Update training logs at step 2400

training_logs.jsonl

@@ -84,3 +84,20 @@
 {"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}}
+{"step": 2025, "epoch": 1.6383495145631068, "time": "2026-06-26 20:49:02", "logs": {"loss": 0.18048593521118164, "grad_norm": 1.8338792324066162, "learning_rate": 1.4712021581249534e-05, "epoch": 1.6383495145631068}}
+{"step": 2050, "epoch": 1.6585760517799353, "time": "2026-06-26 20:49:26", "logs": {"loss": 0.1664619827270508, "grad_norm": 0.2766644060611725, "learning_rate": 1.4555623646116325e-05, "epoch": 1.6585760517799353}}
+{"step": 2075, "epoch": 1.6788025889967637, "time": "2026-06-26 20:49:48", "logs": {"loss": 0.16300722122192382, "grad_norm": 2.5218565464019775, "learning_rate": 1.4397806665532693e-05, "epoch": 1.6788025889967637}}
+{"step": 2100, "epoch": 1.6990291262135924, "time": "2026-06-26 20:50:11", "logs": {"loss": 0.14837112426757812, "grad_norm": 0.9285559058189392, "learning_rate": 1.4238619798403266e-05, "epoch": 1.6990291262135924}}
+{"step": 2125, "epoch": 1.7192556634304208, "time": "2026-06-26 20:50:33", "logs": {"loss": 0.15740616798400878, "grad_norm": 10.178064346313477, "learning_rate": 1.4078112630342891e-05, "epoch": 1.7192556634304208}}
+{"step": 2150, "epoch": 1.7394822006472492, "time": "2026-06-26 20:50:56", "logs": {"loss": 0.22019144058227538, "grad_norm": 19.79058074951172, "learning_rate": 1.3916335158231101e-05, "epoch": 1.7394822006472492}}
+{"step": 2175, "epoch": 1.7597087378640777, "time": "2026-06-26 20:51:19", "logs": {"loss": 0.10831342697143555, "grad_norm": 8.479653358459473, "learning_rate": 1.3753337774638397e-05, "epoch": 1.7597087378640777}}
+{"step": 2200, "epoch": 1.779935275080906, "time": "2026-06-26 20:51:42", "logs": {"loss": 0.14887014389038086, "grad_norm": 0.27186402678489685, "learning_rate": 1.3589171252129329e-05, "epoch": 1.779935275080906}}
+{"step": 2225, "epoch": 1.8001618122977345, "time": "2026-06-26 20:52:05", "logs": {"loss": 0.19739471435546874, "grad_norm": 5.499264240264893, "learning_rate": 1.3423886727447176e-05, "epoch": 1.8001618122977345}}
+{"step": 2250, "epoch": 1.820388349514563, "time": "2026-06-26 20:52:27", "logs": {"loss": 0.19788772583007813, "grad_norm": 2.787201166152954, "learning_rate": 1.325753568558521e-05, "epoch": 1.820388349514563}}
+{"step": 2275, "epoch": 1.8406148867313916, "time": "2026-06-26 20:52:50", "logs": {"loss": 0.11929478645324706, "grad_norm": 3.942160129547119, "learning_rate": 1.3090169943749475e-05, "epoch": 1.8406148867313916}}
+{"step": 2300, "epoch": 1.86084142394822, "time": "2026-06-26 20:53:13", "logs": {"loss": 0.09196714401245117, "grad_norm": 0.19959710538387299, "learning_rate": 1.2921841635218082e-05, "epoch": 1.86084142394822}}
+{"step": 2325, "epoch": 1.8810679611650487, "time": "2026-06-26 20:53:36", "logs": {"loss": 0.2154999542236328, "grad_norm": 0.05811980366706848, "learning_rate": 1.275260319310205e-05, "epoch": 1.8810679611650487}}
+{"step": 2350, "epoch": 1.9012944983818771, "time": "2026-06-26 20:53:59", "logs": {"loss": 0.1920686912536621, "grad_norm": 1.1418527364730835, "learning_rate": 1.2582507334012755e-05, "epoch": 1.9012944983818771}}
+{"step": 2375, "epoch": 1.9215210355987056, "time": "2026-06-26 20:54:21", "logs": {"loss": 0.15039829254150391, "grad_norm": 3.8587708473205566, "learning_rate": 1.2411607041641062e-05, "epoch": 1.9215210355987056}}
+{"step": 2400, "epoch": 1.941747572815534, "time": "2026-06-26 20:54:44", "logs": {"loss": 0.1844302558898926, "grad_norm": 0.10201486200094223, "learning_rate": 1.2239955550253277e-05, "epoch": 1.941747572815534}}
+{"step": 2400, "epoch": 1.941747572815534, "time": "2026-06-26 20:55:19", "logs": {"eval_loss": 0.14186660945415497, "eval_accuracy": 0.9631126831733199, "eval_precision": 0.9644012944983819, "eval_recall": 0.9880636604774535, "eval_f1": 0.9760890926957091, "eval_runtime": 34.6039, "eval_samples_per_second": 57.19, "eval_steps_per_second": 3.583, "epoch": 1.941747572815534}}