| { | |
| "best_global_step": 800, | |
| "best_metric": 0.2848590016365051, | |
| "best_model_checkpoint": "/kaggle/working/Llama-Factory-out/checkpoint-800", | |
| "epoch": 2.0, | |
| "eval_steps": 50, | |
| "global_step": 848, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02359882005899705, | |
| "grad_norm": 22.34249496459961, | |
| "learning_rate": 1.8e-06, | |
| "loss": 0.9401, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0471976401179941, | |
| "grad_norm": 5.369502544403076, | |
| "learning_rate": 3.8e-06, | |
| "loss": 0.4883, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07079646017699115, | |
| "grad_norm": 4.609455585479736, | |
| "learning_rate": 5.8e-06, | |
| "loss": 0.2716, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0943952802359882, | |
| "grad_norm": 4.0787458419799805, | |
| "learning_rate": 7.8e-06, | |
| "loss": 0.3014, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11799410029498525, | |
| "grad_norm": 3.1666529178619385, | |
| "learning_rate": 9.8e-06, | |
| "loss": 0.2465, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11799410029498525, | |
| "eval_loss": 0.38123074173927307, | |
| "eval_runtime": 375.1701, | |
| "eval_samples_per_second": 3.145, | |
| "eval_steps_per_second": 0.786, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1415929203539823, | |
| "grad_norm": 6.0952606201171875, | |
| "learning_rate": 1.1799999999999999e-05, | |
| "loss": 0.2726, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16519174041297935, | |
| "grad_norm": 6.293701171875, | |
| "learning_rate": 1.38e-05, | |
| "loss": 0.2495, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1887905604719764, | |
| "grad_norm": 3.303353786468506, | |
| "learning_rate": 1.58e-05, | |
| "loss": 0.2617, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21238938053097345, | |
| "grad_norm": 2.348959445953369, | |
| "learning_rate": 1.699884721115522e-05, | |
| "loss": 0.2635, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2359882005899705, | |
| "grad_norm": 2.1490566730499268, | |
| "learning_rate": 1.698588192740479e-05, | |
| "loss": 0.2805, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2359882005899705, | |
| "eval_loss": 0.344037264585495, | |
| "eval_runtime": 375.9092, | |
| "eval_samples_per_second": 3.139, | |
| "eval_steps_per_second": 0.785, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25958702064896755, | |
| "grad_norm": 3.625964403152466, | |
| "learning_rate": 1.695853242428357e-05, | |
| "loss": 0.2473, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2831858407079646, | |
| "grad_norm": 1.9131460189819336, | |
| "learning_rate": 1.6916845061292673e-05, | |
| "loss": 0.2083, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.30678466076696165, | |
| "grad_norm": 3.0459189414978027, | |
| "learning_rate": 1.6860890501703082e-05, | |
| "loss": 0.2358, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3303834808259587, | |
| "grad_norm": 4.418868541717529, | |
| "learning_rate": 1.6790763592776032e-05, | |
| "loss": 0.2745, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.35398230088495575, | |
| "grad_norm": 2.294529438018799, | |
| "learning_rate": 1.670658320498962e-05, | |
| "loss": 0.2016, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.35398230088495575, | |
| "eval_loss": 0.32990705966949463, | |
| "eval_runtime": 375.8551, | |
| "eval_samples_per_second": 3.14, | |
| "eval_steps_per_second": 0.785, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3775811209439528, | |
| "grad_norm": 2.648970603942871, | |
| "learning_rate": 1.660849203054426e-05, | |
| "loss": 0.1936, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.40117994100294985, | |
| "grad_norm": 2.6948256492614746, | |
| "learning_rate": 1.6496656341488462e-05, | |
| "loss": 0.2291, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4247787610619469, | |
| "grad_norm": 3.7231318950653076, | |
| "learning_rate": 1.6371265707875017e-05, | |
| "loss": 0.2248, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.44837758112094395, | |
| "grad_norm": 1.2238047122955322, | |
| "learning_rate": 1.6232532676425206e-05, | |
| "loss": 0.1789, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.471976401179941, | |
| "grad_norm": 3.25620174407959, | |
| "learning_rate": 1.608069241024588e-05, | |
| "loss": 0.3261, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.471976401179941, | |
| "eval_loss": 0.3187030255794525, | |
| "eval_runtime": 376.0322, | |
| "eval_samples_per_second": 3.138, | |
| "eval_steps_per_second": 0.785, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.49557522123893805, | |
| "grad_norm": 5.596831798553467, | |
| "learning_rate": 1.5916002290209964e-05, | |
| "loss": 0.2322, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5191740412979351, | |
| "grad_norm": 2.483771562576294, | |
| "learning_rate": 1.5738741478676192e-05, | |
| "loss": 0.2322, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5427728613569321, | |
| "grad_norm": 2.2052314281463623, | |
| "learning_rate": 1.5549210446287542e-05, | |
| "loss": 0.2337, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5663716814159292, | |
| "grad_norm": 4.261275768280029, | |
| "learning_rate": 1.534773046265049e-05, | |
| "loss": 0.2147, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5899705014749262, | |
| "grad_norm": 2.935073137283325, | |
| "learning_rate": 1.5134643051758448e-05, | |
| "loss": 0.2523, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5899705014749262, | |
| "eval_loss": 0.3116294741630554, | |
| "eval_runtime": 375.6346, | |
| "eval_samples_per_second": 3.141, | |
| "eval_steps_per_second": 0.785, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6135693215339233, | |
| "grad_norm": 4.341355323791504, | |
| "learning_rate": 1.4910309413082452e-05, | |
| "loss": 0.3063, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6371681415929203, | |
| "grad_norm": 2.187041759490967, | |
| "learning_rate": 1.4675109809310403e-05, | |
| "loss": 0.2022, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6607669616519174, | |
| "grad_norm": 1.6396753787994385, | |
| "learning_rate": 1.442944292177272e-05, | |
| "loss": 0.2349, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6843657817109144, | |
| "grad_norm": 4.564992904663086, | |
| "learning_rate": 1.4173725174646962e-05, | |
| "loss": 0.2014, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7079646017699115, | |
| "grad_norm": 2.3131611347198486, | |
| "learning_rate": 1.3908390029086974e-05, | |
| "loss": 0.2505, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7079646017699115, | |
| "eval_loss": 0.30485060811042786, | |
| "eval_runtime": 376.7196, | |
| "eval_samples_per_second": 3.132, | |
| "eval_steps_per_second": 0.783, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7315634218289085, | |
| "grad_norm": 2.313690662384033, | |
| "learning_rate": 1.363388724847306e-05, | |
| "loss": 0.2047, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7551622418879056, | |
| "grad_norm": 3.2190001010894775, | |
| "learning_rate": 1.335068213602862e-05, | |
| "loss": 0.2269, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7787610619469026, | |
| "grad_norm": 1.8587112426757812, | |
| "learning_rate": 1.3059254746095588e-05, | |
| "loss": 0.2213, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8023598820058997, | |
| "grad_norm": 1.2564051151275635, | |
| "learning_rate": 1.2760099070405554e-05, | |
| "loss": 0.1944, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8259587020648967, | |
| "grad_norm": 1.7770769596099854, | |
| "learning_rate": 1.2453722200725996e-05, | |
| "loss": 0.2371, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8259587020648967, | |
| "eval_loss": 0.29784390330314636, | |
| "eval_runtime": 376.2347, | |
| "eval_samples_per_second": 3.136, | |
| "eval_steps_per_second": 0.784, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8495575221238938, | |
| "grad_norm": 1.94675874710083, | |
| "learning_rate": 1.2140643469300905e-05, | |
| "loss": 0.2745, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8731563421828908, | |
| "grad_norm": 2.1903910636901855, | |
| "learning_rate": 1.1821393568542884e-05, | |
| "loss": 0.2029, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8967551622418879, | |
| "grad_norm": 2.2799696922302246, | |
| "learning_rate": 1.1496513651468901e-05, | |
| "loss": 0.2394, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9203539823008849, | |
| "grad_norm": 2.491417646408081, | |
| "learning_rate": 1.116655441440449e-05, | |
| "loss": 0.2071, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.943952802359882, | |
| "grad_norm": 1.9791756868362427, | |
| "learning_rate": 1.0832075163511334e-05, | |
| "loss": 0.2177, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.943952802359882, | |
| "eval_loss": 0.2940136194229126, | |
| "eval_runtime": 376.4574, | |
| "eval_samples_per_second": 3.134, | |
| "eval_steps_per_second": 0.784, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.967551622418879, | |
| "grad_norm": 1.4067103862762451, | |
| "learning_rate": 1.0493642866720528e-05, | |
| "loss": 0.206, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9911504424778761, | |
| "grad_norm": 2.350339651107788, | |
| "learning_rate": 1.0151831192678511e-05, | |
| "loss": 0.2531, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.0141592920353983, | |
| "grad_norm": 2.0622878074645996, | |
| "learning_rate": 9.807219538334829e-06, | |
| "loss": 0.2002, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.0377581120943953, | |
| "grad_norm": 1.5239025354385376, | |
| "learning_rate": 9.460392046819943e-06, | |
| "loss": 0.1457, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0613569321533922, | |
| "grad_norm": 1.3972654342651367, | |
| "learning_rate": 9.11193661727792e-06, | |
| "loss": 0.1686, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0613569321533922, | |
| "eval_loss": 0.29345282912254333, | |
| "eval_runtime": 376.3252, | |
| "eval_samples_per_second": 3.136, | |
| "eval_steps_per_second": 0.784, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0849557522123894, | |
| "grad_norm": 2.420490026473999, | |
| "learning_rate": 8.762443908332387e-06, | |
| "loss": 0.1673, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.1085545722713865, | |
| "grad_norm": 2.7378032207489014, | |
| "learning_rate": 8.412506336874943e-06, | |
| "loss": 0.1962, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.1321533923303835, | |
| "grad_norm": 3.4118051528930664, | |
| "learning_rate": 8.062717073873204e-06, | |
| "loss": 0.1875, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1557522123893804, | |
| "grad_norm": 1.5541094541549683, | |
| "learning_rate": 7.713669038900597e-06, | |
| "loss": 0.1828, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1793510324483776, | |
| "grad_norm": 1.0582072734832764, | |
| "learning_rate": 7.36595389509231e-06, | |
| "loss": 0.1189, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.1793510324483776, | |
| "eval_loss": 0.29354554414749146, | |
| "eval_runtime": 375.7093, | |
| "eval_samples_per_second": 3.141, | |
| "eval_steps_per_second": 0.785, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.2029498525073747, | |
| "grad_norm": 2.497019052505493, | |
| "learning_rate": 7.020161046230986e-06, | |
| "loss": 0.1473, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.2265486725663717, | |
| "grad_norm": 2.6418516635894775, | |
| "learning_rate": 6.676876637662204e-06, | |
| "loss": 0.2029, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2501474926253686, | |
| "grad_norm": 2.695983648300171, | |
| "learning_rate": 6.33668256273325e-06, | |
| "loss": 0.1751, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2737463126843658, | |
| "grad_norm": 2.907141923904419, | |
| "learning_rate": 6.000155476439363e-06, | |
| "loss": 0.1648, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.297345132743363, | |
| "grad_norm": 1.4841465950012207, | |
| "learning_rate": 5.667865817949368e-06, | |
| "loss": 0.1955, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.297345132743363, | |
| "eval_loss": 0.29069384932518005, | |
| "eval_runtime": 375.8529, | |
| "eval_samples_per_second": 3.14, | |
| "eval_steps_per_second": 0.785, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.3209439528023599, | |
| "grad_norm": 1.7871296405792236, | |
| "learning_rate": 5.340376843667641e-06, | |
| "loss": 0.1749, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.3445427728613568, | |
| "grad_norm": 1.2715787887573242, | |
| "learning_rate": 5.01824367247138e-06, | |
| "loss": 0.1471, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.368141592920354, | |
| "grad_norm": 2.7896149158477783, | |
| "learning_rate": 4.702012344741626e-06, | |
| "loss": 0.2003, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3917404129793511, | |
| "grad_norm": 0.8350914716720581, | |
| "learning_rate": 4.39221889678302e-06, | |
| "loss": 0.1667, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.415339233038348, | |
| "grad_norm": 1.4638220071792603, | |
| "learning_rate": 4.089388452201232e-06, | |
| "loss": 0.1341, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.415339233038348, | |
| "eval_loss": 0.28851860761642456, | |
| "eval_runtime": 375.2313, | |
| "eval_samples_per_second": 3.145, | |
| "eval_steps_per_second": 0.786, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.438938053097345, | |
| "grad_norm": 1.2502944469451904, | |
| "learning_rate": 3.7940343317782858e-06, | |
| "loss": 0.1275, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.4625368731563422, | |
| "grad_norm": 3.265089273452759, | |
| "learning_rate": 3.5066571833544922e-06, | |
| "loss": 0.1594, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4861356932153393, | |
| "grad_norm": 1.8018122911453247, | |
| "learning_rate": 3.227744133192099e-06, | |
| "loss": 0.17, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.5097345132743363, | |
| "grad_norm": 2.1491341590881348, | |
| "learning_rate": 2.9577679602589466e-06, | |
| "loss": 0.2164, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.5333333333333332, | |
| "grad_norm": 0.88905930519104, | |
| "learning_rate": 2.6971862948319636e-06, | |
| "loss": 0.1591, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.5333333333333332, | |
| "eval_loss": 0.2874307930469513, | |
| "eval_runtime": 376.0722, | |
| "eval_samples_per_second": 3.138, | |
| "eval_steps_per_second": 0.784, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.5569321533923304, | |
| "grad_norm": 1.6071833372116089, | |
| "learning_rate": 2.44644084277879e-06, | |
| "loss": 0.1565, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5805309734513275, | |
| "grad_norm": 2.2239670753479004, | |
| "learning_rate": 2.205956636832558e-06, | |
| "loss": 0.1556, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.6041297935103245, | |
| "grad_norm": 2.679152011871338, | |
| "learning_rate": 1.976141316128839e-06, | |
| "loss": 0.1882, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.6277286135693214, | |
| "grad_norm": 1.2197039127349854, | |
| "learning_rate": 1.7573844352261477e-06, | |
| "loss": 0.1485, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.6513274336283186, | |
| "grad_norm": 1.7231520414352417, | |
| "learning_rate": 1.5500568037811163e-06, | |
| "loss": 0.1594, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6513274336283186, | |
| "eval_loss": 0.2859014570713043, | |
| "eval_runtime": 376.4703, | |
| "eval_samples_per_second": 3.134, | |
| "eval_steps_per_second": 0.784, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6749262536873157, | |
| "grad_norm": 3.1574690341949463, | |
| "learning_rate": 1.3545098579977715e-06, | |
| "loss": 0.219, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.6985250737463127, | |
| "grad_norm": 1.9597457647323608, | |
| "learning_rate": 1.171075064916245e-06, | |
| "loss": 0.1802, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.7221238938053096, | |
| "grad_norm": 2.8772366046905518, | |
| "learning_rate": 1.0000633605507938e-06, | |
| "loss": 0.139, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.7457227138643068, | |
| "grad_norm": 2.4213573932647705, | |
| "learning_rate": 8.417646228294382e-07, | |
| "loss": 0.1385, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.769321533923304, | |
| "grad_norm": 3.8496439456939697, | |
| "learning_rate": 6.964471802286975e-07, | |
| "loss": 0.1452, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.769321533923304, | |
| "eval_loss": 0.28498101234436035, | |
| "eval_runtime": 376.0272, | |
| "eval_samples_per_second": 3.138, | |
| "eval_steps_per_second": 0.785, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.7929203539823009, | |
| "grad_norm": 0.9809938669204712, | |
| "learning_rate": 5.643573569362806e-07, | |
| "loss": 0.1819, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.8165191740412978, | |
| "grad_norm": 3.2049953937530518, | |
| "learning_rate": 4.4571905531273924e-07, | |
| "loss": 0.2087, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.840117994100295, | |
| "grad_norm": 1.921066403388977, | |
| "learning_rate": 3.4073337635982153e-07, | |
| "loss": 0.2, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.8637168141592921, | |
| "grad_norm": 1.9557863473892212, | |
| "learning_rate": 2.495782788388865e-07, | |
| "loss": 0.1669, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.887315634218289, | |
| "grad_norm": 3.648777484893799, | |
| "learning_rate": 1.7240827761718658e-07, | |
| "loss": 0.1845, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.887315634218289, | |
| "eval_loss": 0.2848590016365051, | |
| "eval_runtime": 376.2036, | |
| "eval_samples_per_second": 3.137, | |
| "eval_steps_per_second": 0.784, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.910914454277286, | |
| "grad_norm": 1.149221420288086, | |
| "learning_rate": 1.09354181753332e-07, | |
| "loss": 0.1676, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.9345132743362832, | |
| "grad_norm": 2.6451611518859863, | |
| "learning_rate": 6.05228727659301e-08, | |
| "loss": 0.157, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.9581120943952803, | |
| "grad_norm": 2.323096990585327, | |
| "learning_rate": 2.5997123461232284e-08, | |
| "loss": 0.1613, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.9817109144542773, | |
| "grad_norm": 2.0650336742401123, | |
| "learning_rate": 5.835457626888918e-09, | |
| "loss": 0.1628, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 848, | |
| "total_flos": 2.0361935130617446e+17, | |
| "train_loss": 0.21512415639634402, | |
| "train_runtime": 40076.9541, | |
| "train_samples_per_second": 0.677, | |
| "train_steps_per_second": 0.021 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 848, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.0361935130617446e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |