| { | |
| "best_metric": 0.6102484464645386, | |
| "best_model_checkpoint": "./qwen2.5-0.5b/qwen2.5-0.5b-expo-L2EXPO-ES-0.001/checkpoint-300", | |
| "epoch": 2.269721303731696, | |
| "eval_steps": 50, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "dpo_loss": 0.6931471824645996, | |
| "epoch": 0.002834199338686821, | |
| "grad_norm": 0.3688501423173312, | |
| "learning_rate": 2.840909090909091e-08, | |
| "logits": -1.359458565711975, | |
| "logps": -84.69721221923828, | |
| "loss": 0.3913, | |
| "objective": 0.3618059456348419, | |
| "ranking_idealized": 1.0, | |
| "ranking_idealized_expo": 0.6875, | |
| "ranking_simple": 0.5833333134651184, | |
| "regularize": 0.3618059456348419, | |
| "step": 1, | |
| "wo_beta": 14.830931663513184 | |
| }, | |
| { | |
| "dpo_loss": 0.6929696202278137, | |
| "epoch": 0.14170996693434104, | |
| "grad_norm": 0.6973089072493135, | |
| "learning_rate": 1.4204545454545458e-06, | |
| "logits": -1.5327931642532349, | |
| "logps": -83.60688018798828, | |
| "loss": 0.418, | |
| "objective": 0.42159923911094666, | |
| "ranking_idealized": 0.9876700639724731, | |
| "ranking_idealized_expo": 0.6386054158210754, | |
| "ranking_simple": 0.5280612111091614, | |
| "regularize": 0.42159923911094666, | |
| "step": 50, | |
| "wo_beta": 16.323150634765625 | |
| }, | |
| { | |
| "epoch": 0.14170996693434104, | |
| "eval_dpo_loss": 0.6926723122596741, | |
| "eval_logits": -1.810510516166687, | |
| "eval_logps": -107.43917083740234, | |
| "eval_loss": 0.41496098041534424, | |
| "eval_objective": 0.4128378927707672, | |
| "eval_ranking_idealized": 0.9870600700378418, | |
| "eval_ranking_idealized_expo": 0.6319875717163086, | |
| "eval_ranking_simple": 0.5351966619491577, | |
| "eval_regularize": 0.4128378927707672, | |
| "eval_runtime": 308.8567, | |
| "eval_samples_per_second": 18.747, | |
| "eval_steps_per_second": 1.564, | |
| "eval_wo_beta": 22.02687644958496, | |
| "step": 50 | |
| }, | |
| { | |
| "dpo_loss": 0.6878826022148132, | |
| "epoch": 0.2834199338686821, | |
| "grad_norm": 2.816808446897818, | |
| "learning_rate": 2.8409090909090916e-06, | |
| "logits": -1.554953932762146, | |
| "logps": -162.0962677001953, | |
| "loss": 0.416, | |
| "objective": 0.4231468141078949, | |
| "ranking_idealized": 0.987500011920929, | |
| "ranking_idealized_expo": 0.6287500262260437, | |
| "ranking_simple": 0.597083330154419, | |
| "regularize": 0.4231468141078949, | |
| "step": 100, | |
| "wo_beta": 36.895965576171875 | |
| }, | |
| { | |
| "epoch": 0.2834199338686821, | |
| "eval_dpo_loss": 0.6895796060562134, | |
| "eval_logits": -2.0485212802886963, | |
| "eval_logps": -230.8855438232422, | |
| "eval_loss": 0.4087027907371521, | |
| "eval_objective": 0.40811070799827576, | |
| "eval_ranking_idealized": 0.9870600700378418, | |
| "eval_ranking_idealized_expo": 0.6319875717163086, | |
| "eval_ranking_simple": 0.5559006333351135, | |
| "eval_regularize": 0.40811070799827576, | |
| "eval_runtime": 308.2409, | |
| "eval_samples_per_second": 18.784, | |
| "eval_steps_per_second": 1.567, | |
| "eval_wo_beta": 52.94944381713867, | |
| "step": 100 | |
| }, | |
| { | |
| "dpo_loss": 0.6755279302597046, | |
| "epoch": 0.42512990080302315, | |
| "grad_norm": 4.687417348983457, | |
| "learning_rate": 4.2613636363636365e-06, | |
| "logits": -2.6038007736206055, | |
| "logps": -284.96868896484375, | |
| "loss": 0.387, | |
| "objective": 0.39124202728271484, | |
| "ranking_idealized": 0.9887499809265137, | |
| "ranking_idealized_expo": 0.6299999952316284, | |
| "ranking_simple": 0.6474999785423279, | |
| "regularize": 0.39124202728271484, | |
| "step": 150, | |
| "wo_beta": 83.33438110351562 | |
| }, | |
| { | |
| "epoch": 0.42512990080302315, | |
| "eval_dpo_loss": 0.6843881607055664, | |
| "eval_logits": -3.9840264320373535, | |
| "eval_logps": -343.55194091796875, | |
| "eval_loss": 0.40323564410209656, | |
| "eval_objective": 0.40214404463768005, | |
| "eval_ranking_idealized": 0.9870600700378418, | |
| "eval_ranking_idealized_expo": 0.6319875717163086, | |
| "eval_ranking_simple": 0.5766045451164246, | |
| "eval_regularize": 0.40214404463768005, | |
| "eval_runtime": 308.6069, | |
| "eval_samples_per_second": 18.762, | |
| "eval_steps_per_second": 1.565, | |
| "eval_wo_beta": 90.2214584350586, | |
| "step": 150 | |
| }, | |
| { | |
| "dpo_loss": 0.6573903560638428, | |
| "epoch": 0.5668398677373642, | |
| "grad_norm": 5.4307407287631735, | |
| "learning_rate": 4.997168347957521e-06, | |
| "logits": -5.123294353485107, | |
| "logps": -384.2275390625, | |
| "loss": 0.3587, | |
| "objective": 0.36179742217063904, | |
| "ranking_idealized": 0.9891666769981384, | |
| "ranking_idealized_expo": 0.6195833086967468, | |
| "ranking_simple": 0.684166669845581, | |
| "regularize": 0.36179742217063904, | |
| "step": 200, | |
| "wo_beta": 136.6976318359375 | |
| }, | |
| { | |
| "epoch": 0.5668398677373642, | |
| "eval_dpo_loss": 0.6754290461540222, | |
| "eval_logits": -6.168106555938721, | |
| "eval_logps": -390.38665771484375, | |
| "eval_loss": 0.3916535973548889, | |
| "eval_objective": 0.3892715573310852, | |
| "eval_ranking_idealized": 0.9870600700378418, | |
| "eval_ranking_idealized_expo": 0.6319875717163086, | |
| "eval_ranking_simple": 0.6004140973091125, | |
| "eval_regularize": 0.3892715573310852, | |
| "eval_runtime": 309.2072, | |
| "eval_samples_per_second": 18.725, | |
| "eval_steps_per_second": 1.562, | |
| "eval_wo_beta": 124.65765380859375, | |
| "step": 200 | |
| }, | |
| { | |
| "dpo_loss": 0.6350498199462891, | |
| "epoch": 0.7085498346717053, | |
| "grad_norm": 6.529681856006604, | |
| "learning_rate": 4.973122855144066e-06, | |
| "logits": -6.972330093383789, | |
| "logps": -475.43475341796875, | |
| "loss": 0.3299, | |
| "objective": 0.3326449394226074, | |
| "ranking_idealized": 0.9837499856948853, | |
| "ranking_idealized_expo": 0.6225000023841858, | |
| "ranking_simple": 0.7291666865348816, | |
| "regularize": 0.3326449394226074, | |
| "step": 250, | |
| "wo_beta": 194.3697967529297 | |
| }, | |
| { | |
| "epoch": 0.7085498346717053, | |
| "eval_dpo_loss": 0.6764808893203735, | |
| "eval_logits": -7.7444071769714355, | |
| "eval_logps": -474.0688171386719, | |
| "eval_loss": 0.39678695797920227, | |
| "eval_objective": 0.3968295454978943, | |
| "eval_ranking_idealized": 0.9870600700378418, | |
| "eval_ranking_idealized_expo": 0.6319875717163086, | |
| "eval_ranking_simple": 0.5957556962966919, | |
| "eval_regularize": 0.3968295454978943, | |
| "eval_runtime": 308.4253, | |
| "eval_samples_per_second": 18.773, | |
| "eval_steps_per_second": 1.566, | |
| "eval_wo_beta": 147.76255798339844, | |
| "step": 250 | |
| }, | |
| { | |
| "dpo_loss": 0.6194267868995667, | |
| "epoch": 0.8502598016060463, | |
| "grad_norm": 7.819775688472429, | |
| "learning_rate": 4.924776641419513e-06, | |
| "logits": -8.305917739868164, | |
| "logps": -537.9514770507812, | |
| "loss": 0.294, | |
| "objective": 0.29155203700065613, | |
| "ranking_idealized": 0.9829166531562805, | |
| "ranking_idealized_expo": 0.6075000166893005, | |
| "ranking_simple": 0.7541666626930237, | |
| "regularize": 0.29155203700065613, | |
| "step": 300, | |
| "wo_beta": 228.0120849609375 | |
| }, | |
| { | |
| "epoch": 0.8502598016060463, | |
| "eval_dpo_loss": 0.6728345155715942, | |
| "eval_logits": -8.890972137451172, | |
| "eval_logps": -573.5075073242188, | |
| "eval_loss": 0.3941618800163269, | |
| "eval_objective": 0.3930768370628357, | |
| "eval_ranking_idealized": 0.9870600700378418, | |
| "eval_ranking_idealized_expo": 0.6319875717163086, | |
| "eval_ranking_simple": 0.6102484464645386, | |
| "eval_regularize": 0.3930768370628357, | |
| "eval_runtime": 308.0714, | |
| "eval_samples_per_second": 18.794, | |
| "eval_steps_per_second": 1.568, | |
| "eval_wo_beta": 160.35784912109375, | |
| "step": 300 | |
| }, | |
| { | |
| "dpo_loss": 0.6043005585670471, | |
| "epoch": 0.9919697685403873, | |
| "grad_norm": 8.598806793267013, | |
| "learning_rate": 4.8526047530778175e-06, | |
| "logits": -8.97115421295166, | |
| "logps": -561.0111083984375, | |
| "loss": 0.2753, | |
| "objective": 0.2713463306427002, | |
| "ranking_idealized": 0.9850000143051147, | |
| "ranking_idealized_expo": 0.6341666579246521, | |
| "ranking_simple": 0.7933333516120911, | |
| "regularize": 0.2713463306427002, | |
| "step": 350, | |
| "wo_beta": 253.40798950195312 | |
| }, | |
| { | |
| "epoch": 0.9919697685403873, | |
| "eval_dpo_loss": 0.6731387972831726, | |
| "eval_logits": -9.998077392578125, | |
| "eval_logps": -593.110107421875, | |
| "eval_loss": 0.3965202271938324, | |
| "eval_objective": 0.3959551751613617, | |
| "eval_ranking_idealized": 0.9870600700378418, | |
| "eval_ranking_idealized_expo": 0.6319875717163086, | |
| "eval_ranking_simple": 0.5936853289604187, | |
| "eval_regularize": 0.3959551751613617, | |
| "eval_runtime": 308.2686, | |
| "eval_samples_per_second": 18.782, | |
| "eval_steps_per_second": 1.567, | |
| "eval_wo_beta": 171.5761260986328, | |
| "step": 350 | |
| }, | |
| { | |
| "dpo_loss": 0.5814460515975952, | |
| "epoch": 1.1336797354747283, | |
| "grad_norm": 7.338503940970108, | |
| "learning_rate": 4.757316345716554e-06, | |
| "logits": -9.615409851074219, | |
| "logps": -592.6610717773438, | |
| "loss": 0.2316, | |
| "objective": 0.23074908554553986, | |
| "ranking_idealized": 0.9850000143051147, | |
| "ranking_idealized_expo": 0.6329166889190674, | |
| "ranking_simple": 0.8429166674613953, | |
| "regularize": 0.23074908554553986, | |
| "step": 400, | |
| "wo_beta": 295.14337158203125 | |
| }, | |
| { | |
| "epoch": 1.1336797354747283, | |
| "eval_dpo_loss": 0.6717904210090637, | |
| "eval_logits": -9.647905349731445, | |
| "eval_logps": -564.7660522460938, | |
| "eval_loss": 0.3965735137462616, | |
| "eval_objective": 0.3956299126148224, | |
| "eval_ranking_idealized": 0.9870600700378418, | |
| "eval_ranking_idealized_expo": 0.6319875717163086, | |
| "eval_ranking_simple": 0.5874741077423096, | |
| "eval_regularize": 0.3956299126148224, | |
| "eval_runtime": 308.3873, | |
| "eval_samples_per_second": 18.775, | |
| "eval_steps_per_second": 1.566, | |
| "eval_wo_beta": 171.6053924560547, | |
| "step": 400 | |
| }, | |
| { | |
| "dpo_loss": 0.57535320520401, | |
| "epoch": 1.2753897024090695, | |
| "grad_norm": 7.067175428131206, | |
| "learning_rate": 4.639847716126855e-06, | |
| "logits": -10.082599639892578, | |
| "logps": -593.1123046875, | |
| "loss": 0.2205, | |
| "objective": 0.21684379875659943, | |
| "ranking_idealized": 0.9895833134651184, | |
| "ranking_idealized_expo": 0.6204166412353516, | |
| "ranking_simple": 0.8416666388511658, | |
| "regularize": 0.21684379875659943, | |
| "step": 450, | |
| "wo_beta": 313.67462158203125 | |
| }, | |
| { | |
| "epoch": 1.2753897024090695, | |
| "eval_dpo_loss": 0.6725399494171143, | |
| "eval_logits": -10.967289924621582, | |
| "eval_logps": -599.2516479492188, | |
| "eval_loss": 0.3962310552597046, | |
| "eval_objective": 0.39826443791389465, | |
| "eval_ranking_idealized": 0.9870600700378418, | |
| "eval_ranking_idealized_expo": 0.6319875717163086, | |
| "eval_ranking_simple": 0.5859213471412659, | |
| "eval_regularize": 0.39826443791389465, | |
| "eval_runtime": 308.0799, | |
| "eval_samples_per_second": 18.794, | |
| "eval_steps_per_second": 1.568, | |
| "eval_wo_beta": 182.48765563964844, | |
| "step": 450 | |
| }, | |
| { | |
| "dpo_loss": 0.5704715251922607, | |
| "epoch": 1.4170996693434104, | |
| "grad_norm": 8.491423005159572, | |
| "learning_rate": 4.501353102310901e-06, | |
| "logits": -10.000563621520996, | |
| "logps": -594.431396484375, | |
| "loss": 0.2058, | |
| "objective": 0.2110779583454132, | |
| "ranking_idealized": 0.9854166507720947, | |
| "ranking_idealized_expo": 0.6070833206176758, | |
| "ranking_simple": 0.8395833373069763, | |
| "regularize": 0.2110779583454132, | |
| "step": 500, | |
| "wo_beta": 325.75177001953125 | |
| }, | |
| { | |
| "epoch": 1.4170996693434104, | |
| "eval_dpo_loss": 0.6740813851356506, | |
| "eval_logits": -9.617457389831543, | |
| "eval_logps": -589.5045166015625, | |
| "eval_loss": 0.4004902243614197, | |
| "eval_objective": 0.402893602848053, | |
| "eval_ranking_idealized": 0.9870600700378418, | |
| "eval_ranking_idealized_expo": 0.6319875717163086, | |
| "eval_ranking_simple": 0.5797101259231567, | |
| "eval_regularize": 0.402893602848053, | |
| "eval_runtime": 307.827, | |
| "eval_samples_per_second": 18.809, | |
| "eval_steps_per_second": 1.569, | |
| "eval_wo_beta": 188.1012725830078, | |
| "step": 500 | |
| }, | |
| { | |
| "dpo_loss": 0.5671207904815674, | |
| "epoch": 1.5588096362777515, | |
| "grad_norm": 8.449525787360594, | |
| "learning_rate": 4.34319334202531e-06, | |
| "logits": -9.910933494567871, | |
| "logps": -622.9572143554688, | |
| "loss": 0.2027, | |
| "objective": 0.20102910697460175, | |
| "ranking_idealized": 0.9883333444595337, | |
| "ranking_idealized_expo": 0.6195833086967468, | |
| "ranking_simple": 0.8554166555404663, | |
| "regularize": 0.20102910697460175, | |
| "step": 550, | |
| "wo_beta": 329.6236877441406 | |
| }, | |
| { | |
| "epoch": 1.5588096362777515, | |
| "eval_dpo_loss": 0.6730445623397827, | |
| "eval_logits": -10.393749237060547, | |
| "eval_logps": -622.4690551757812, | |
| "eval_loss": 0.39951398968696594, | |
| "eval_objective": 0.40004628896713257, | |
| "eval_ranking_idealized": 0.9870600700378418, | |
| "eval_ranking_idealized_expo": 0.6319875717163086, | |
| "eval_ranking_simple": 0.5947204828262329, | |
| "eval_regularize": 0.40004628896713257, | |
| "eval_runtime": 308.3244, | |
| "eval_samples_per_second": 18.779, | |
| "eval_steps_per_second": 1.567, | |
| "eval_wo_beta": 185.8619842529297, | |
| "step": 550 | |
| }, | |
| { | |
| "dpo_loss": 0.5614171624183655, | |
| "epoch": 1.7028814359943316, | |
| "grad_norm": 8.320325832092646, | |
| "learning_rate": 4.16692250129073e-06, | |
| "logits": -10.030584335327148, | |
| "logps": -637.830078125, | |
| "loss": 0.1897, | |
| "objective": 0.1895790994167328, | |
| "ranking_idealized": 0.9850000143051147, | |
| "ranking_idealized_expo": 0.6225000023841858, | |
| "ranking_simple": 0.8608333468437195, | |
| "regularize": 0.1895790994167328, | |
| "step": 600, | |
| "wo_beta": 343.5328369140625 | |
| }, | |
| { | |
| "epoch": 1.7028814359943316, | |
| "eval_dpo_loss": 0.6715614199638367, | |
| "eval_logits": -11.553997993469238, | |
| "eval_logps": -755.1119384765625, | |
| "eval_loss": 0.4028206467628479, | |
| "eval_objective": 0.4023354947566986, | |
| "eval_ranking_idealized": 0.9870600700378418, | |
| "eval_ranking_idealized_expo": 0.6319875717163086, | |
| "eval_ranking_simple": 0.5952380895614624, | |
| "eval_regularize": 0.4023354947566986, | |
| "eval_runtime": 308.0753, | |
| "eval_samples_per_second": 18.794, | |
| "eval_steps_per_second": 1.568, | |
| "eval_wo_beta": 201.23565673828125, | |
| "step": 600 | |
| }, | |
| { | |
| "dpo_loss": 0.5596800446510315, | |
| "epoch": 1.8445914029286725, | |
| "grad_norm": 7.934464503648664, | |
| "learning_rate": 3.974272604254906e-06, | |
| "logits": -10.258437156677246, | |
| "logps": -652.069091796875, | |
| "loss": 0.1797, | |
| "objective": 0.17688363790512085, | |
| "ranking_idealized": 0.9837499856948853, | |
| "ranking_idealized_expo": 0.6324999928474426, | |
| "ranking_simple": 0.8679166436195374, | |
| "regularize": 0.17688363790512085, | |
| "step": 650, | |
| "wo_beta": 346.150634765625 | |
| }, | |
| { | |
| "epoch": 1.8445914029286725, | |
| "eval_dpo_loss": 0.6730169653892517, | |
| "eval_logits": -10.819306373596191, | |
| "eval_logps": -673.7770385742188, | |
| "eval_loss": 0.39966142177581787, | |
| "eval_objective": 0.3991987109184265, | |
| "eval_ranking_idealized": 0.9870600700378418, | |
| "eval_ranking_idealized_expo": 0.6319875717163086, | |
| "eval_ranking_simple": 0.5942028760910034, | |
| "eval_regularize": 0.3991987109184265, | |
| "eval_runtime": 307.7337, | |
| "eval_samples_per_second": 18.815, | |
| "eval_steps_per_second": 1.57, | |
| "eval_wo_beta": 188.3079071044922, | |
| "step": 650 | |
| }, | |
| { | |
| "dpo_loss": 0.5620754957199097, | |
| "epoch": 1.9863013698630136, | |
| "grad_norm": 7.492993323139572, | |
| "learning_rate": 3.767136614452458e-06, | |
| "logits": -10.352383613586426, | |
| "logps": -666.3911743164062, | |
| "loss": 0.1689, | |
| "objective": 0.17240169644355774, | |
| "ranking_idealized": 0.9908333420753479, | |
| "ranking_idealized_expo": 0.621666669845581, | |
| "ranking_simple": 0.8704166412353516, | |
| "regularize": 0.17240169644355774, | |
| "step": 700, | |
| "wo_beta": 337.1234130859375 | |
| }, | |
| { | |
| "epoch": 1.9863013698630136, | |
| "eval_dpo_loss": 0.6712956428527832, | |
| "eval_logits": -11.077164649963379, | |
| "eval_logps": -653.8335571289062, | |
| "eval_loss": 0.3985289931297302, | |
| "eval_objective": 0.3969685435295105, | |
| "eval_ranking_idealized": 0.9870600700378418, | |
| "eval_ranking_idealized_expo": 0.6319875717163086, | |
| "eval_ranking_simple": 0.5910972952842712, | |
| "eval_regularize": 0.3969685435295105, | |
| "eval_runtime": 308.1698, | |
| "eval_samples_per_second": 18.788, | |
| "eval_steps_per_second": 1.567, | |
| "eval_wo_beta": 182.3851776123047, | |
| "step": 700 | |
| }, | |
| { | |
| "dpo_loss": 0.5451232194900513, | |
| "epoch": 2.1280113367973548, | |
| "grad_norm": 6.5335714189025635, | |
| "learning_rate": 3.547549834686222e-06, | |
| "logits": -11.081757545471191, | |
| "logps": -661.833251953125, | |
| "loss": 0.1492, | |
| "objective": 0.1450423002243042, | |
| "ranking_idealized": 0.9887499809265137, | |
| "ranking_idealized_expo": 0.627916693687439, | |
| "ranking_simple": 0.8899999856948853, | |
| "regularize": 0.1450423002243042, | |
| "step": 750, | |
| "wo_beta": 375.9898986816406 | |
| }, | |
| { | |
| "epoch": 2.1280113367973548, | |
| "eval_dpo_loss": 0.6708096265792847, | |
| "eval_logits": -11.47172737121582, | |
| "eval_logps": -624.3671875, | |
| "eval_loss": 0.39592552185058594, | |
| "eval_objective": 0.3955978453159332, | |
| "eval_ranking_idealized": 0.9870600700378418, | |
| "eval_ranking_idealized_expo": 0.6319875717163086, | |
| "eval_ranking_simple": 0.6024844646453857, | |
| "eval_regularize": 0.3955978453159332, | |
| "eval_runtime": 309.3114, | |
| "eval_samples_per_second": 18.719, | |
| "eval_steps_per_second": 1.562, | |
| "eval_wo_beta": 182.7602081298828, | |
| "step": 750 | |
| }, | |
| { | |
| "dpo_loss": 0.5449449419975281, | |
| "epoch": 2.269721303731696, | |
| "grad_norm": 6.765232021702658, | |
| "learning_rate": 3.3176699082935546e-06, | |
| "logits": -11.165037155151367, | |
| "logps": -677.394775390625, | |
| "loss": 0.143, | |
| "objective": 0.14202022552490234, | |
| "ranking_idealized": 0.98458331823349, | |
| "ranking_idealized_expo": 0.6179166436195374, | |
| "ranking_simple": 0.9054166674613953, | |
| "regularize": 0.14202022552490234, | |
| "step": 800, | |
| "wo_beta": 368.1688537597656 | |
| }, | |
| { | |
| "epoch": 2.269721303731696, | |
| "eval_dpo_loss": 0.6701000332832336, | |
| "eval_logits": -11.25588607788086, | |
| "eval_logps": -657.3067016601562, | |
| "eval_loss": 0.395544171333313, | |
| "eval_objective": 0.395794540643692, | |
| "eval_ranking_idealized": 0.9870600700378418, | |
| "eval_ranking_idealized_expo": 0.6319875717163086, | |
| "eval_ranking_simple": 0.600931704044342, | |
| "eval_regularize": 0.395794540643692, | |
| "eval_runtime": 308.0676, | |
| "eval_samples_per_second": 18.795, | |
| "eval_steps_per_second": 1.568, | |
| "eval_wo_beta": 190.53713989257812, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.269721303731696, | |
| "step": 800, | |
| "total_flos": 0.0, | |
| "train_loss": 0.051899830102920534, | |
| "train_runtime": 6898.2847, | |
| "train_samples_per_second": 36.822, | |
| "train_steps_per_second": 0.255 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1760, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |