grad_norm": 3.2695255279541016, "learning_rate": 1.886965553444568e-05, "epoch": 0.9506472491909385}}
+{"step": 1200, "epoch": 0.970873786407767, "time": "2026-06-26 20:33:45", "logs": {"loss": 0.22285139083862304, "grad_norm": 19.842267990112305, "learning_rate": 1.8786767152368197e-05, "epoch": 0.970873786407767}}
+{"step": 1200, "epoch": 0.970873786407767, "time": "2026-06-26 20:34:20", "logs": {"eval_loss": 0.14106644690036774, "eval_accuracy": 0.9641232945932289, "eval_precision": 0.9650485436893204, "eval_recall": 0.9887267904509284, "eval_f1": 0.9767441860465116, "eval_runtime": 34.6101, "eval_samples_per_second": 57.18, "eval_steps_per_second": 3.583, "epoch": 0.970873786407767}}