Update training logs at step 2000

training_logs.jsonl

@@ -67,3 +67,20 @@
 {"step": 1575, "epoch": 1.2742718446601942, "time": "2026-06-26 20:40:22", "logs": {"loss": 0.10571711540222167, "grad_norm": 0.07893255352973938, "learning_rate": 1.7231432530282246e-05, "epoch": 1.2742718446601942}}
 {"step": 1600, "epoch": 1.2944983818770226, "time": "2026-06-26 20:40:44", "logs": {"loss": 0.1872186279296875, "grad_norm": 0.5910708904266357, "learning_rate": 1.7108408542839146e-05, "epoch": 1.2944983818770226}}
 {"step": 1600, "epoch": 1.2944983818770226, "time": "2026-06-26 20:41:19", "logs": {"eval_loss": 0.1455843597650528, "eval_accuracy": 0.9671551288529561, "eval_precision": 0.9737360472751149, "eval_recall": 0.98342175066313, "eval_f1": 0.9785549323655559, "eval_runtime": 34.8064, "eval_samples_per_second": 56.857, "eval_steps_per_second": 3.563, "epoch": 1.2944983818770226}}
+{"step": 1625, "epoch": 1.3147249190938513, "time": "2026-06-26 20:42:01", "logs": {"loss": 0.1566315174102783, "grad_norm": 0.48737797141075134, "learning_rate": 1.698317033499813e-05, "epoch": 1.3147249190938513}}
+{"step": 1650, "epoch": 1.3349514563106797, "time": "2026-06-26 20:42:25", "logs": {"loss": 0.15158571243286134, "grad_norm": 17.18292808532715, "learning_rate": 1.6855756917600057e-05, "epoch": 1.3349514563106797}}
+{"step": 1675, "epoch": 1.3551779935275081, "time": "2026-06-26 20:42:48", "logs": {"loss": 0.16150398254394532, "grad_norm": 10.572613716125488, "learning_rate": 1.6726207979048604e-05, "epoch": 1.3551779935275081}}
+{"step": 1700, "epoch": 1.3754045307443366, "time": "2026-06-26 20:43:10", "logs": {"loss": 0.09849663734436036, "grad_norm": 0.1977110058069229, "learning_rate": 1.6594563872947613e-05, "epoch": 1.3754045307443366}}
+{"step": 1725, "epoch": 1.395631067961165, "time": "2026-06-26 20:43:33", "logs": {"loss": 0.17041929244995116, "grad_norm": 2.6522152423858643, "learning_rate": 1.6460865605531214e-05, "epoch": 1.395631067961165}}
+{"step": 1750, "epoch": 1.4158576051779934, "time": "2026-06-26 20:43:56", "logs": {"loss": 0.1783625602722168, "grad_norm": 0.18808063864707947, "learning_rate": 1.6325154822890663e-05, "epoch": 1.4158576051779934}}
+{"step": 1775, "epoch": 1.436084142394822, "time": "2026-06-26 20:44:19", "logs": {"loss": 0.15096524238586426, "grad_norm": 33.89837646484375, "learning_rate": 1.618747379800188e-05, "epoch": 1.436084142394822}}
+{"step": 1800, "epoch": 1.4563106796116505, "time": "2026-06-26 20:44:41", "logs": {"loss": 0.2288828659057617, "grad_norm": 10.100881576538086, "learning_rate": 1.6047865417557695e-05, "epoch": 1.4563106796116505}}
+{"step": 1825, "epoch": 1.476537216828479, "time": "2026-06-26 20:45:04", "logs": {"loss": 0.22033729553222656, "grad_norm": 7.704436302185059, "learning_rate": 1.5906373168608952e-05, "epoch": 1.476537216828479}}
+{"step": 1850, "epoch": 1.4967637540453074, "time": "2026-06-26 20:45:27", "logs": {"loss": 0.15806819915771483, "grad_norm": 9.382397651672363, "learning_rate": 1.576304112501858e-05, "epoch": 1.4967637540453074}}
+{"step": 1875, "epoch": 1.516990291262136, "time": "2026-06-26 20:45:50", "logs": {"loss": 0.16990087509155274, "grad_norm": 6.415167808532715, "learning_rate": 1.5617913933732892e-05, "epoch": 1.516990291262136}}
+{"step": 1900, "epoch": 1.5372168284789645, "time": "2026-06-26 20:46:13", "logs": {"loss": 0.1730282974243164, "grad_norm": 8.820036888122559, "learning_rate": 1.5471036800874375e-05, "epoch": 1.5372168284789645}}
+{"step": 1925, "epoch": 1.557443365695793, "time": "2026-06-26 20:46:36", "logs": {"loss": 0.15791168212890624, "grad_norm": 28.52211570739746, "learning_rate": 1.5322455477660274e-05, "epoch": 1.557443365695793}}
+{"step": 1950, "epoch": 1.5776699029126213, "time": "2026-06-26 20:46:58", "logs": {"loss": 0.24158744812011718, "grad_norm": 15.133056640625, "learning_rate": 1.5172216246151426e-05, "epoch": 1.5776699029126213}}
+{"step": 1975, "epoch": 1.5978964401294498, "time": "2026-06-26 20:47:21", "logs": {"loss": 0.07609220504760743, "grad_norm": 13.767041206359863, "learning_rate": 1.50203659048357e-05, "epoch": 1.5978964401294498}}
+{"step": 2000, "epoch": 1.6181229773462782, "time": "2026-06-26 20:47:44", "logs": {"loss": 0.2856024742126465, "grad_norm": 2.377875328063965, "learning_rate": 1.4866951754050605e-05, "epoch": 1.6181229773462782}}
+{"step": 2000, "epoch": 1.6181229773462782, "time": "2026-06-26 20:48:19", "logs": {"eval_loss": 0.12881171703338623, "eval_accuracy": 0.9671551288529561, "eval_precision": 0.9819639278557114, "eval_recall": 0.9748010610079576, "eval_f1": 0.978369384359401, "eval_runtime": 34.7861, "eval_samples_per_second": 56.891, "eval_steps_per_second": 3.565, "epoch": 1.6181229773462782}}