| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.99775617053104, | |
| "eval_steps": 100, | |
| "global_step": 1002, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0029917726252804786, | |
| "grad_norm": 12.0, | |
| "learning_rate": 4.95049504950495e-09, | |
| "logits/chosen": -17.95128631591797, | |
| "logits/rejected": -17.9676513671875, | |
| "logps/chosen": -470.5423889160156, | |
| "logps/rejected": -476.4247131347656, | |
| "loss": 0.6931, | |
| "rewards/accuracies": 0.0, | |
| "rewards/chosen": 0.0, | |
| "rewards/margins": 0.0, | |
| "rewards/rejected": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.029917726252804786, | |
| "grad_norm": 12.75, | |
| "learning_rate": 4.950495049504951e-08, | |
| "logits/chosen": -18.26405906677246, | |
| "logits/rejected": -18.187000274658203, | |
| "logps/chosen": -499.1011962890625, | |
| "logps/rejected": -476.3055419921875, | |
| "loss": 0.6925, | |
| "rewards/accuracies": 0.1753472238779068, | |
| "rewards/chosen": -0.0009479601285420358, | |
| "rewards/margins": 0.0018414496444165707, | |
| "rewards/rejected": -0.002789410063996911, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05983545250560957, | |
| "grad_norm": 14.5, | |
| "learning_rate": 9.900990099009901e-08, | |
| "logits/chosen": -18.466373443603516, | |
| "logits/rejected": -18.416664123535156, | |
| "logps/chosen": -518.89794921875, | |
| "logps/rejected": -501.88494873046875, | |
| "loss": 0.6937, | |
| "rewards/accuracies": 0.48124998807907104, | |
| "rewards/chosen": 0.004138890188187361, | |
| "rewards/margins": 0.0013234459329396486, | |
| "rewards/rejected": 0.0028154447209089994, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08975317875841436, | |
| "grad_norm": 12.125, | |
| "learning_rate": 1.485148514851485e-07, | |
| "logits/chosen": -18.632816314697266, | |
| "logits/rejected": -18.364212036132812, | |
| "logps/chosen": -518.1107177734375, | |
| "logps/rejected": -474.103271484375, | |
| "loss": 0.6978, | |
| "rewards/accuracies": 0.44218748807907104, | |
| "rewards/chosen": -0.0032092046458274126, | |
| "rewards/margins": -0.005843925289809704, | |
| "rewards/rejected": 0.0026347211096435785, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11967090501121914, | |
| "grad_norm": 12.1875, | |
| "learning_rate": 1.9801980198019803e-07, | |
| "logits/chosen": -18.572345733642578, | |
| "logits/rejected": -18.411455154418945, | |
| "logps/chosen": -499.1954650878906, | |
| "logps/rejected": -475.9703674316406, | |
| "loss": 0.6935, | |
| "rewards/accuracies": 0.484375, | |
| "rewards/chosen": -0.007920954376459122, | |
| "rewards/margins": 0.003416565014049411, | |
| "rewards/rejected": -0.011337519623339176, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14958863126402394, | |
| "grad_norm": 14.0625, | |
| "learning_rate": 2.475247524752475e-07, | |
| "logits/chosen": -18.346946716308594, | |
| "logits/rejected": -18.163400650024414, | |
| "logps/chosen": -488.15997314453125, | |
| "logps/rejected": -466.6705017089844, | |
| "loss": 0.6953, | |
| "rewards/accuracies": 0.4781250059604645, | |
| "rewards/chosen": -0.0012789719039574265, | |
| "rewards/margins": -0.00010849386308109388, | |
| "rewards/rejected": -0.0011704775970429182, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17950635751682872, | |
| "grad_norm": 14.375, | |
| "learning_rate": 2.97029702970297e-07, | |
| "logits/chosen": -18.437816619873047, | |
| "logits/rejected": -18.432828903198242, | |
| "logps/chosen": -494.74176025390625, | |
| "logps/rejected": -490.072021484375, | |
| "loss": 0.6937, | |
| "rewards/accuracies": 0.48124998807907104, | |
| "rewards/chosen": 0.005937687586992979, | |
| "rewards/margins": 0.003491427283734083, | |
| "rewards/rejected": 0.0024462605360895395, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2094240837696335, | |
| "grad_norm": 12.9375, | |
| "learning_rate": 3.465346534653465e-07, | |
| "logits/chosen": -18.613513946533203, | |
| "logits/rejected": -18.44839859008789, | |
| "logps/chosen": -496.1435546875, | |
| "logps/rejected": -476.2933044433594, | |
| "loss": 0.6983, | |
| "rewards/accuracies": 0.45781248807907104, | |
| "rewards/chosen": -0.006354107521474361, | |
| "rewards/margins": -0.00639874953776598, | |
| "rewards/rejected": 4.464127050596289e-05, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2393418100224383, | |
| "grad_norm": 13.0, | |
| "learning_rate": 3.9603960396039606e-07, | |
| "logits/chosen": -18.565101623535156, | |
| "logits/rejected": -18.38371467590332, | |
| "logps/chosen": -515.5604858398438, | |
| "logps/rejected": -464.8475646972656, | |
| "loss": 0.6953, | |
| "rewards/accuracies": 0.46875, | |
| "rewards/chosen": -0.010281904600560665, | |
| "rewards/margins": 0.0007311844383366406, | |
| "rewards/rejected": -0.01101309061050415, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.26925953627524307, | |
| "grad_norm": 12.75, | |
| "learning_rate": 4.4554455445544555e-07, | |
| "logits/chosen": -18.506877899169922, | |
| "logits/rejected": -18.355941772460938, | |
| "logps/chosen": -496.4579162597656, | |
| "logps/rejected": -481.5419921875, | |
| "loss": 0.696, | |
| "rewards/accuracies": 0.4765625, | |
| "rewards/chosen": -0.008175070397555828, | |
| "rewards/margins": -0.0013799158623442054, | |
| "rewards/rejected": -0.006795152090489864, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2991772625280479, | |
| "grad_norm": 13.25, | |
| "learning_rate": 4.95049504950495e-07, | |
| "logits/chosen": -18.576337814331055, | |
| "logits/rejected": -18.462890625, | |
| "logps/chosen": -507.07696533203125, | |
| "logps/rejected": -471.42303466796875, | |
| "loss": 0.6955, | |
| "rewards/accuracies": 0.4859375059604645, | |
| "rewards/chosen": 0.007285754196345806, | |
| "rewards/margins": 0.0004216151428408921, | |
| "rewards/rejected": 0.0068641407415270805, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2991772625280479, | |
| "eval_logits/chosen": -18.482393264770508, | |
| "eval_logits/rejected": -18.36368751525879, | |
| "eval_logps/chosen": -494.2335510253906, | |
| "eval_logps/rejected": -478.78997802734375, | |
| "eval_loss": 0.6958388686180115, | |
| "eval_rewards/accuracies": 0.4701046347618103, | |
| "eval_rewards/chosen": -0.001653533661738038, | |
| "eval_rewards/margins": -0.0008236159919761121, | |
| "eval_rewards/rejected": -0.0008299172623082995, | |
| "eval_runtime": 844.1668, | |
| "eval_samples_per_second": 6.335, | |
| "eval_steps_per_second": 0.792, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.32909498878085264, | |
| "grad_norm": 14.25, | |
| "learning_rate": 4.998769137458909e-07, | |
| "logits/chosen": -18.438594818115234, | |
| "logits/rejected": -18.30778694152832, | |
| "logps/chosen": -488.8753967285156, | |
| "logps/rejected": -469.21240234375, | |
| "loss": 0.693, | |
| "rewards/accuracies": 0.49687498807907104, | |
| "rewards/chosen": -0.0037526420783251524, | |
| "rewards/margins": 0.005193626508116722, | |
| "rewards/rejected": -0.008946266956627369, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.35901271503365745, | |
| "grad_norm": 13.375, | |
| "learning_rate": 4.994515860008407e-07, | |
| "logits/chosen": -18.361738204956055, | |
| "logits/rejected": -18.35593032836914, | |
| "logps/chosen": -502.665771484375, | |
| "logps/rejected": -485.8645935058594, | |
| "loss": 0.6939, | |
| "rewards/accuracies": 0.4921875, | |
| "rewards/chosen": -0.011272026225924492, | |
| "rewards/margins": 0.0029675140976905823, | |
| "rewards/rejected": -0.0142395393922925, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3889304412864622, | |
| "grad_norm": 14.4375, | |
| "learning_rate": 4.987230141051212e-07, | |
| "logits/chosen": -18.523672103881836, | |
| "logits/rejected": -18.332469940185547, | |
| "logps/chosen": -497.9520568847656, | |
| "logps/rejected": -494.5643615722656, | |
| "loss": 0.6936, | |
| "rewards/accuracies": 0.48124998807907104, | |
| "rewards/chosen": 0.0009459417196922004, | |
| "rewards/margins": 0.003786131041124463, | |
| "rewards/rejected": -0.0028401894960552454, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.418848167539267, | |
| "grad_norm": 13.6875, | |
| "learning_rate": 4.976920837422805e-07, | |
| "logits/chosen": -18.39594078063965, | |
| "logits/rejected": -18.280231475830078, | |
| "logps/chosen": -499.1576232910156, | |
| "logps/rejected": -480.56964111328125, | |
| "loss": 0.692, | |
| "rewards/accuracies": 0.504687488079071, | |
| "rewards/chosen": -0.008311725221574306, | |
| "rewards/margins": 0.006742014549672604, | |
| "rewards/rejected": -0.01505373977124691, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4487658937920718, | |
| "grad_norm": 13.5, | |
| "learning_rate": 4.963600481559129e-07, | |
| "logits/chosen": -18.300243377685547, | |
| "logits/rejected": -18.194604873657227, | |
| "logps/chosen": -495.46173095703125, | |
| "logps/rejected": -483.1366271972656, | |
| "loss": 0.6985, | |
| "rewards/accuracies": 0.4671874940395355, | |
| "rewards/chosen": -0.014861522242426872, | |
| "rewards/margins": -0.005774814635515213, | |
| "rewards/rejected": -0.009086708538234234, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4786836200448766, | |
| "grad_norm": 14.9375, | |
| "learning_rate": 4.947285266261623e-07, | |
| "logits/chosen": -18.28691864013672, | |
| "logits/rejected": -18.09464454650879, | |
| "logps/chosen": -501.8270568847656, | |
| "logps/rejected": -481.210693359375, | |
| "loss": 0.6892, | |
| "rewards/accuracies": 0.542187511920929, | |
| "rewards/chosen": 0.004282023757696152, | |
| "rewards/margins": 0.012691694311797619, | |
| "rewards/rejected": -0.008409671485424042, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5086013462976814, | |
| "grad_norm": 12.375, | |
| "learning_rate": 4.927995025012548e-07, | |
| "logits/chosen": -18.599102020263672, | |
| "logits/rejected": -18.47110366821289, | |
| "logps/chosen": -497.13409423828125, | |
| "logps/rejected": -462.9967346191406, | |
| "loss": 0.6976, | |
| "rewards/accuracies": 0.47187501192092896, | |
| "rewards/chosen": -0.015234975144267082, | |
| "rewards/margins": -0.004649547394365072, | |
| "rewards/rejected": -0.010585429146885872, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5385190725504861, | |
| "grad_norm": 18.0, | |
| "learning_rate": 4.905753207864547e-07, | |
| "logits/chosen": -18.513076782226562, | |
| "logits/rejected": -18.358755111694336, | |
| "logps/chosen": -499.5277404785156, | |
| "logps/rejected": -484.95782470703125, | |
| "loss": 0.6963, | |
| "rewards/accuracies": 0.47968751192092896, | |
| "rewards/chosen": -0.002763888565823436, | |
| "rewards/margins": -0.0016130201984196901, | |
| "rewards/rejected": -0.0011508697643876076, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5684367988032909, | |
| "grad_norm": 14.0625, | |
| "learning_rate": 4.880586852933747e-07, | |
| "logits/chosen": -18.47112464904785, | |
| "logits/rejected": -18.298198699951172, | |
| "logps/chosen": -504.328857421875, | |
| "logps/rejected": -473.43359375, | |
| "loss": 0.6939, | |
| "rewards/accuracies": 0.512499988079071, | |
| "rewards/chosen": -0.0022486697416752577, | |
| "rewards/margins": 0.00311539089307189, | |
| "rewards/rejected": -0.005364061798900366, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5983545250560958, | |
| "grad_norm": 13.9375, | |
| "learning_rate": 4.852526553531054e-07, | |
| "logits/chosen": -18.492422103881836, | |
| "logits/rejected": -18.396549224853516, | |
| "logps/chosen": -498.78741455078125, | |
| "logps/rejected": -481.09405517578125, | |
| "loss": 0.6906, | |
| "rewards/accuracies": 0.4781250059604645, | |
| "rewards/chosen": -0.0009043412283062935, | |
| "rewards/margins": 0.010298773646354675, | |
| "rewards/rejected": -0.01120311301201582, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5983545250560958, | |
| "eval_logits/chosen": -18.480627059936523, | |
| "eval_logits/rejected": -18.362462997436523, | |
| "eval_logps/chosen": -494.2452697753906, | |
| "eval_logps/rejected": -478.79736328125, | |
| "eval_loss": 0.6961907148361206, | |
| "eval_rewards/accuracies": 0.4744020998477936, | |
| "eval_rewards/chosen": -0.0028220494277775288, | |
| "eval_rewards/margins": -0.001257332507520914, | |
| "eval_rewards/rejected": -0.0015647169202566147, | |
| "eval_runtime": 842.3412, | |
| "eval_samples_per_second": 6.349, | |
| "eval_steps_per_second": 0.794, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6282722513089005, | |
| "grad_norm": 13.6875, | |
| "learning_rate": 4.8216064209716e-07, | |
| "logits/chosen": -18.475950241088867, | |
| "logits/rejected": -18.323816299438477, | |
| "logps/chosen": -510.2359313964844, | |
| "logps/rejected": -491.6826171875, | |
| "loss": 0.6954, | |
| "rewards/accuracies": 0.4703125059604645, | |
| "rewards/chosen": -0.00869015883654356, | |
| "rewards/margins": 0.0011458725202828646, | |
| "rewards/rejected": -0.009836031123995781, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.6581899775617053, | |
| "grad_norm": 13.75, | |
| "learning_rate": 4.787864043107546e-07, | |
| "logits/chosen": -18.483421325683594, | |
| "logits/rejected": -18.315481185913086, | |
| "logps/chosen": -505.24383544921875, | |
| "logps/rejected": -480.8597717285156, | |
| "loss": 0.6945, | |
| "rewards/accuracies": 0.4984374940395355, | |
| "rewards/chosen": -0.007081210613250732, | |
| "rewards/margins": 0.002295692218467593, | |
| "rewards/rejected": -0.009376903995871544, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6881077038145101, | |
| "grad_norm": 12.3125, | |
| "learning_rate": 4.751340438634669e-07, | |
| "logits/chosen": -18.307737350463867, | |
| "logits/rejected": -18.23043441772461, | |
| "logps/chosen": -492.05596923828125, | |
| "logps/rejected": -478.38238525390625, | |
| "loss": 0.6932, | |
| "rewards/accuracies": 0.4828124940395355, | |
| "rewards/chosen": -0.005866049323230982, | |
| "rewards/margins": 0.005141937639564276, | |
| "rewards/rejected": -0.011007988825440407, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.7180254300673149, | |
| "grad_norm": 13.8125, | |
| "learning_rate": 4.712080007228254e-07, | |
| "logits/chosen": -18.248706817626953, | |
| "logits/rejected": -18.240238189697266, | |
| "logps/chosen": -498.770263671875, | |
| "logps/rejected": -494.4297790527344, | |
| "loss": 0.6899, | |
| "rewards/accuracies": 0.5015624761581421, | |
| "rewards/chosen": -0.0009179557673633099, | |
| "rewards/margins": 0.01158793456852436, | |
| "rewards/rejected": -0.012505888938903809, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.7479431563201197, | |
| "grad_norm": 15.5625, | |
| "learning_rate": 4.670130475568927e-07, | |
| "logits/chosen": -18.496627807617188, | |
| "logits/rejected": -18.331436157226562, | |
| "logps/chosen": -501.021728515625, | |
| "logps/rejected": -485.9256896972656, | |
| "loss": 0.693, | |
| "rewards/accuracies": 0.4859375059604645, | |
| "rewards/chosen": 0.0024902846198529005, | |
| "rewards/margins": 0.005465887952595949, | |
| "rewards/rejected": -0.002975603099912405, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7778608825729244, | |
| "grad_norm": 12.625, | |
| "learning_rate": 4.6255428393240354e-07, | |
| "logits/chosen": -18.292850494384766, | |
| "logits/rejected": -18.20071029663086, | |
| "logps/chosen": -479.3639221191406, | |
| "logps/rejected": -463.76776123046875, | |
| "loss": 0.6947, | |
| "rewards/accuracies": 0.484375, | |
| "rewards/chosen": -0.019604574888944626, | |
| "rewards/margins": 0.0011741012567654252, | |
| "rewards/rejected": -0.020778674632310867, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.8077786088257293, | |
| "grad_norm": 13.4375, | |
| "learning_rate": 4.578371301155106e-07, | |
| "logits/chosen": -18.332660675048828, | |
| "logits/rejected": -18.25689697265625, | |
| "logps/chosen": -497.0006408691406, | |
| "logps/rejected": -493.8580017089844, | |
| "loss": 0.6925, | |
| "rewards/accuracies": 0.4937500059604645, | |
| "rewards/chosen": -0.017484821379184723, | |
| "rewards/margins": 0.006399748381227255, | |
| "rewards/rejected": -0.023884572088718414, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.837696335078534, | |
| "grad_norm": 13.625, | |
| "learning_rate": 4.528673204826744e-07, | |
| "logits/chosen": -18.48120880126953, | |
| "logits/rejected": -18.390308380126953, | |
| "logps/chosen": -513.1058959960938, | |
| "logps/rejected": -496.99578857421875, | |
| "loss": 0.6956, | |
| "rewards/accuracies": 0.4515624940395355, | |
| "rewards/chosen": -0.023203711956739426, | |
| "rewards/margins": 0.0008115891250781715, | |
| "rewards/rejected": -0.02401530183851719, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.8676140613313388, | |
| "grad_norm": 15.3125, | |
| "learning_rate": 4.476508965497067e-07, | |
| "logits/chosen": -18.398761749267578, | |
| "logits/rejected": -18.283004760742188, | |
| "logps/chosen": -498.1253967285156, | |
| "logps/rejected": -489.4436950683594, | |
| "loss": 0.697, | |
| "rewards/accuracies": 0.4749999940395355, | |
| "rewards/chosen": -0.015816329047083855, | |
| "rewards/margins": -0.002141923177987337, | |
| "rewards/rejected": -0.013674402609467506, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.8975317875841436, | |
| "grad_norm": 15.0, | |
| "learning_rate": 4.421941996274423e-07, | |
| "logits/chosen": -18.34426498413086, | |
| "logits/rejected": -18.241085052490234, | |
| "logps/chosen": -527.1797485351562, | |
| "logps/rejected": -507.3211975097656, | |
| "loss": 0.6985, | |
| "rewards/accuracies": 0.4593749940395355, | |
| "rewards/chosen": -0.020052501931786537, | |
| "rewards/margins": -0.005515648517757654, | |
| "rewards/rejected": -0.014536852948367596, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.8975317875841436, | |
| "eval_logits/chosen": -18.48088836669922, | |
| "eval_logits/rejected": -18.36236000061035, | |
| "eval_logps/chosen": -494.4387512207031, | |
| "eval_logps/rejected": -478.9952392578125, | |
| "eval_loss": 0.6959420442581177, | |
| "eval_rewards/accuracies": 0.4738415479660034, | |
| "eval_rewards/chosen": -0.022165408357977867, | |
| "eval_rewards/margins": -0.000810055120382458, | |
| "eval_rewards/rejected": -0.02135535702109337, | |
| "eval_runtime": 842.4585, | |
| "eval_samples_per_second": 6.348, | |
| "eval_steps_per_second": 0.794, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9274495138369484, | |
| "grad_norm": 14.0625, | |
| "learning_rate": 4.3650386311296715e-07, | |
| "logits/chosen": -18.639049530029297, | |
| "logits/rejected": -18.473182678222656, | |
| "logps/chosen": -519.571533203125, | |
| "logps/rejected": -493.08416748046875, | |
| "loss": 0.7007, | |
| "rewards/accuracies": 0.44218748807907104, | |
| "rewards/chosen": -0.020600352436304092, | |
| "rewards/margins": -0.009581638500094414, | |
| "rewards/rejected": -0.011018714867532253, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.9573672400897532, | |
| "grad_norm": 14.625, | |
| "learning_rate": 4.305868044257734e-07, | |
| "logits/chosen": -18.35852813720703, | |
| "logits/rejected": -18.237619400024414, | |
| "logps/chosen": -494.0035705566406, | |
| "logps/rejected": -474.61175537109375, | |
| "loss": 0.6962, | |
| "rewards/accuracies": 0.4921875, | |
| "rewards/chosen": -0.03291434049606323, | |
| "rewards/margins": -0.0014624244067817926, | |
| "rewards/rejected": -0.031451914459466934, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.9872849663425579, | |
| "grad_norm": 15.0, | |
| "learning_rate": 4.244502165986448e-07, | |
| "logits/chosen": -18.50986099243164, | |
| "logits/rejected": -18.264389038085938, | |
| "logps/chosen": -487.98284912109375, | |
| "logps/rejected": -478.84002685546875, | |
| "loss": 0.6944, | |
| "rewards/accuracies": 0.4859375059604645, | |
| "rewards/chosen": -0.018264159560203552, | |
| "rewards/margins": 0.0021764684934169054, | |
| "rewards/rejected": -0.02044062688946724, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.0172026925953628, | |
| "grad_norm": 13.0625, | |
| "learning_rate": 4.1810155953349445e-07, | |
| "logits/chosen": -18.608068466186523, | |
| "logits/rejected": -18.53306007385254, | |
| "logps/chosen": -499.0755310058594, | |
| "logps/rejected": -490.98486328125, | |
| "loss": 0.6936, | |
| "rewards/accuracies": 0.47343748807907104, | |
| "rewards/chosen": -0.01962715946137905, | |
| "rewards/margins": 0.00391949201002717, | |
| "rewards/rejected": -0.023546651005744934, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.0471204188481675, | |
| "grad_norm": 12.1875, | |
| "learning_rate": 4.115485509327851e-07, | |
| "logits/chosen": -18.467256546020508, | |
| "logits/rejected": -18.209827423095703, | |
| "logps/chosen": -505.059814453125, | |
| "logps/rejected": -475.1127014160156, | |
| "loss": 0.6934, | |
| "rewards/accuracies": 0.4937500059604645, | |
| "rewards/chosen": -0.009037208743393421, | |
| "rewards/margins": 0.004168554209172726, | |
| "rewards/rejected": -0.013205763883888721, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.0770381451009723, | |
| "grad_norm": 12.4375, | |
| "learning_rate": 4.0479915691755583e-07, | |
| "logits/chosen": -18.381351470947266, | |
| "logits/rejected": -18.23720359802246, | |
| "logps/chosen": -503.64044189453125, | |
| "logps/rejected": -486.0143127441406, | |
| "loss": 0.7002, | |
| "rewards/accuracies": 0.4703125059604645, | |
| "rewards/chosen": -0.015495906583964825, | |
| "rewards/margins": -0.009308911859989166, | |
| "rewards/rejected": -0.006186993792653084, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.106955871353777, | |
| "grad_norm": 13.8125, | |
| "learning_rate": 3.9786158234346e-07, | |
| "logits/chosen": -18.671598434448242, | |
| "logits/rejected": -18.52102279663086, | |
| "logps/chosen": -491.046142578125, | |
| "logps/rejected": -473.78057861328125, | |
| "loss": 0.692, | |
| "rewards/accuracies": 0.48750001192092896, | |
| "rewards/chosen": -0.0006091233226470649, | |
| "rewards/margins": 0.007144009228795767, | |
| "rewards/rejected": -0.007753132376819849, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.136873597606582, | |
| "grad_norm": 14.375, | |
| "learning_rate": 3.90744260826588e-07, | |
| "logits/chosen": -18.341663360595703, | |
| "logits/rejected": -18.282123565673828, | |
| "logps/chosen": -503.53521728515625, | |
| "logps/rejected": -478.75726318359375, | |
| "loss": 0.6975, | |
| "rewards/accuracies": 0.4828124940395355, | |
| "rewards/chosen": -0.014238146133720875, | |
| "rewards/margins": -0.004205497447401285, | |
| "rewards/rejected": -0.010032649151980877, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.1667913238593868, | |
| "grad_norm": 13.75, | |
| "learning_rate": 3.834558444911977e-07, | |
| "logits/chosen": -18.506235122680664, | |
| "logits/rejected": -18.454498291015625, | |
| "logps/chosen": -501.6888122558594, | |
| "logps/rejected": -492.0193786621094, | |
| "loss": 0.6937, | |
| "rewards/accuracies": 0.4671874940395355, | |
| "rewards/chosen": -0.013215325772762299, | |
| "rewards/margins": 0.004076224751770496, | |
| "rewards/rejected": -0.01729154959321022, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.1967090501121915, | |
| "grad_norm": 11.4375, | |
| "learning_rate": 3.760051934518178e-07, | |
| "logits/chosen": -18.325563430786133, | |
| "logits/rejected": -18.207347869873047, | |
| "logps/chosen": -490.45599365234375, | |
| "logps/rejected": -484.768798828125, | |
| "loss": 0.6946, | |
| "rewards/accuracies": 0.503125011920929, | |
| "rewards/chosen": -0.012493303045630455, | |
| "rewards/margins": 0.0020187748596072197, | |
| "rewards/rejected": -0.0145120769739151, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.1967090501121915, | |
| "eval_logits/chosen": -18.481069564819336, | |
| "eval_logits/rejected": -18.362834930419922, | |
| "eval_logps/chosen": -494.2017822265625, | |
| "eval_logps/rejected": -478.7664489746094, | |
| "eval_loss": 0.6955097913742065, | |
| "eval_rewards/accuracies": 0.47533631324768066, | |
| "eval_rewards/chosen": 0.0015334173804149032, | |
| "eval_rewards/margins": 5.264274932414992e-06, | |
| "eval_rewards/rejected": 0.0015281536616384983, | |
| "eval_runtime": 842.6072, | |
| "eval_samples_per_second": 6.347, | |
| "eval_steps_per_second": 0.794, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.2266267763649963, | |
| "grad_norm": 12.5, | |
| "learning_rate": 3.6840136504250895e-07, | |
| "logits/chosen": -18.419193267822266, | |
| "logits/rejected": -18.217782974243164, | |
| "logps/chosen": -504.786865234375, | |
| "logps/rejected": -477.596923828125, | |
| "loss": 0.6965, | |
| "rewards/accuracies": 0.4984374940395355, | |
| "rewards/chosen": -0.006161923985928297, | |
| "rewards/margins": -0.001232474809512496, | |
| "rewards/rejected": -0.004929449409246445, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.256544502617801, | |
| "grad_norm": 13.0625, | |
| "learning_rate": 3.6065360280637635e-07, | |
| "logits/chosen": -18.372119903564453, | |
| "logits/rejected": -18.320249557495117, | |
| "logps/chosen": -484.0809020996094, | |
| "logps/rejected": -474.786376953125, | |
| "loss": 0.6929, | |
| "rewards/accuracies": 0.47343748807907104, | |
| "rewards/chosen": -0.009603636339306831, | |
| "rewards/margins": 0.00548522686585784, | |
| "rewards/rejected": -0.015088860876858234, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.2864622288706058, | |
| "grad_norm": 16.375, | |
| "learning_rate": 3.527713252587179e-07, | |
| "logits/chosen": -18.48366928100586, | |
| "logits/rejected": -18.39108657836914, | |
| "logps/chosen": -501.91314697265625, | |
| "logps/rejected": -480.6852111816406, | |
| "loss": 0.6968, | |
| "rewards/accuracies": 0.4671874940395355, | |
| "rewards/chosen": -0.004988933447748423, | |
| "rewards/margins": -0.0021209451369941235, | |
| "rewards/rejected": -0.002867989707738161, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.3163799551234106, | |
| "grad_norm": 14.0625, | |
| "learning_rate": 3.447641144374697e-07, | |
| "logits/chosen": -18.41563606262207, | |
| "logits/rejected": -18.326993942260742, | |
| "logps/chosen": -495.029541015625, | |
| "logps/rejected": -485.95654296875, | |
| "loss": 0.6938, | |
| "rewards/accuracies": 0.5062500238418579, | |
| "rewards/chosen": -0.0021522603929042816, | |
| "rewards/margins": 0.003724109847098589, | |
| "rewards/rejected": -0.005876368843019009, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.3462976813762153, | |
| "grad_norm": 12.8125, | |
| "learning_rate": 3.3664170425486577e-07, | |
| "logits/chosen": -18.418684005737305, | |
| "logits/rejected": -18.22823143005371, | |
| "logps/chosen": -508.91619873046875, | |
| "logps/rejected": -493.2528381347656, | |
| "loss": 0.6962, | |
| "rewards/accuracies": 0.4859375059604645, | |
| "rewards/chosen": -0.016366075724363327, | |
| "rewards/margins": -0.0013246103189885616, | |
| "rewards/rejected": -0.015041463077068329, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.37621540762902, | |
| "grad_norm": 12.25, | |
| "learning_rate": 3.2841396866447216e-07, | |
| "logits/chosen": -18.291414260864258, | |
| "logits/rejected": -18.216777801513672, | |
| "logps/chosen": -494.11651611328125, | |
| "logps/rejected": -479.777587890625, | |
| "loss": 0.6941, | |
| "rewards/accuracies": 0.4749999940395355, | |
| "rewards/chosen": 0.010070102289319038, | |
| "rewards/margins": 0.002756762085482478, | |
| "rewards/rejected": 0.007313339505344629, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.406133133881825, | |
| "grad_norm": 12.125, | |
| "learning_rate": 3.200909096579822e-07, | |
| "logits/chosen": -18.547330856323242, | |
| "logits/rejected": -18.329965591430664, | |
| "logps/chosen": -502.29052734375, | |
| "logps/rejected": -481.80035400390625, | |
| "loss": 0.6937, | |
| "rewards/accuracies": 0.484375, | |
| "rewards/chosen": 0.006962032523006201, | |
| "rewards/margins": 0.004513027612119913, | |
| "rewards/rejected": 0.0024490035139024258, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.4360508601346298, | |
| "grad_norm": 13.75, | |
| "learning_rate": 3.116826451063618e-07, | |
| "logits/chosen": -18.396873474121094, | |
| "logits/rejected": -18.2117862701416, | |
| "logps/chosen": -498.18048095703125, | |
| "logps/rejected": -463.1722106933594, | |
| "loss": 0.6994, | |
| "rewards/accuracies": 0.4625000059604645, | |
| "rewards/chosen": -0.007130985148251057, | |
| "rewards/margins": -0.007668208330869675, | |
| "rewards/rejected": 0.0005372242303565145, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.4659685863874345, | |
| "grad_norm": 13.4375, | |
| "learning_rate": 3.031993964601274e-07, | |
| "logits/chosen": -18.40250015258789, | |
| "logits/rejected": -18.297494888305664, | |
| "logps/chosen": -503.1748962402344, | |
| "logps/rejected": -499.47900390625, | |
| "loss": 0.6945, | |
| "rewards/accuracies": 0.4937500059604645, | |
| "rewards/chosen": -0.006336678750813007, | |
| "rewards/margins": 0.0019012052798643708, | |
| "rewards/rejected": -0.008237885311245918, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.4958863126402393, | |
| "grad_norm": 12.6875, | |
| "learning_rate": 2.9465147632370795e-07, | |
| "logits/chosen": -18.3398380279541, | |
| "logits/rejected": -18.301984786987305, | |
| "logps/chosen": -485.8975524902344, | |
| "logps/rejected": -474.5433654785156, | |
| "loss": 0.6946, | |
| "rewards/accuracies": 0.4765625, | |
| "rewards/chosen": -0.00577941257506609, | |
| "rewards/margins": 0.0024705647956579924, | |
| "rewards/rejected": -0.008249977603554726, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.4958863126402393, | |
| "eval_logits/chosen": -18.481569290161133, | |
| "eval_logits/rejected": -18.363122940063477, | |
| "eval_logps/chosen": -494.26336669921875, | |
| "eval_logps/rejected": -478.822265625, | |
| "eval_loss": 0.6959648728370667, | |
| "eval_rewards/accuracies": 0.47907325625419617, | |
| "eval_rewards/chosen": -0.0046310219913721085, | |
| "eval_rewards/margins": -0.0005819797515869141, | |
| "eval_rewards/rejected": -0.0040490408428013325, | |
| "eval_runtime": 842.3853, | |
| "eval_samples_per_second": 6.349, | |
| "eval_steps_per_second": 0.794, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.5258040388930443, | |
| "grad_norm": 15.875, | |
| "learning_rate": 2.86049275918997e-07, | |
| "logits/chosen": -18.267154693603516, | |
| "logits/rejected": -18.09113883972168, | |
| "logps/chosen": -506.2464904785156, | |
| "logps/rejected": -472.58721923828125, | |
| "loss": 0.6937, | |
| "rewards/accuracies": 0.5062500238418579, | |
| "rewards/chosen": 0.00022939778864383698, | |
| "rewards/margins": 0.003868215484544635, | |
| "rewards/rejected": -0.003638815600425005, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.555721765145849, | |
| "grad_norm": 11.9375, | |
| "learning_rate": 2.774032524533323e-07, | |
| "logits/chosen": -18.302738189697266, | |
| "logits/rejected": -18.214998245239258, | |
| "logps/chosen": -485.1527404785156, | |
| "logps/rejected": -474.42120361328125, | |
| "loss": 0.6912, | |
| "rewards/accuracies": 0.4937500059604645, | |
| "rewards/chosen": -0.0037696107756346464, | |
| "rewards/margins": 0.008755478076636791, | |
| "rewards/rejected": -0.01252509094774723, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.5856394913986538, | |
| "grad_norm": 13.25, | |
| "learning_rate": 2.6872391640726276e-07, | |
| "logits/chosen": -18.349544525146484, | |
| "logits/rejected": -18.272260665893555, | |
| "logps/chosen": -496.89117431640625, | |
| "logps/rejected": -471.0453186035156, | |
| "loss": 0.696, | |
| "rewards/accuracies": 0.46406251192092896, | |
| "rewards/chosen": -0.016991907730698586, | |
| "rewards/margins": -0.0011090601328760386, | |
| "rewards/rejected": -0.01588284783065319, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.6155572176514585, | |
| "grad_norm": 14.5625, | |
| "learning_rate": 2.6002181875755233e-07, | |
| "logits/chosen": -18.489253997802734, | |
| "logits/rejected": -18.443098068237305, | |
| "logps/chosen": -492.5693359375, | |
| "logps/rejected": -482.33306884765625, | |
| "loss": 0.6967, | |
| "rewards/accuracies": 0.48750001192092896, | |
| "rewards/chosen": -0.0029235139954835176, | |
| "rewards/margins": -0.0017206415068358183, | |
| "rewards/rejected": -0.0012028723722323775, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.6454749439042633, | |
| "grad_norm": 12.6875, | |
| "learning_rate": 2.5130753815095647e-07, | |
| "logits/chosen": -18.483600616455078, | |
| "logits/rejected": -18.2879581451416, | |
| "logps/chosen": -510.51348876953125, | |
| "logps/rejected": -490.70196533203125, | |
| "loss": 0.6949, | |
| "rewards/accuracies": 0.4921875, | |
| "rewards/chosen": -0.0024643188808113337, | |
| "rewards/margins": 0.001509314402937889, | |
| "rewards/rejected": -0.003973634447902441, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.675392670157068, | |
| "grad_norm": 12.0, | |
| "learning_rate": 2.4259166804436003e-07, | |
| "logits/chosen": -18.499126434326172, | |
| "logits/rejected": -18.366363525390625, | |
| "logps/chosen": -499.53240966796875, | |
| "logps/rejected": -479.3192443847656, | |
| "loss": 0.6907, | |
| "rewards/accuracies": 0.5171874761581421, | |
| "rewards/chosen": -0.0017261719331145287, | |
| "rewards/margins": 0.009601183235645294, | |
| "rewards/rejected": -0.011327354237437248, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.7053103964098728, | |
| "grad_norm": 13.5, | |
| "learning_rate": 2.338848038269135e-07, | |
| "logits/chosen": -18.419811248779297, | |
| "logits/rejected": -18.180389404296875, | |
| "logps/chosen": -502.84686279296875, | |
| "logps/rejected": -476.781494140625, | |
| "loss": 0.692, | |
| "rewards/accuracies": 0.49531251192092896, | |
| "rewards/chosen": 0.001199430669657886, | |
| "rewards/margins": 0.007095737848430872, | |
| "rewards/rejected": -0.005896307062357664, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.7352281226626776, | |
| "grad_norm": 14.125, | |
| "learning_rate": 2.2519752993981804e-07, | |
| "logits/chosen": -18.500263214111328, | |
| "logits/rejected": -18.394670486450195, | |
| "logps/chosen": -514.1810913085938, | |
| "logps/rejected": -490.6826171875, | |
| "loss": 0.7018, | |
| "rewards/accuracies": 0.42656248807907104, | |
| "rewards/chosen": -0.007822760380804539, | |
| "rewards/margins": -0.011961746029555798, | |
| "rewards/rejected": 0.004138986114412546, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.7651458489154823, | |
| "grad_norm": 14.0, | |
| "learning_rate": 2.1654040700942112e-07, | |
| "logits/chosen": -18.530935287475586, | |
| "logits/rejected": -18.39280891418457, | |
| "logps/chosen": -511.75115966796875, | |
| "logps/rejected": -486.78564453125, | |
| "loss": 0.6949, | |
| "rewards/accuracies": 0.48750001192092896, | |
| "rewards/chosen": 0.006620324216783047, | |
| "rewards/margins": 0.0015118361916393042, | |
| "rewards/rejected": 0.005108488257974386, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.795063575168287, | |
| "grad_norm": 13.75, | |
| "learning_rate": 2.0792395900926155e-07, | |
| "logits/chosen": -18.366960525512695, | |
| "logits/rejected": -18.27281379699707, | |
| "logps/chosen": -495.75445556640625, | |
| "logps/rejected": -479.6105041503906, | |
| "loss": 0.6952, | |
| "rewards/accuracies": 0.4703125059604645, | |
| "rewards/chosen": -0.01034991629421711, | |
| "rewards/margins": 0.0005709372344426811, | |
| "rewards/rejected": -0.010920852422714233, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.795063575168287, | |
| "eval_logits/chosen": -18.48212432861328, | |
| "eval_logits/rejected": -18.363605499267578, | |
| "eval_logps/chosen": -494.263916015625, | |
| "eval_logps/rejected": -478.8390808105469, | |
| "eval_loss": 0.695127010345459, | |
| "eval_rewards/accuracies": 0.4882287085056305, | |
| "eval_rewards/chosen": -0.0046835425309836864, | |
| "eval_rewards/margins": 0.0010564102558419108, | |
| "eval_rewards/rejected": -0.005739952437579632, | |
| "eval_runtime": 842.133, | |
| "eval_samples_per_second": 6.351, | |
| "eval_steps_per_second": 0.794, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.824981301421092, | |
| "grad_norm": 13.3125, | |
| "learning_rate": 1.9935866046667134e-07, | |
| "logits/chosen": -18.486186981201172, | |
| "logits/rejected": -18.327022552490234, | |
| "logps/chosen": -518.8204956054688, | |
| "logps/rejected": -491.86737060546875, | |
| "loss": 0.6928, | |
| "rewards/accuracies": 0.5078125, | |
| "rewards/chosen": -0.0042625004425644875, | |
| "rewards/margins": 0.00539636705070734, | |
| "rewards/rejected": -0.009658867493271828, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.8548990276738968, | |
| "grad_norm": 13.0625, | |
| "learning_rate": 1.9085492372948678e-07, | |
| "logits/chosen": -18.573169708251953, | |
| "logits/rejected": -18.4843692779541, | |
| "logps/chosen": -523.7990112304688, | |
| "logps/rejected": -502.0945739746094, | |
| "loss": 0.6918, | |
| "rewards/accuracies": 0.504687488079071, | |
| "rewards/chosen": -0.007377514149993658, | |
| "rewards/margins": 0.00755069125443697, | |
| "rewards/rejected": -0.01492820493876934, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.8848167539267016, | |
| "grad_norm": 13.4375, | |
| "learning_rate": 1.824230863083477e-07, | |
| "logits/chosen": -18.435693740844727, | |
| "logits/rejected": -18.278911590576172, | |
| "logps/chosen": -500.37103271484375, | |
| "logps/rejected": -478.5856018066406, | |
| "loss": 0.6983, | |
| "rewards/accuracies": 0.46406251192092896, | |
| "rewards/chosen": -0.014031234197318554, | |
| "rewards/margins": -0.005335616413503885, | |
| "rewards/rejected": -0.008695616386830807, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.9147344801795063, | |
| "grad_norm": 11.75, | |
| "learning_rate": 1.7407339830997154e-07, | |
| "logits/chosen": -18.601871490478516, | |
| "logits/rejected": -18.49062156677246, | |
| "logps/chosen": -509.70428466796875, | |
| "logps/rejected": -490.6293029785156, | |
| "loss": 0.6979, | |
| "rewards/accuracies": 0.4515624940395355, | |
| "rewards/chosen": -0.005590735003352165, | |
| "rewards/margins": -0.00480449665337801, | |
| "rewards/rejected": -0.0007862389320507646, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.9446522064323113, | |
| "grad_norm": 14.0, | |
| "learning_rate": 1.658160099766799e-07, | |
| "logits/chosen": -18.551902770996094, | |
| "logits/rejected": -18.38374900817871, | |
| "logps/chosen": -494.0267639160156, | |
| "logps/rejected": -469.78143310546875, | |
| "loss": 0.6993, | |
| "rewards/accuracies": 0.4515624940395355, | |
| "rewards/chosen": -0.014440399594604969, | |
| "rewards/margins": -0.007908724248409271, | |
| "rewards/rejected": -0.006531675346195698, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.974569932685116, | |
| "grad_norm": 13.4375, | |
| "learning_rate": 1.576609593473246e-07, | |
| "logits/chosen": -18.249267578125, | |
| "logits/rejected": -18.19643783569336, | |
| "logps/chosen": -497.38641357421875, | |
| "logps/rejected": -477.0294494628906, | |
| "loss": 0.695, | |
| "rewards/accuracies": 0.44999998807907104, | |
| "rewards/chosen": -0.010250954888761044, | |
| "rewards/margins": 0.0014018019428476691, | |
| "rewards/rejected": -0.011652758345007896, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.004487658937921, | |
| "grad_norm": 13.125, | |
| "learning_rate": 1.4961816005461222e-07, | |
| "logits/chosen": -18.5499324798584, | |
| "logits/rejected": -18.45195198059082, | |
| "logps/chosen": -503.68096923828125, | |
| "logps/rejected": -480.076904296875, | |
| "loss": 0.695, | |
| "rewards/accuracies": 0.49531251192092896, | |
| "rewards/chosen": -0.003980870358645916, | |
| "rewards/margins": 0.0012054868275299668, | |
| "rewards/rejected": -0.005186358001083136, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.0344053851907256, | |
| "grad_norm": 11.9375, | |
| "learning_rate": 1.416973892736638e-07, | |
| "logits/chosen": -18.451631546020508, | |
| "logits/rejected": -18.396869659423828, | |
| "logps/chosen": -498.55267333984375, | |
| "logps/rejected": -484.3282165527344, | |
| "loss": 0.6977, | |
| "rewards/accuracies": 0.4625000059604645, | |
| "rewards/chosen": -0.014167798683047295, | |
| "rewards/margins": -0.00439287768676877, | |
| "rewards/rejected": -0.009774921461939812, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.0643231114435303, | |
| "grad_norm": 12.875, | |
| "learning_rate": 1.339082758364569e-07, | |
| "logits/chosen": -18.43014907836914, | |
| "logits/rejected": -18.314260482788086, | |
| "logps/chosen": -495.68145751953125, | |
| "logps/rejected": -485.66632080078125, | |
| "loss": 0.6979, | |
| "rewards/accuracies": 0.4625000059604645, | |
| "rewards/chosen": -0.017589876428246498, | |
| "rewards/margins": -0.0047332653775811195, | |
| "rewards/rejected": -0.012856610119342804, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.094240837696335, | |
| "grad_norm": 12.75, | |
| "learning_rate": 1.2626028852660026e-07, | |
| "logits/chosen": -18.41107749938965, | |
| "logits/rejected": -18.227169036865234, | |
| "logps/chosen": -505.9676818847656, | |
| "logps/rejected": -484.62548828125, | |
| "loss": 0.6947, | |
| "rewards/accuracies": 0.4765625, | |
| "rewards/chosen": -0.014858139678835869, | |
| "rewards/margins": 0.0021128151565790176, | |
| "rewards/rejected": -0.016970956698060036, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.094240837696335, | |
| "eval_logits/chosen": -18.482025146484375, | |
| "eval_logits/rejected": -18.363367080688477, | |
| "eval_logps/chosen": -494.2701416015625, | |
| "eval_logps/rejected": -478.8379211425781, | |
| "eval_loss": 0.6954838633537292, | |
| "eval_rewards/accuracies": 0.4822496175765991, | |
| "eval_rewards/chosen": -0.005303152371197939, | |
| "eval_rewards/margins": 0.0003158066247124225, | |
| "eval_rewards/rejected": -0.005618959199637175, | |
| "eval_runtime": 841.92, | |
| "eval_samples_per_second": 6.352, | |
| "eval_steps_per_second": 0.795, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.12415856394914, | |
| "grad_norm": 13.375, | |
| "learning_rate": 1.1876272456867081e-07, | |
| "logits/chosen": -18.531566619873047, | |
| "logits/rejected": -18.326671600341797, | |
| "logps/chosen": -510.41888427734375, | |
| "logps/rejected": -488.3369140625, | |
| "loss": 0.6989, | |
| "rewards/accuracies": 0.48750001192092896, | |
| "rewards/chosen": -0.008112497627735138, | |
| "rewards/margins": -0.006051483564078808, | |
| "rewards/rejected": -0.002061013597995043, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.1540762902019446, | |
| "grad_norm": 13.0, | |
| "learning_rate": 1.114246983261046e-07, | |
| "logits/chosen": -18.460107803344727, | |
| "logits/rejected": -18.281509399414062, | |
| "logps/chosen": -493.8604431152344, | |
| "logps/rejected": -470.369140625, | |
| "loss": 0.697, | |
| "rewards/accuracies": 0.46406251192092896, | |
| "rewards/chosen": -0.0026031527668237686, | |
| "rewards/margins": -0.0029606991447508335, | |
| "rewards/rejected": 0.0003575454466044903, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.1839940164547493, | |
| "grad_norm": 14.625, | |
| "learning_rate": 1.0425513022138202e-07, | |
| "logits/chosen": -18.540891647338867, | |
| "logits/rejected": -18.398468017578125, | |
| "logps/chosen": -490.9407653808594, | |
| "logps/rejected": -473.2347717285156, | |
| "loss": 0.693, | |
| "rewards/accuracies": 0.4859375059604645, | |
| "rewards/chosen": -0.0007933437591418624, | |
| "rewards/margins": 0.005172435659915209, | |
| "rewards/rejected": -0.005965779535472393, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.213911742707554, | |
| "grad_norm": 13.4375, | |
| "learning_rate": 9.726273589197565e-08, | |
| "logits/chosen": -18.563766479492188, | |
| "logits/rejected": -18.471820831298828, | |
| "logps/chosen": -508.5835876464844, | |
| "logps/rejected": -494.5013122558594, | |
| "loss": 0.6915, | |
| "rewards/accuracies": 0.5, | |
| "rewards/chosen": -0.00014840513176750392, | |
| "rewards/margins": 0.008764137513935566, | |
| "rewards/rejected": -0.008912542834877968, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.243829468960359, | |
| "grad_norm": 16.25, | |
| "learning_rate": 9.045601559524434e-08, | |
| "logits/chosen": -18.197242736816406, | |
| "logits/rejected": -18.150014877319336, | |
| "logps/chosen": -496.7591247558594, | |
| "logps/rejected": -475.01141357421875, | |
| "loss": 0.6983, | |
| "rewards/accuracies": 0.4609375, | |
| "rewards/chosen": -0.005830574780702591, | |
| "rewards/margins": -0.005549018736928701, | |
| "rewards/rejected": -0.0002815568877849728, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.273747195213164, | |
| "grad_norm": 12.8125, | |
| "learning_rate": 8.384324387515202e-08, | |
| "logits/chosen": -18.513484954833984, | |
| "logits/rejected": -18.47811508178711, | |
| "logps/chosen": -509.2792053222656, | |
| "logps/rejected": -504.4214782714844, | |
| "loss": 0.6973, | |
| "rewards/accuracies": 0.4703125059604645, | |
| "rewards/chosen": -0.0049002873711287975, | |
| "rewards/margins": -0.0031452118419110775, | |
| "rewards/rejected": -0.001755074947141111, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.303664921465969, | |
| "grad_norm": 13.6875, | |
| "learning_rate": 7.743245950337365e-08, | |
| "logits/chosen": -18.391809463500977, | |
| "logits/rejected": -18.290664672851562, | |
| "logps/chosen": -499.37353515625, | |
| "logps/rejected": -488.48388671875, | |
| "loss": 0.6934, | |
| "rewards/accuracies": 0.503125011920929, | |
| "rewards/chosen": -0.013569754548370838, | |
| "rewards/margins": 0.004729210399091244, | |
| "rewards/rejected": -0.018298964947462082, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.3335826477187736, | |
| "grad_norm": 11.9375, | |
| "learning_rate": 7.123145570701638e-08, | |
| "logits/chosen": -18.322669982910156, | |
| "logits/rejected": -18.09329605102539, | |
| "logps/chosen": -498.12548828125, | |
| "logps/rejected": -465.91497802734375, | |
| "loss": 0.6925, | |
| "rewards/accuracies": 0.4703125059604645, | |
| "rewards/chosen": -0.011946515180170536, | |
| "rewards/margins": 0.006278673652559519, | |
| "rewards/rejected": -0.018225187435746193, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.3635003739715783, | |
| "grad_norm": 12.0, | |
| "learning_rate": 6.524777069483525e-08, | |
| "logits/chosen": -18.426311492919922, | |
| "logits/rejected": -18.294950485229492, | |
| "logps/chosen": -502.55810546875, | |
| "logps/rejected": -476.4676818847656, | |
| "loss": 0.7011, | |
| "rewards/accuracies": 0.44062501192092896, | |
| "rewards/chosen": -0.02296162210404873, | |
| "rewards/margins": -0.01101845782250166, | |
| "rewards/rejected": -0.01194316241890192, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.393418100224383, | |
| "grad_norm": 14.75, | |
| "learning_rate": 5.948867849345979e-08, | |
| "logits/chosen": -18.55495834350586, | |
| "logits/rejected": -18.406208038330078, | |
| "logps/chosen": -493.659423828125, | |
| "logps/rejected": -478.211181640625, | |
| "loss": 0.6995, | |
| "rewards/accuracies": 0.45625001192092896, | |
| "rewards/chosen": -0.009105198085308075, | |
| "rewards/margins": -0.007736638188362122, | |
| "rewards/rejected": -0.001368560828268528, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.393418100224383, | |
| "eval_logits/chosen": -18.481842041015625, | |
| "eval_logits/rejected": -18.36322021484375, | |
| "eval_logps/chosen": -494.27740478515625, | |
| "eval_logps/rejected": -478.857421875, | |
| "eval_loss": 0.6948285102844238, | |
| "eval_rewards/accuracies": 0.49177876114845276, | |
| "eval_rewards/chosen": -0.006035235244780779, | |
| "eval_rewards/margins": 0.0015357759548351169, | |
| "eval_rewards/rejected": -0.007571011781692505, | |
| "eval_runtime": 842.3774, | |
| "eval_samples_per_second": 6.349, | |
| "eval_steps_per_second": 0.794, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.423335826477188, | |
| "grad_norm": 15.5, | |
| "learning_rate": 5.396118010477274e-08, | |
| "logits/chosen": -18.395492553710938, | |
| "logits/rejected": -18.27509117126465, | |
| "logps/chosen": -502.3111877441406, | |
| "logps/rejected": -475.66973876953125, | |
| "loss": 0.6989, | |
| "rewards/accuracies": 0.4453125, | |
| "rewards/chosen": -0.01698307693004608, | |
| "rewards/margins": -0.006895692553371191, | |
| "rewards/rejected": -0.010087382979691029, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.4532535527299926, | |
| "grad_norm": 15.0625, | |
| "learning_rate": 4.867199499518873e-08, | |
| "logits/chosen": -18.451091766357422, | |
| "logits/rejected": -18.34830093383789, | |
| "logps/chosen": -500.35595703125, | |
| "logps/rejected": -482.3310546875, | |
| "loss": 0.6971, | |
| "rewards/accuracies": 0.44999998807907104, | |
| "rewards/chosen": -0.006859651766717434, | |
| "rewards/margins": -0.0022591417655348778, | |
| "rewards/rejected": -0.004600510932505131, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.4831712789827973, | |
| "grad_norm": 13.875, | |
| "learning_rate": 4.362755292717993e-08, | |
| "logits/chosen": -18.62723731994629, | |
| "logits/rejected": -18.555469512939453, | |
| "logps/chosen": -508.4722595214844, | |
| "logps/rejected": -480.99932861328125, | |
| "loss": 0.6959, | |
| "rewards/accuracies": 0.4515624940395355, | |
| "rewards/chosen": 7.3916649853345e-05, | |
| "rewards/margins": -0.0006395616801455617, | |
| "rewards/rejected": 0.0007134780171327293, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.513089005235602, | |
| "grad_norm": 15.1875, | |
| "learning_rate": 3.883398614297831e-08, | |
| "logits/chosen": -18.562936782836914, | |
| "logits/rejected": -18.407032012939453, | |
| "logps/chosen": -518.3756103515625, | |
| "logps/rejected": -503.34063720703125, | |
| "loss": 0.6958, | |
| "rewards/accuracies": 0.4671874940395355, | |
| "rewards/chosen": -0.007723680697381496, | |
| "rewards/margins": -2.291230521223042e-05, | |
| "rewards/rejected": -0.007700768765062094, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.543006731488407, | |
| "grad_norm": 13.375, | |
| "learning_rate": 3.4297121909956485e-08, | |
| "logits/chosen": -18.537033081054688, | |
| "logits/rejected": -18.43063735961914, | |
| "logps/chosen": -490.99017333984375, | |
| "logps/rejected": -469.899658203125, | |
| "loss": 0.6941, | |
| "rewards/accuracies": 0.45625001192092896, | |
| "rewards/chosen": -0.006467898841947317, | |
| "rewards/margins": 0.003015016671270132, | |
| "rewards/rejected": -0.00948291551321745, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.5729244577412116, | |
| "grad_norm": 14.0, | |
| "learning_rate": 3.002247543674921e-08, | |
| "logits/chosen": -18.188644409179688, | |
| "logits/rejected": -18.097511291503906, | |
| "logps/chosen": -497.510986328125, | |
| "logps/rejected": -473.9842224121094, | |
| "loss": 0.6961, | |
| "rewards/accuracies": 0.46875, | |
| "rewards/chosen": -0.011478578671813011, | |
| "rewards/margins": -0.0014710351824760437, | |
| "rewards/rejected": -0.010007544420659542, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.6028421839940163, | |
| "grad_norm": 14.4375, | |
| "learning_rate": 2.6015243168726607e-08, | |
| "logits/chosen": -18.49826431274414, | |
| "logits/rejected": -18.359790802001953, | |
| "logps/chosen": -513.165771484375, | |
| "logps/rejected": -497.18487548828125, | |
| "loss": 0.6947, | |
| "rewards/accuracies": 0.4906249940395355, | |
| "rewards/chosen": -0.007126118056476116, | |
| "rewards/margins": 0.002322929911315441, | |
| "rewards/rejected": -0.009449047967791557, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.632759910246821, | |
| "grad_norm": 12.4375, | |
| "learning_rate": 2.228029647097057e-08, | |
| "logits/chosen": -18.447689056396484, | |
| "logits/rejected": -18.275293350219727, | |
| "logps/chosen": -497.46392822265625, | |
| "logps/rejected": -472.00531005859375, | |
| "loss": 0.6973, | |
| "rewards/accuracies": 0.4765625, | |
| "rewards/chosen": -0.00794267375022173, | |
| "rewards/margins": -0.0032855805475264788, | |
| "rewards/rejected": -0.004657094366848469, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.662677636499626, | |
| "grad_norm": 12.6875, | |
| "learning_rate": 1.882217570643216e-08, | |
| "logits/chosen": -18.6273193359375, | |
| "logits/rejected": -18.57034683227539, | |
| "logps/chosen": -493.40191650390625, | |
| "logps/rejected": -481.95062255859375, | |
| "loss": 0.6963, | |
| "rewards/accuracies": 0.49687498807907104, | |
| "rewards/chosen": -0.010606282390654087, | |
| "rewards/margins": -0.0014992398209869862, | |
| "rewards/rejected": -0.009107043035328388, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.6925953627524306, | |
| "grad_norm": 13.5625, | |
| "learning_rate": 1.5645084716469776e-08, | |
| "logits/chosen": -18.280813217163086, | |
| "logits/rejected": -18.22847557067871, | |
| "logps/chosen": -503.5279846191406, | |
| "logps/rejected": -490.97320556640625, | |
| "loss": 0.6932, | |
| "rewards/accuracies": 0.49687498807907104, | |
| "rewards/chosen": -0.007966242730617523, | |
| "rewards/margins": 0.004499543458223343, | |
| "rewards/rejected": -0.012465784326195717, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.6925953627524306, | |
| "eval_logits/chosen": -18.48170280456543, | |
| "eval_logits/rejected": -18.363323211669922, | |
| "eval_logps/chosen": -494.2970275878906, | |
| "eval_logps/rejected": -478.86920166015625, | |
| "eval_loss": 0.6951792240142822, | |
| "eval_rewards/accuracies": 0.48374438285827637, | |
| "eval_rewards/chosen": -0.007996306754648685, | |
| "eval_rewards/margins": 0.0007518637576140463, | |
| "eval_rewards/rejected": -0.008748171851038933, | |
| "eval_runtime": 842.6667, | |
| "eval_samples_per_second": 6.347, | |
| "eval_steps_per_second": 0.794, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.7225130890052354, | |
| "grad_norm": 13.375, | |
| "learning_rate": 1.2752885710477584e-08, | |
| "logits/chosen": -18.436344146728516, | |
| "logits/rejected": -18.28668975830078, | |
| "logps/chosen": -502.52911376953125, | |
| "logps/rejected": -478.9175720214844, | |
| "loss": 0.6917, | |
| "rewards/accuracies": 0.47968751192092896, | |
| "rewards/chosen": -0.0051972828805446625, | |
| "rewards/margins": 0.007670181337743998, | |
| "rewards/rejected": -0.012867462821304798, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.75243081525804, | |
| "grad_norm": 14.5625, | |
| "learning_rate": 1.014909457081664e-08, | |
| "logits/chosen": -18.285552978515625, | |
| "logits/rejected": -18.188400268554688, | |
| "logps/chosen": -495.7474670410156, | |
| "logps/rejected": -482.32086181640625, | |
| "loss": 0.7018, | |
| "rewards/accuracies": 0.4281249940395355, | |
| "rewards/chosen": -0.014425873756408691, | |
| "rewards/margins": -0.012442706152796745, | |
| "rewards/rejected": -0.0019831680692732334, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.7823485415108453, | |
| "grad_norm": 13.625, | |
| "learning_rate": 7.836876578755758e-09, | |
| "logits/chosen": -18.36880874633789, | |
| "logits/rejected": -18.273122787475586, | |
| "logps/chosen": -505.2574157714844, | |
| "logps/rejected": -478.4847717285156, | |
| "loss": 0.6956, | |
| "rewards/accuracies": 0.4859375059604645, | |
| "rewards/chosen": -0.005088160280138254, | |
| "rewards/margins": 0.00010951366130029783, | |
| "rewards/rejected": -0.005197672639042139, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.81226626776365, | |
| "grad_norm": 13.125, | |
| "learning_rate": 5.819042566618831e-09, | |
| "logits/chosen": -18.473098754882812, | |
| "logits/rejected": -18.300846099853516, | |
| "logps/chosen": -503.1376953125, | |
| "logps/rejected": -475.238037109375, | |
| "loss": 0.6943, | |
| "rewards/accuracies": 0.4749999940395355, | |
| "rewards/chosen": 0.0007304133614525199, | |
| "rewards/margins": 0.002083559287711978, | |
| "rewards/rejected": -0.00135314604267478, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.842183994016455, | |
| "grad_norm": 12.625, | |
| "learning_rate": 4.098045500815106e-09, | |
| "logits/chosen": -18.308658599853516, | |
| "logits/rejected": -18.19416046142578, | |
| "logps/chosen": -495.00604248046875, | |
| "logps/rejected": -475.799072265625, | |
| "loss": 0.696, | |
| "rewards/accuracies": 0.44843751192092896, | |
| "rewards/chosen": -0.004273262806236744, | |
| "rewards/margins": -0.0009155833977274597, | |
| "rewards/rejected": -0.0033576800487935543, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.8721017202692596, | |
| "grad_norm": 14.5625, | |
| "learning_rate": 2.6759774999071673e-09, | |
| "logits/chosen": -18.59539794921875, | |
| "logits/rejected": -18.472515106201172, | |
| "logps/chosen": -514.5612182617188, | |
| "logps/rejected": -492.31890869140625, | |
| "loss": 0.6964, | |
| "rewards/accuracies": 0.4515624940395355, | |
| "rewards/chosen": -0.0067207301035523415, | |
| "rewards/margins": -0.0017061748076230288, | |
| "rewards/rejected": -0.005014555994421244, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.9020194465220643, | |
| "grad_norm": 11.625, | |
| "learning_rate": 1.5545672913407914e-09, | |
| "logits/chosen": -18.352832794189453, | |
| "logits/rejected": -18.20647621154785, | |
| "logps/chosen": -501.56317138671875, | |
| "logps/rejected": -487.9432678222656, | |
| "loss": 0.6959, | |
| "rewards/accuracies": 0.5, | |
| "rewards/chosen": -0.013429331593215466, | |
| "rewards/margins": -0.0001061473521986045, | |
| "rewards/rejected": -0.013323183171451092, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.931937172774869, | |
| "grad_norm": 19.5, | |
| "learning_rate": 7.351781099292353e-10, | |
| "logits/chosen": -18.442501068115234, | |
| "logits/rejected": -18.37118148803711, | |
| "logps/chosen": -501.3379821777344, | |
| "logps/rejected": -496.15924072265625, | |
| "loss": 0.7002, | |
| "rewards/accuracies": 0.45625001192092896, | |
| "rewards/chosen": -0.01971256360411644, | |
| "rewards/margins": -0.00949421338737011, | |
| "rewards/rejected": -0.01021835207939148, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.961854899027674, | |
| "grad_norm": 11.5, | |
| "learning_rate": 2.1880604064578035e-10, | |
| "logits/chosen": -18.448497772216797, | |
| "logits/rejected": -18.216806411743164, | |
| "logps/chosen": -508.0194396972656, | |
| "logps/rejected": -466.27301025390625, | |
| "loss": 0.6949, | |
| "rewards/accuracies": 0.484375, | |
| "rewards/chosen": -0.0018872346263378859, | |
| "rewards/margins": 0.0016591917956247926, | |
| "rewards/rejected": -0.003546426072716713, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.9917726252804786, | |
| "grad_norm": 19.5, | |
| "learning_rate": 6.07880773983993e-12, | |
| "logits/chosen": -18.198387145996094, | |
| "logits/rejected": -18.139768600463867, | |
| "logps/chosen": -483.9991149902344, | |
| "logps/rejected": -473.9156188964844, | |
| "loss": 0.6964, | |
| "rewards/accuracies": 0.45781248807907104, | |
| "rewards/chosen": -0.009544356726109982, | |
| "rewards/margins": -0.0014166312757879496, | |
| "rewards/rejected": -0.00812772661447525, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.9917726252804786, | |
| "eval_logits/chosen": -18.481870651245117, | |
| "eval_logits/rejected": -18.36333465576172, | |
| "eval_logps/chosen": -494.2957763671875, | |
| "eval_logps/rejected": -478.8612060546875, | |
| "eval_loss": 0.6955399513244629, | |
| "eval_rewards/accuracies": 0.48131540417671204, | |
| "eval_rewards/chosen": -0.007866346277296543, | |
| "eval_rewards/margins": 8.37442566989921e-05, | |
| "eval_rewards/rejected": -0.007950090803205967, | |
| "eval_runtime": 843.4786, | |
| "eval_samples_per_second": 6.34, | |
| "eval_steps_per_second": 0.793, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.99775617053104, | |
| "step": 1002, | |
| "total_flos": 0.0, | |
| "train_loss": 0.6953648589328377, | |
| "train_runtime": 32693.7742, | |
| "train_samples_per_second": 1.963, | |
| "train_steps_per_second": 0.031 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1002, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |