| { |
| "best_global_step": 300, |
| "best_metric": 0.68528539, |
| "best_model_checkpoint": "/data2/kdd/crag/cjz/output/task1_dpo_absgt10_noidk__pari0.5_0602_p2prompt_r16/v0-20250604-235901/checkpoint-300", |
| "epoch": 0.8802263439170073, |
| "eval_steps": 300, |
| "global_step": 350, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.002514932411191449, |
| "grad_norm": 5.559185028076172, |
| "learning_rate": 3.3333333333333333e-06, |
| "logits/chosen": -0.5158984065055847, |
| "logits/rejected": -0.6433685421943665, |
| "logps/chosen": -8.879493713378906, |
| "logps/rejected": -18.298219680786133, |
| "loss": 1.2430726289749146, |
| "memory(GiB)": 30.69, |
| "nll_loss": 0.5499253869056702, |
| "rewards/accuracies": 0.0, |
| "rewards/chosen": 0.0, |
| "rewards/margins": 0.0, |
| "rewards/rejected": 0.0, |
| "step": 1, |
| "train_speed(iter/s)": 0.010477 |
| }, |
| { |
| "epoch": 0.005029864822382898, |
| "grad_norm": 5.400235176086426, |
| "learning_rate": 6.666666666666667e-06, |
| "logits/chosen": -0.5219721794128418, |
| "logits/rejected": -0.6263731718063354, |
| "logps/chosen": -4.77984094619751, |
| "logps/rejected": -15.150838851928711, |
| "loss": 1.0675525665283203, |
| "memory(GiB)": 33.9, |
| "nll_loss": 0.3744054436683655, |
| "rewards/accuracies": 0.0, |
| "rewards/chosen": 0.0, |
| "rewards/margins": 0.0, |
| "rewards/rejected": 0.0, |
| "step": 2, |
| "train_speed(iter/s)": 0.010866 |
| }, |
| { |
| "epoch": 0.007544797233574348, |
| "grad_norm": 7.852550983428955, |
| "learning_rate": 1e-05, |
| "logits/chosen": -0.48881009221076965, |
| "logits/rejected": -0.6540625691413879, |
| "logps/chosen": -4.714770793914795, |
| "logps/rejected": -17.99374008178711, |
| "loss": 1.0851404666900635, |
| "memory(GiB)": 33.9, |
| "nll_loss": 0.3894187808036804, |
| "rewards/accuracies": 0.375, |
| "rewards/chosen": -0.002094469266012311, |
| "rewards/margins": -0.004971538204699755, |
| "rewards/rejected": 0.0028770684730261564, |
| "step": 3, |
| "train_speed(iter/s)": 0.011002 |
| }, |
| { |
| "epoch": 0.010059729644765796, |
| "grad_norm": 10.150762557983398, |
| "learning_rate": 1.3333333333333333e-05, |
| "logits/chosen": -0.4506370425224304, |
| "logits/rejected": -0.6422093510627747, |
| "logps/chosen": -3.6849846839904785, |
| "logps/rejected": -21.201997756958008, |
| "loss": 1.092491865158081, |
| "memory(GiB)": 37.36, |
| "nll_loss": 0.4020901322364807, |
| "rewards/accuracies": 0.5, |
| "rewards/chosen": 0.007022961974143982, |
| "rewards/margins": 0.0057290042750537395, |
| "rewards/rejected": 0.001293957349844277, |
| "step": 4, |
| "train_speed(iter/s)": 0.011051 |
| }, |
| { |
| "epoch": 0.012574662055957246, |
| "grad_norm": 6.588510036468506, |
| "learning_rate": 1.6666666666666667e-05, |
| "logits/chosen": -0.4159216284751892, |
| "logits/rejected": -0.5884239673614502, |
| "logps/chosen": -8.611150741577148, |
| "logps/rejected": -19.931533813476562, |
| "loss": 1.1986628770828247, |
| "memory(GiB)": 37.36, |
| "nll_loss": 0.5155895948410034, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.005048489198088646, |
| "rewards/margins": 0.020845137536525726, |
| "rewards/rejected": -0.01579664833843708, |
| "step": 5, |
| "train_speed(iter/s)": 0.011086 |
| }, |
| { |
| "epoch": 0.015089594467148696, |
| "grad_norm": 3.965754508972168, |
| "learning_rate": 2e-05, |
| "logits/chosen": -0.47118157148361206, |
| "logits/rejected": -0.5790206789970398, |
| "logps/chosen": -9.572708129882812, |
| "logps/rejected": -19.066829681396484, |
| "loss": 1.1965497732162476, |
| "memory(GiB)": 37.36, |
| "nll_loss": 0.5279884338378906, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.006116065196692944, |
| "rewards/margins": 0.05174415558576584, |
| "rewards/rejected": -0.04562808945775032, |
| "step": 6, |
| "train_speed(iter/s)": 0.01111 |
| }, |
| { |
| "epoch": 0.017604526878340146, |
| "grad_norm": 2.719625234603882, |
| "learning_rate": 2.3333333333333336e-05, |
| "logits/chosen": -0.40740644931793213, |
| "logits/rejected": -0.5419386029243469, |
| "logps/chosen": -9.413152694702148, |
| "logps/rejected": -24.703401565551758, |
| "loss": 1.1549676656723022, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.5149396061897278, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": -0.02250390499830246, |
| "rewards/margins": 0.12123934924602509, |
| "rewards/rejected": -0.14374326169490814, |
| "step": 7, |
| "train_speed(iter/s)": 0.011114 |
| }, |
| { |
| "epoch": 0.020119459289531592, |
| "grad_norm": 3.325852394104004, |
| "learning_rate": 2.6666666666666667e-05, |
| "logits/chosen": -0.4091758728027344, |
| "logits/rejected": -0.5692812204360962, |
| "logps/chosen": -5.904629230499268, |
| "logps/rejected": -20.752662658691406, |
| "loss": 1.0213468074798584, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.3945533037185669, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": -0.041384391486644745, |
| "rewards/margins": 0.17802417278289795, |
| "rewards/rejected": -0.2194085717201233, |
| "step": 8, |
| "train_speed(iter/s)": 0.011127 |
| }, |
| { |
| "epoch": 0.022634391700723042, |
| "grad_norm": 3.5531411170959473, |
| "learning_rate": 3e-05, |
| "logits/chosen": -0.3281947374343872, |
| "logits/rejected": -0.5156837701797485, |
| "logps/chosen": -5.975313186645508, |
| "logps/rejected": -27.066158294677734, |
| "loss": 0.8695712089538574, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.3611774742603302, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.0457351878285408, |
| "rewards/margins": 0.4895857870578766, |
| "rewards/rejected": -0.443850576877594, |
| "step": 9, |
| "train_speed(iter/s)": 0.011136 |
| }, |
| { |
| "epoch": 0.025149324111914492, |
| "grad_norm": 4.356088161468506, |
| "learning_rate": 3.3333333333333335e-05, |
| "logits/chosen": -0.43971675634384155, |
| "logits/rejected": -0.5702978372573853, |
| "logps/chosen": -6.376318454742432, |
| "logps/rejected": -19.42030143737793, |
| "loss": 1.0046417713165283, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.42133060097694397, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": -0.17984721064567566, |
| "rewards/margins": 0.43266722559928894, |
| "rewards/rejected": -0.6125144362449646, |
| "step": 10, |
| "train_speed(iter/s)": 0.01115 |
| }, |
| { |
| "epoch": 0.027664256523105942, |
| "grad_norm": 3.9732213020324707, |
| "learning_rate": 3.6666666666666666e-05, |
| "logits/chosen": -0.4561832845211029, |
| "logits/rejected": -0.6065505146980286, |
| "logps/chosen": -6.498957633972168, |
| "logps/rejected": -27.428552627563477, |
| "loss": 0.9565106630325317, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.40273764729499817, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": -0.12391924858093262, |
| "rewards/margins": 0.5706068277359009, |
| "rewards/rejected": -0.6945260763168335, |
| "step": 11, |
| "train_speed(iter/s)": 0.011161 |
| }, |
| { |
| "epoch": 0.030179188934297392, |
| "grad_norm": 2.2540578842163086, |
| "learning_rate": 4e-05, |
| "logits/chosen": -0.42088037729263306, |
| "logits/rejected": -0.6009025573730469, |
| "logps/chosen": -4.243446350097656, |
| "logps/rejected": -26.567686080932617, |
| "loss": 0.7599425911903381, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.28007903695106506, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": -0.14110325276851654, |
| "rewards/margins": 0.6590132713317871, |
| "rewards/rejected": -0.8001165390014648, |
| "step": 12, |
| "train_speed(iter/s)": 0.011171 |
| }, |
| { |
| "epoch": 0.03269412134548884, |
| "grad_norm": 6.460833549499512, |
| "learning_rate": 4.3333333333333334e-05, |
| "logits/chosen": -0.4136754274368286, |
| "logits/rejected": -0.5452494621276855, |
| "logps/chosen": -7.585506439208984, |
| "logps/rejected": -21.19340705871582, |
| "loss": 1.223608136177063, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.6720148921012878, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": -0.25483113527297974, |
| "rewards/margins": 0.49035438895225525, |
| "rewards/rejected": -0.7451854944229126, |
| "step": 13, |
| "train_speed(iter/s)": 0.011181 |
| }, |
| { |
| "epoch": 0.03520905375668029, |
| "grad_norm": 4.092947006225586, |
| "learning_rate": 4.666666666666667e-05, |
| "logits/chosen": -0.527854323387146, |
| "logits/rejected": -0.5994939804077148, |
| "logps/chosen": -8.185604095458984, |
| "logps/rejected": -17.946279525756836, |
| "loss": 1.2557107210159302, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.66472989320755, |
| "rewards/accuracies": 0.65625, |
| "rewards/chosen": -0.145107239484787, |
| "rewards/margins": 0.41058170795440674, |
| "rewards/rejected": -0.5556889772415161, |
| "step": 14, |
| "train_speed(iter/s)": 0.011194 |
| }, |
| { |
| "epoch": 0.03772398616787174, |
| "grad_norm": 3.926342248916626, |
| "learning_rate": 5e-05, |
| "logits/chosen": -0.407508909702301, |
| "logits/rejected": -0.5949459075927734, |
| "logps/chosen": -3.4148104190826416, |
| "logps/rejected": -22.69104766845703, |
| "loss": 0.8548452258110046, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.40506720542907715, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": -0.025914989411830902, |
| "rewards/margins": 0.6952927708625793, |
| "rewards/rejected": -0.7212077379226685, |
| "step": 15, |
| "train_speed(iter/s)": 0.0112 |
| }, |
| { |
| "epoch": 0.040238918579063185, |
| "grad_norm": 2.4273853302001953, |
| "learning_rate": 5.333333333333333e-05, |
| "logits/chosen": -0.3462049961090088, |
| "logits/rejected": -0.58342045545578, |
| "logps/chosen": -3.8651039600372314, |
| "logps/rejected": -28.470134735107422, |
| "loss": 0.821665346622467, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.3309793472290039, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.04178892821073532, |
| "rewards/margins": 0.5164157152175903, |
| "rewards/rejected": -0.4746267795562744, |
| "step": 16, |
| "train_speed(iter/s)": 0.011202 |
| }, |
| { |
| "epoch": 0.04275385099025464, |
| "grad_norm": 1.8921568393707275, |
| "learning_rate": 5.666666666666667e-05, |
| "logits/chosen": -0.5054872632026672, |
| "logits/rejected": -0.6153637170791626, |
| "logps/chosen": -1.8910857439041138, |
| "logps/rejected": -16.781475067138672, |
| "loss": 0.7665270566940308, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.2412014603614807, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.04062865674495697, |
| "rewards/margins": 0.41468262672424316, |
| "rewards/rejected": -0.3740540146827698, |
| "step": 17, |
| "train_speed(iter/s)": 0.011212 |
| }, |
| { |
| "epoch": 0.045268783401446085, |
| "grad_norm": 3.2724339962005615, |
| "learning_rate": 6e-05, |
| "logits/chosen": -0.45994284749031067, |
| "logits/rejected": -0.5327339768409729, |
| "logps/chosen": -8.705971717834473, |
| "logps/rejected": -17.33376121520996, |
| "loss": 1.2050995826721191, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.5643416047096252, |
| "rewards/accuracies": 0.625, |
| "rewards/chosen": -0.048418305814266205, |
| "rewards/margins": 0.16582812368869781, |
| "rewards/rejected": -0.21424642205238342, |
| "step": 18, |
| "train_speed(iter/s)": 0.011215 |
| }, |
| { |
| "epoch": 0.04778371581263754, |
| "grad_norm": 2.6650567054748535, |
| "learning_rate": 6.333333333333333e-05, |
| "logits/chosen": -0.48406994342803955, |
| "logits/rejected": -0.5535129308700562, |
| "logps/chosen": -10.087296485900879, |
| "logps/rejected": -17.584102630615234, |
| "loss": 1.1602699756622314, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.5509804487228394, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": -0.005405411124229431, |
| "rewards/margins": 0.23162491619586945, |
| "rewards/rejected": -0.23703034222126007, |
| "step": 19, |
| "train_speed(iter/s)": 0.01122 |
| }, |
| { |
| "epoch": 0.050298648223828984, |
| "grad_norm": 2.393120527267456, |
| "learning_rate": 6.666666666666667e-05, |
| "logits/chosen": -0.4699333906173706, |
| "logits/rejected": -0.5745525360107422, |
| "logps/chosen": -5.482749938964844, |
| "logps/rejected": -15.294036865234375, |
| "loss": 1.0463979244232178, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.40886539220809937, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.030414806678891182, |
| "rewards/margins": 0.18470264971256256, |
| "rewards/rejected": -0.15428784489631653, |
| "step": 20, |
| "train_speed(iter/s)": 0.011224 |
| }, |
| { |
| "epoch": 0.05281358063502043, |
| "grad_norm": 1.7328065633773804, |
| "learning_rate": 7e-05, |
| "logits/chosen": -0.5130109190940857, |
| "logits/rejected": -0.6171243190765381, |
| "logps/chosen": -8.619268417358398, |
| "logps/rejected": -18.43971824645996, |
| "loss": 1.1801689863204956, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.6120539903640747, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.07324957102537155, |
| "rewards/margins": 0.3033149242401123, |
| "rewards/rejected": -0.23006536066532135, |
| "step": 21, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.055328513046211884, |
| "grad_norm": 2.848578691482544, |
| "learning_rate": 7.333333333333333e-05, |
| "logits/chosen": -0.46683233976364136, |
| "logits/rejected": -0.5329924821853638, |
| "logps/chosen": -4.357663154602051, |
| "logps/rejected": -15.35399055480957, |
| "loss": 0.9406945705413818, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.3216635584831238, |
| "rewards/accuracies": 0.65625, |
| "rewards/chosen": -0.010179778560996056, |
| "rewards/margins": 0.2008945494890213, |
| "rewards/rejected": -0.21107429265975952, |
| "step": 22, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.05784344545740333, |
| "grad_norm": 1.7426271438598633, |
| "learning_rate": 7.666666666666667e-05, |
| "logits/chosen": -0.5002316236495972, |
| "logits/rejected": -0.5488481521606445, |
| "logps/chosen": -5.690494537353516, |
| "logps/rejected": -15.590461730957031, |
| "loss": 0.9775924682617188, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.355554461479187, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": 0.009325886145234108, |
| "rewards/margins": 0.18430516123771667, |
| "rewards/rejected": -0.1749793142080307, |
| "step": 23, |
| "train_speed(iter/s)": 0.011234 |
| }, |
| { |
| "epoch": 0.060358377868594784, |
| "grad_norm": 1.8518409729003906, |
| "learning_rate": 8e-05, |
| "logits/chosen": -0.5258264541625977, |
| "logits/rejected": -0.5805689096450806, |
| "logps/chosen": -9.133979797363281, |
| "logps/rejected": -17.886051177978516, |
| "loss": 1.1810051202774048, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.6029603481292725, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.04269062727689743, |
| "rewards/margins": 0.2787190079689026, |
| "rewards/rejected": -0.23602835834026337, |
| "step": 24, |
| "train_speed(iter/s)": 0.011237 |
| }, |
| { |
| "epoch": 0.06287331027978624, |
| "grad_norm": 2.4842066764831543, |
| "learning_rate": 8.333333333333334e-05, |
| "logits/chosen": -0.44220152497291565, |
| "logits/rejected": -0.5788168907165527, |
| "logps/chosen": -4.989194869995117, |
| "logps/rejected": -18.047056198120117, |
| "loss": 1.0011777877807617, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.4066605269908905, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.021916719153523445, |
| "rewards/margins": 0.2587287425994873, |
| "rewards/rejected": -0.236812025308609, |
| "step": 25, |
| "train_speed(iter/s)": 0.011239 |
| }, |
| { |
| "epoch": 0.06538824269097768, |
| "grad_norm": 1.766322135925293, |
| "learning_rate": 8.666666666666667e-05, |
| "logits/chosen": -0.3389984369277954, |
| "logits/rejected": -0.543292224407196, |
| "logps/chosen": -11.735610961914062, |
| "logps/rejected": -26.25033950805664, |
| "loss": 1.0063844919204712, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.5172990560531616, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.07315510511398315, |
| "rewards/margins": 0.5734083652496338, |
| "rewards/rejected": -0.5002533197402954, |
| "step": 26, |
| "train_speed(iter/s)": 0.011238 |
| }, |
| { |
| "epoch": 0.06790317510216913, |
| "grad_norm": 3.3314130306243896, |
| "learning_rate": 9e-05, |
| "logits/chosen": -0.37741950154304504, |
| "logits/rejected": -0.5884826183319092, |
| "logps/chosen": -5.442512035369873, |
| "logps/rejected": -27.738323211669922, |
| "loss": 0.8821365237236023, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.4055330753326416, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": -0.03083166666328907, |
| "rewards/margins": 0.6056570410728455, |
| "rewards/rejected": -0.6364887952804565, |
| "step": 27, |
| "train_speed(iter/s)": 0.011238 |
| }, |
| { |
| "epoch": 0.07041810751336058, |
| "grad_norm": 2.849647283554077, |
| "learning_rate": 9.333333333333334e-05, |
| "logits/chosen": -0.4310716688632965, |
| "logits/rejected": -0.5529810190200806, |
| "logps/chosen": -8.224971771240234, |
| "logps/rejected": -26.79846954345703, |
| "loss": 0.8747767806053162, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.45313140749931335, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": -0.07478700578212738, |
| "rewards/margins": 0.8052245378494263, |
| "rewards/rejected": -0.8800115585327148, |
| "step": 28, |
| "train_speed(iter/s)": 0.011238 |
| }, |
| { |
| "epoch": 0.07293303992455202, |
| "grad_norm": 2.247368097305298, |
| "learning_rate": 9.666666666666667e-05, |
| "logits/chosen": -0.37296879291534424, |
| "logits/rejected": -0.5259015560150146, |
| "logps/chosen": -6.546780109405518, |
| "logps/rejected": -25.603477478027344, |
| "loss": 0.9804578423500061, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.4873877465724945, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": -0.046319298446178436, |
| "rewards/margins": 0.5485984086990356, |
| "rewards/rejected": -0.5949177145957947, |
| "step": 29, |
| "train_speed(iter/s)": 0.011239 |
| }, |
| { |
| "epoch": 0.07544797233574348, |
| "grad_norm": 1.7451585531234741, |
| "learning_rate": 0.0001, |
| "logits/chosen": -0.36992424726486206, |
| "logits/rejected": -0.45540890097618103, |
| "logps/chosen": -6.483048439025879, |
| "logps/rejected": -18.744525909423828, |
| "loss": 0.9453181624412537, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.37866073846817017, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": 0.0520947091281414, |
| "rewards/margins": 0.33587026596069336, |
| "rewards/rejected": -0.28377556800842285, |
| "step": 30, |
| "train_speed(iter/s)": 0.01124 |
| }, |
| { |
| "epoch": 0.07796290474693493, |
| "grad_norm": 2.8843863010406494, |
| "learning_rate": 0.00010333333333333334, |
| "logits/chosen": -0.3973531723022461, |
| "logits/rejected": -0.4880366325378418, |
| "logps/chosen": -6.5046491622924805, |
| "logps/rejected": -18.793209075927734, |
| "loss": 1.0352380275726318, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.514582097530365, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.06333249807357788, |
| "rewards/margins": 0.5268359780311584, |
| "rewards/rejected": -0.4635034203529358, |
| "step": 31, |
| "train_speed(iter/s)": 0.011242 |
| }, |
| { |
| "epoch": 0.08047783715812637, |
| "grad_norm": 1.9934616088867188, |
| "learning_rate": 0.00010666666666666667, |
| "logits/chosen": -0.38435813784599304, |
| "logits/rejected": -0.4866703450679779, |
| "logps/chosen": -5.984093189239502, |
| "logps/rejected": -28.37721061706543, |
| "loss": 0.9228850603103638, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.3919341564178467, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": 0.08762034773826599, |
| "rewards/margins": 0.4990919232368469, |
| "rewards/rejected": -0.41147157549858093, |
| "step": 32, |
| "train_speed(iter/s)": 0.011242 |
| }, |
| { |
| "epoch": 0.08299276956931782, |
| "grad_norm": 2.605156421661377, |
| "learning_rate": 0.00011000000000000002, |
| "logits/chosen": -0.3683161437511444, |
| "logits/rejected": -0.4800977110862732, |
| "logps/chosen": -6.79887056350708, |
| "logps/rejected": -18.521530151367188, |
| "loss": 0.9287618398666382, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.4155515730381012, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.062238909304142, |
| "rewards/margins": 0.4814634323120117, |
| "rewards/rejected": -0.41922450065612793, |
| "step": 33, |
| "train_speed(iter/s)": 0.011243 |
| }, |
| { |
| "epoch": 0.08550770198050928, |
| "grad_norm": 2.1593198776245117, |
| "learning_rate": 0.00011333333333333334, |
| "logits/chosen": -0.3462904989719391, |
| "logits/rejected": -0.4482634663581848, |
| "logps/chosen": -4.484028339385986, |
| "logps/rejected": -22.155223846435547, |
| "loss": 0.8287199139595032, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.3564324378967285, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": -0.011370105668902397, |
| "rewards/margins": 0.8015316724777222, |
| "rewards/rejected": -0.8129018545150757, |
| "step": 34, |
| "train_speed(iter/s)": 0.011244 |
| }, |
| { |
| "epoch": 0.08802263439170073, |
| "grad_norm": 2.1223862171173096, |
| "learning_rate": 0.00011666666666666668, |
| "logits/chosen": -0.23746490478515625, |
| "logits/rejected": -0.4123544991016388, |
| "logps/chosen": -4.062009334564209, |
| "logps/rejected": -30.214771270751953, |
| "loss": 0.8381334543228149, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.45768678188323975, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.06588438153266907, |
| "rewards/margins": 1.1650195121765137, |
| "rewards/rejected": -1.0991352796554565, |
| "step": 35, |
| "train_speed(iter/s)": 0.011244 |
| }, |
| { |
| "epoch": 0.09053756680289217, |
| "grad_norm": 1.7519793510437012, |
| "learning_rate": 0.00012, |
| "logits/chosen": -0.274143248796463, |
| "logits/rejected": -0.4072067439556122, |
| "logps/chosen": -7.12678861618042, |
| "logps/rejected": -29.586929321289062, |
| "loss": 0.7818687558174133, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.38336753845214844, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.030900314450263977, |
| "rewards/margins": 1.0601840019226074, |
| "rewards/rejected": -1.0292836427688599, |
| "step": 36, |
| "train_speed(iter/s)": 0.011244 |
| }, |
| { |
| "epoch": 0.09305249921408362, |
| "grad_norm": 2.2621781826019287, |
| "learning_rate": 0.00012333333333333334, |
| "logits/chosen": -0.30612003803253174, |
| "logits/rejected": -0.44930776953697205, |
| "logps/chosen": -5.637537956237793, |
| "logps/rejected": -30.86564064025879, |
| "loss": 0.7518173456192017, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.4073091149330139, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": -0.1094760149717331, |
| "rewards/margins": 1.2509604692459106, |
| "rewards/rejected": -1.3604364395141602, |
| "step": 37, |
| "train_speed(iter/s)": 0.011245 |
| }, |
| { |
| "epoch": 0.09556743162527508, |
| "grad_norm": 2.6005046367645264, |
| "learning_rate": 0.00012666666666666666, |
| "logits/chosen": -0.36841830611228943, |
| "logits/rejected": -0.44501256942749023, |
| "logps/chosen": -8.786764144897461, |
| "logps/rejected": -21.693777084350586, |
| "loss": 0.967311441898346, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.5350124835968018, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": -0.05166015028953552, |
| "rewards/margins": 0.9184513092041016, |
| "rewards/rejected": -0.9701113700866699, |
| "step": 38, |
| "train_speed(iter/s)": 0.011247 |
| }, |
| { |
| "epoch": 0.09808236403646652, |
| "grad_norm": 7.679723262786865, |
| "learning_rate": 0.00013000000000000002, |
| "logits/chosen": -0.3933795094490051, |
| "logits/rejected": -0.4303474426269531, |
| "logps/chosen": -9.630545616149902, |
| "logps/rejected": -25.0108642578125, |
| "loss": 1.1940371990203857, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.6422770023345947, |
| "rewards/accuracies": 0.65625, |
| "rewards/chosen": -0.19723013043403625, |
| "rewards/margins": 0.8150386214256287, |
| "rewards/rejected": -1.0122687816619873, |
| "step": 39, |
| "train_speed(iter/s)": 0.011247 |
| }, |
| { |
| "epoch": 0.10059729644765797, |
| "grad_norm": 2.497746229171753, |
| "learning_rate": 0.00013333333333333334, |
| "logits/chosen": -0.3561173677444458, |
| "logits/rejected": -0.4964173436164856, |
| "logps/chosen": -6.288295269012451, |
| "logps/rejected": -28.722339630126953, |
| "loss": 0.7734813690185547, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.35979557037353516, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.020053118467330933, |
| "rewards/margins": 1.0713183879852295, |
| "rewards/rejected": -1.0512654781341553, |
| "step": 40, |
| "train_speed(iter/s)": 0.011248 |
| }, |
| { |
| "epoch": 0.10311222885884942, |
| "grad_norm": 3.900786876678467, |
| "learning_rate": 0.00013666666666666666, |
| "logits/chosen": -0.30438148975372314, |
| "logits/rejected": -0.4660162031650543, |
| "logps/chosen": -9.80126953125, |
| "logps/rejected": -22.89883804321289, |
| "loss": 1.0617499351501465, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.5348615646362305, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.037312038242816925, |
| "rewards/margins": 0.48836010694503784, |
| "rewards/rejected": -0.4510480761528015, |
| "step": 41, |
| "train_speed(iter/s)": 0.011248 |
| }, |
| { |
| "epoch": 0.10562716127004086, |
| "grad_norm": 4.212996006011963, |
| "learning_rate": 0.00014, |
| "logits/chosen": -0.37392380833625793, |
| "logits/rejected": -0.4811669588088989, |
| "logps/chosen": -8.54138469696045, |
| "logps/rejected": -24.88803482055664, |
| "loss": 0.9449828267097473, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.40984830260276794, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": -0.078499935567379, |
| "rewards/margins": 0.6149317026138306, |
| "rewards/rejected": -0.6934316754341125, |
| "step": 42, |
| "train_speed(iter/s)": 0.011249 |
| }, |
| { |
| "epoch": 0.10814209368123232, |
| "grad_norm": 2.7297940254211426, |
| "learning_rate": 0.00014333333333333334, |
| "logits/chosen": -0.22235050797462463, |
| "logits/rejected": -0.44656193256378174, |
| "logps/chosen": -3.8628368377685547, |
| "logps/rejected": -29.070890426635742, |
| "loss": 0.6864454746246338, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.3404179513454437, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.10101112723350525, |
| "rewards/margins": 1.1784940958023071, |
| "rewards/rejected": -1.0774829387664795, |
| "step": 43, |
| "train_speed(iter/s)": 0.011247 |
| }, |
| { |
| "epoch": 0.11065702609242377, |
| "grad_norm": 4.357929229736328, |
| "learning_rate": 0.00014666666666666666, |
| "logits/chosen": -0.3152369558811188, |
| "logits/rejected": -0.4675106406211853, |
| "logps/chosen": -8.47473430633545, |
| "logps/rejected": -35.49666976928711, |
| "loss": 0.8841890096664429, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.543793261051178, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": -0.2599925100803375, |
| "rewards/margins": 1.5472975969314575, |
| "rewards/rejected": -1.8072898387908936, |
| "step": 44, |
| "train_speed(iter/s)": 0.011248 |
| }, |
| { |
| "epoch": 0.11317195850361522, |
| "grad_norm": 4.053813934326172, |
| "learning_rate": 0.00015000000000000001, |
| "logits/chosen": -0.47932106256484985, |
| "logits/rejected": -0.5357992053031921, |
| "logps/chosen": -10.139131546020508, |
| "logps/rejected": -29.30261993408203, |
| "loss": 1.0090879201889038, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.6002873182296753, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": -0.2646394371986389, |
| "rewards/margins": 1.3857942819595337, |
| "rewards/rejected": -1.6504336595535278, |
| "step": 45, |
| "train_speed(iter/s)": 0.01125 |
| }, |
| { |
| "epoch": 0.11568689091480666, |
| "grad_norm": 3.4071342945098877, |
| "learning_rate": 0.00015333333333333334, |
| "logits/chosen": -0.35965389013290405, |
| "logits/rejected": -0.4886631965637207, |
| "logps/chosen": -6.492125988006592, |
| "logps/rejected": -33.90357971191406, |
| "loss": 0.9477238655090332, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.5519906878471375, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": -0.13393068313598633, |
| "rewards/margins": 1.3498430252075195, |
| "rewards/rejected": -1.4837737083435059, |
| "step": 46, |
| "train_speed(iter/s)": 0.011251 |
| }, |
| { |
| "epoch": 0.11820182332599811, |
| "grad_norm": 1.5676898956298828, |
| "learning_rate": 0.00015666666666666666, |
| "logits/chosen": -0.3339039087295532, |
| "logits/rejected": -0.5405474305152893, |
| "logps/chosen": -5.18754768371582, |
| "logps/rejected": -34.61940383911133, |
| "loss": 0.5877978205680847, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.26233971118927, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.04858784377574921, |
| "rewards/margins": 1.4838428497314453, |
| "rewards/rejected": -1.4352549314498901, |
| "step": 47, |
| "train_speed(iter/s)": 0.011252 |
| }, |
| { |
| "epoch": 0.12071675573718957, |
| "grad_norm": 1.7600055932998657, |
| "learning_rate": 0.00016, |
| "logits/chosen": -0.38554954528808594, |
| "logits/rejected": -0.5349220633506775, |
| "logps/chosen": -5.35024356842041, |
| "logps/rejected": -30.936561584472656, |
| "loss": 0.7445188760757446, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.3484676480293274, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": -0.04428477957844734, |
| "rewards/margins": 1.158116340637207, |
| "rewards/rejected": -1.2024011611938477, |
| "step": 48, |
| "train_speed(iter/s)": 0.011253 |
| }, |
| { |
| "epoch": 0.12323168814838101, |
| "grad_norm": 1.8286348581314087, |
| "learning_rate": 0.00016333333333333334, |
| "logits/chosen": -0.3060781955718994, |
| "logits/rejected": -0.5333737134933472, |
| "logps/chosen": -4.790343761444092, |
| "logps/rejected": -32.540409088134766, |
| "loss": 0.6686277985572815, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.3360018730163574, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.0967080146074295, |
| "rewards/margins": 1.285821795463562, |
| "rewards/rejected": -1.1891138553619385, |
| "step": 49, |
| "train_speed(iter/s)": 0.011254 |
| }, |
| { |
| "epoch": 0.12574662055957248, |
| "grad_norm": 1.8983184099197388, |
| "learning_rate": 0.0001666666666666667, |
| "logits/chosen": -0.22582519054412842, |
| "logits/rejected": -0.47035256028175354, |
| "logps/chosen": -6.48522424697876, |
| "logps/rejected": -32.73487091064453, |
| "loss": 0.8076327443122864, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.3926582336425781, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.01478707417845726, |
| "rewards/margins": 1.167083501815796, |
| "rewards/rejected": -1.1522964239120483, |
| "step": 50, |
| "train_speed(iter/s)": 0.011253 |
| }, |
| { |
| "epoch": 0.12826155297076391, |
| "grad_norm": 2.4192955493927, |
| "learning_rate": 0.00017, |
| "logits/chosen": -0.30057138204574585, |
| "logits/rejected": -0.4678650498390198, |
| "logps/chosen": -7.537961483001709, |
| "logps/rejected": -34.26948547363281, |
| "loss": 0.8188683390617371, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.4251425266265869, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": -0.051345158368349075, |
| "rewards/margins": 1.1266952753067017, |
| "rewards/rejected": -1.178040623664856, |
| "step": 51, |
| "train_speed(iter/s)": 0.01121 |
| }, |
| { |
| "epoch": 0.13077648538195535, |
| "grad_norm": 2.0905075073242188, |
| "learning_rate": 0.00017333333333333334, |
| "logits/chosen": -0.2889178395271301, |
| "logits/rejected": -0.49443909525871277, |
| "logps/chosen": -6.827200412750244, |
| "logps/rejected": -44.23398971557617, |
| "loss": 0.7206944227218628, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.39006102085113525, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": -0.06844954192638397, |
| "rewards/margins": 2.328122854232788, |
| "rewards/rejected": -2.3965721130371094, |
| "step": 52, |
| "train_speed(iter/s)": 0.01121 |
| }, |
| { |
| "epoch": 0.13329141779314682, |
| "grad_norm": 1.9464434385299683, |
| "learning_rate": 0.00017666666666666666, |
| "logits/chosen": -0.30524271726608276, |
| "logits/rejected": -0.5259577631950378, |
| "logps/chosen": -8.820595741271973, |
| "logps/rejected": -34.23869705200195, |
| "loss": 0.8924205899238586, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.5174475312232971, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": -0.007829657755792141, |
| "rewards/margins": 1.6594951152801514, |
| "rewards/rejected": -1.6673249006271362, |
| "step": 53, |
| "train_speed(iter/s)": 0.011211 |
| }, |
| { |
| "epoch": 0.13580635020433826, |
| "grad_norm": 2.15484356880188, |
| "learning_rate": 0.00018, |
| "logits/chosen": -0.36469364166259766, |
| "logits/rejected": -0.5003997087478638, |
| "logps/chosen": -9.828875541687012, |
| "logps/rejected": -35.949886322021484, |
| "loss": 0.8116447925567627, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.4780670404434204, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.04445749148726463, |
| "rewards/margins": 1.7651525735855103, |
| "rewards/rejected": -1.7206950187683105, |
| "step": 54, |
| "train_speed(iter/s)": 0.011212 |
| }, |
| { |
| "epoch": 0.1383212826155297, |
| "grad_norm": 5.288140773773193, |
| "learning_rate": 0.00018333333333333334, |
| "logits/chosen": -0.357359915971756, |
| "logits/rejected": -0.5485042333602905, |
| "logps/chosen": -4.562381744384766, |
| "logps/rejected": -40.544979095458984, |
| "loss": 0.8048219680786133, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.4945175051689148, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": -0.026466388255357742, |
| "rewards/margins": 2.5180537700653076, |
| "rewards/rejected": -2.544520378112793, |
| "step": 55, |
| "train_speed(iter/s)": 0.011214 |
| }, |
| { |
| "epoch": 0.14083621502672117, |
| "grad_norm": 4.063258647918701, |
| "learning_rate": 0.0001866666666666667, |
| "logits/chosen": -0.39062973856925964, |
| "logits/rejected": -0.5040320158004761, |
| "logps/chosen": -10.983360290527344, |
| "logps/rejected": -33.32127380371094, |
| "loss": 1.1587333679199219, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.7283708453178406, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": -0.13727927207946777, |
| "rewards/margins": 1.9422543048858643, |
| "rewards/rejected": -2.079533576965332, |
| "step": 56, |
| "train_speed(iter/s)": 0.011215 |
| }, |
| { |
| "epoch": 0.1433511474379126, |
| "grad_norm": 3.7057104110717773, |
| "learning_rate": 0.00019, |
| "logits/chosen": -0.34116944670677185, |
| "logits/rejected": -0.5513606667518616, |
| "logps/chosen": -5.59161376953125, |
| "logps/rejected": -47.29106903076172, |
| "loss": 0.8299980759620667, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.5494524836540222, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": -0.13214518129825592, |
| "rewards/margins": 2.937675952911377, |
| "rewards/rejected": -3.069821357727051, |
| "step": 57, |
| "train_speed(iter/s)": 0.011217 |
| }, |
| { |
| "epoch": 0.14586607984910405, |
| "grad_norm": 4.7582502365112305, |
| "learning_rate": 0.00019333333333333333, |
| "logits/chosen": -0.4154261350631714, |
| "logits/rejected": -0.5971646904945374, |
| "logps/chosen": -3.059924364089966, |
| "logps/rejected": -43.29597091674805, |
| "loss": 0.5003064274787903, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.25123852491378784, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.07654222846031189, |
| "rewards/margins": 2.7813808917999268, |
| "rewards/rejected": -2.704838752746582, |
| "step": 58, |
| "train_speed(iter/s)": 0.011219 |
| }, |
| { |
| "epoch": 0.14838101226029551, |
| "grad_norm": 2.1735236644744873, |
| "learning_rate": 0.00019666666666666666, |
| "logits/chosen": -0.4227810800075531, |
| "logits/rejected": -0.47660815715789795, |
| "logps/chosen": -8.593082427978516, |
| "logps/rejected": -26.549867630004883, |
| "loss": 1.0610322952270508, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.5426512360572815, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": -0.10025864094495773, |
| "rewards/margins": 1.2511481046676636, |
| "rewards/rejected": -1.3514068126678467, |
| "step": 59, |
| "train_speed(iter/s)": 0.011221 |
| }, |
| { |
| "epoch": 0.15089594467148695, |
| "grad_norm": 2.805598258972168, |
| "learning_rate": 0.0002, |
| "logits/chosen": -0.300743043422699, |
| "logits/rejected": -0.47928643226623535, |
| "logps/chosen": -6.593828201293945, |
| "logps/rejected": -33.23126983642578, |
| "loss": 0.7988956570625305, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.40749770402908325, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.0006714202463626862, |
| "rewards/margins": 1.6283259391784668, |
| "rewards/rejected": -1.6276545524597168, |
| "step": 60, |
| "train_speed(iter/s)": 0.011221 |
| }, |
| { |
| "epoch": 0.1534108770826784, |
| "grad_norm": 2.290149211883545, |
| "learning_rate": 0.0001999996142159566, |
| "logits/chosen": -0.3385659158229828, |
| "logits/rejected": -0.4102441966533661, |
| "logps/chosen": -8.33851146697998, |
| "logps/rejected": -29.508546829223633, |
| "loss": 0.7559148073196411, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.35449326038360596, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": -0.0228387713432312, |
| "rewards/margins": 1.5235671997070312, |
| "rewards/rejected": -1.5464060306549072, |
| "step": 61, |
| "train_speed(iter/s)": 0.011222 |
| }, |
| { |
| "epoch": 0.15592580949386986, |
| "grad_norm": 1.7177425622940063, |
| "learning_rate": 0.0001999984568668029, |
| "logits/chosen": -0.32937324047088623, |
| "logits/rejected": -0.4484848380088806, |
| "logps/chosen": -3.493271827697754, |
| "logps/rejected": -34.78036880493164, |
| "loss": 0.6279686093330383, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.2725304365158081, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.11392105370759964, |
| "rewards/margins": 1.8176403045654297, |
| "rewards/rejected": -1.703719139099121, |
| "step": 62, |
| "train_speed(iter/s)": 0.011223 |
| }, |
| { |
| "epoch": 0.1584407419050613, |
| "grad_norm": 1.8914873600006104, |
| "learning_rate": 0.00019999652796146876, |
| "logits/chosen": -0.29077184200286865, |
| "logits/rejected": -0.48235204815864563, |
| "logps/chosen": -7.319096565246582, |
| "logps/rejected": -39.54444885253906, |
| "loss": 0.7298395037651062, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.40350908041000366, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.0820951834321022, |
| "rewards/margins": 1.882514476776123, |
| "rewards/rejected": -1.8004192113876343, |
| "step": 63, |
| "train_speed(iter/s)": 0.011224 |
| }, |
| { |
| "epoch": 0.16095567431625274, |
| "grad_norm": 1.429303526878357, |
| "learning_rate": 0.0001999938275148369, |
| "logits/chosen": -0.3300917446613312, |
| "logits/rejected": -0.45771050453186035, |
| "logps/chosen": -3.8289737701416016, |
| "logps/rejected": -39.278968811035156, |
| "loss": 0.39868107438087463, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.18221822381019592, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": -0.07021164149045944, |
| "rewards/margins": 2.249926805496216, |
| "rewards/rejected": -2.320138454437256, |
| "step": 64, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.1634706067274442, |
| "grad_norm": 2.639005661010742, |
| "learning_rate": 0.00019999035554774314, |
| "logits/chosen": -0.36244961619377136, |
| "logits/rejected": -0.5052404403686523, |
| "logps/chosen": -5.230596542358398, |
| "logps/rejected": -39.43718338012695, |
| "loss": 0.7721049189567566, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.4854365885257721, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": -0.1088234931230545, |
| "rewards/margins": 2.1535189151763916, |
| "rewards/rejected": -2.2623424530029297, |
| "step": 65, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.16598553913863565, |
| "grad_norm": 2.576199769973755, |
| "learning_rate": 0.00019998611208697607, |
| "logits/chosen": -0.3720204830169678, |
| "logits/rejected": -0.507696270942688, |
| "logps/chosen": -4.436941146850586, |
| "logps/rejected": -34.991371154785156, |
| "loss": 0.7472538352012634, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.39483439922332764, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": -0.0759558230638504, |
| "rewards/margins": 1.7400535345077515, |
| "rewards/rejected": -1.816009521484375, |
| "step": 66, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.16850047154982709, |
| "grad_norm": 1.724285364151001, |
| "learning_rate": 0.00019998109716527686, |
| "logits/chosen": -0.25216248631477356, |
| "logits/rejected": -0.4494931101799011, |
| "logps/chosen": -3.201148748397827, |
| "logps/rejected": -39.95793533325195, |
| "loss": 0.4833192229270935, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.20408841967582703, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": 0.06092430651187897, |
| "rewards/margins": 2.2583165168762207, |
| "rewards/rejected": -2.197392225265503, |
| "step": 67, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.17101540396101855, |
| "grad_norm": 2.91644287109375, |
| "learning_rate": 0.00019997531082133904, |
| "logits/chosen": -0.30811840295791626, |
| "logits/rejected": -0.413838654756546, |
| "logps/chosen": -7.5586838722229, |
| "logps/rejected": -29.464954376220703, |
| "loss": 1.0136064291000366, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.5009399652481079, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": -0.0595913827419281, |
| "rewards/margins": 1.2450876235961914, |
| "rewards/rejected": -1.304679036140442, |
| "step": 68, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.17353033637221, |
| "grad_norm": 1.6453865766525269, |
| "learning_rate": 0.00019996875309980826, |
| "logits/chosen": -0.32626980543136597, |
| "logits/rejected": -0.47710081934928894, |
| "logps/chosen": -4.140695095062256, |
| "logps/rejected": -33.830894470214844, |
| "loss": 0.6451548933982849, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.3717566728591919, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.094700388610363, |
| "rewards/margins": 1.8348017930984497, |
| "rewards/rejected": -1.7401013374328613, |
| "step": 69, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.17604526878340146, |
| "grad_norm": 2.180673360824585, |
| "learning_rate": 0.0001999614240512817, |
| "logits/chosen": -0.2670721411705017, |
| "logits/rejected": -0.46321332454681396, |
| "logps/chosen": -7.102023601531982, |
| "logps/rejected": -27.861366271972656, |
| "loss": 0.7481832504272461, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.37576019763946533, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.16741110384464264, |
| "rewards/margins": 1.3596775531768799, |
| "rewards/rejected": -1.1922664642333984, |
| "step": 70, |
| "train_speed(iter/s)": 0.011231 |
| }, |
| { |
| "epoch": 0.1785602011945929, |
| "grad_norm": 2.049133539199829, |
| "learning_rate": 0.00019995332373230808, |
| "logits/chosen": -0.241715669631958, |
| "logits/rejected": -0.407115638256073, |
| "logps/chosen": -4.861550331115723, |
| "logps/rejected": -34.9086799621582, |
| "loss": 0.6162200570106506, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.25812438130378723, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": 0.037743180990219116, |
| "rewards/margins": 1.569511890411377, |
| "rewards/rejected": -1.5317686796188354, |
| "step": 71, |
| "train_speed(iter/s)": 0.011231 |
| }, |
| { |
| "epoch": 0.18107513360578434, |
| "grad_norm": 4.052990913391113, |
| "learning_rate": 0.00019994445220538677, |
| "logits/chosen": -0.2541053295135498, |
| "logits/rejected": -0.36276954412460327, |
| "logps/chosen": -7.95726203918457, |
| "logps/rejected": -36.47919845581055, |
| "loss": 0.9209573268890381, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.5536596179008484, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": -0.17974892258644104, |
| "rewards/margins": 1.929343581199646, |
| "rewards/rejected": -2.1090924739837646, |
| "step": 72, |
| "train_speed(iter/s)": 0.011231 |
| }, |
| { |
| "epoch": 0.1835900660169758, |
| "grad_norm": 3.210548162460327, |
| "learning_rate": 0.0001999348095389677, |
| "logits/chosen": -0.24167482554912567, |
| "logits/rejected": -0.45636847615242004, |
| "logps/chosen": -7.025866508483887, |
| "logps/rejected": -48.629905700683594, |
| "loss": 0.7358823418617249, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.4621264636516571, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": -0.05025668814778328, |
| "rewards/margins": 2.2894766330718994, |
| "rewards/rejected": -2.339733123779297, |
| "step": 73, |
| "train_speed(iter/s)": 0.011231 |
| }, |
| { |
| "epoch": 0.18610499842816725, |
| "grad_norm": 4.565255165100098, |
| "learning_rate": 0.0001999243958074506, |
| "logits/chosen": -0.21860051155090332, |
| "logits/rejected": -0.42088112235069275, |
| "logps/chosen": -13.931788444519043, |
| "logps/rejected": -42.80027770996094, |
| "loss": 1.2019851207733154, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.7477802038192749, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": -0.36434897780418396, |
| "rewards/margins": 1.4156924486160278, |
| "rewards/rejected": -1.7800413370132446, |
| "step": 74, |
| "train_speed(iter/s)": 0.011231 |
| }, |
| { |
| "epoch": 0.18861993083935868, |
| "grad_norm": 2.291332244873047, |
| "learning_rate": 0.00019991321109118448, |
| "logits/chosen": -0.39398425817489624, |
| "logits/rejected": -0.44725537300109863, |
| "logps/chosen": -6.393754482269287, |
| "logps/rejected": -27.47494888305664, |
| "loss": 0.7488479018211365, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.3586839437484741, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.012238548137247562, |
| "rewards/margins": 1.2588202953338623, |
| "rewards/rejected": -1.246581792831421, |
| "step": 75, |
| "train_speed(iter/s)": 0.011232 |
| }, |
| { |
| "epoch": 0.19113486325055015, |
| "grad_norm": 1.830254077911377, |
| "learning_rate": 0.00019990125547646704, |
| "logits/chosen": -0.31489449739456177, |
| "logits/rejected": -0.47091639041900635, |
| "logps/chosen": -2.980022668838501, |
| "logps/rejected": -29.753929138183594, |
| "loss": 0.6747189164161682, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.2754742503166199, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.03740588575601578, |
| "rewards/margins": 1.4201977252960205, |
| "rewards/rejected": -1.3827917575836182, |
| "step": 76, |
| "train_speed(iter/s)": 0.011233 |
| }, |
| { |
| "epoch": 0.1936497956617416, |
| "grad_norm": 1.903449296951294, |
| "learning_rate": 0.00019988852905554404, |
| "logits/chosen": -0.2765476703643799, |
| "logits/rejected": -0.4408729076385498, |
| "logps/chosen": -5.630273342132568, |
| "logps/rejected": -31.533220291137695, |
| "loss": 0.7030317783355713, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.3307255208492279, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.1330985128879547, |
| "rewards/margins": 1.2641156911849976, |
| "rewards/rejected": -1.1310172080993652, |
| "step": 77, |
| "train_speed(iter/s)": 0.011232 |
| }, |
| { |
| "epoch": 0.19616472807293303, |
| "grad_norm": 1.736433744430542, |
| "learning_rate": 0.0001998750319266084, |
| "logits/chosen": -0.3374086618423462, |
| "logits/rejected": -0.48207730054855347, |
| "logps/chosen": -5.3590593338012695, |
| "logps/rejected": -29.23048973083496, |
| "loss": 0.8495813608169556, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.37136876583099365, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.09036409854888916, |
| "rewards/margins": 1.2102724313735962, |
| "rewards/rejected": -1.119908332824707, |
| "step": 78, |
| "train_speed(iter/s)": 0.011232 |
| }, |
| { |
| "epoch": 0.1986796604841245, |
| "grad_norm": 2.0839672088623047, |
| "learning_rate": 0.00019986076419379974, |
| "logits/chosen": -0.26226145029067993, |
| "logits/rejected": -0.4474099576473236, |
| "logps/chosen": -7.3566060066223145, |
| "logps/rejected": -40.514286041259766, |
| "loss": 0.9187750220298767, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.60602867603302, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.09458937495946884, |
| "rewards/margins": 1.9139156341552734, |
| "rewards/rejected": -1.8193262815475464, |
| "step": 79, |
| "train_speed(iter/s)": 0.011232 |
| }, |
| { |
| "epoch": 0.20119459289531594, |
| "grad_norm": 2.656200885772705, |
| "learning_rate": 0.00019984572596720324, |
| "logits/chosen": -0.4218776226043701, |
| "logits/rejected": -0.548494279384613, |
| "logps/chosen": -5.5665717124938965, |
| "logps/rejected": -34.339046478271484, |
| "loss": 0.7904801964759827, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.4805757403373718, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": -0.07708686590194702, |
| "rewards/margins": 1.846845269203186, |
| "rewards/rejected": -1.9239320755004883, |
| "step": 80, |
| "train_speed(iter/s)": 0.011233 |
| }, |
| { |
| "epoch": 0.20370952530650738, |
| "grad_norm": 1.582141399383545, |
| "learning_rate": 0.00019982991736284915, |
| "logits/chosen": -0.384469211101532, |
| "logits/rejected": -0.48424291610717773, |
| "logps/chosen": -6.730848789215088, |
| "logps/rejected": -35.332828521728516, |
| "loss": 0.6736842393875122, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.38718143105506897, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.02753191813826561, |
| "rewards/margins": 2.01827073097229, |
| "rewards/rejected": -1.9907389879226685, |
| "step": 81, |
| "train_speed(iter/s)": 0.011234 |
| }, |
| { |
| "epoch": 0.20622445771769884, |
| "grad_norm": 10.319942474365234, |
| "learning_rate": 0.00019981333850271158, |
| "logits/chosen": -0.3957505226135254, |
| "logits/rejected": -0.5100387334823608, |
| "logps/chosen": -7.3371148109436035, |
| "logps/rejected": -40.714134216308594, |
| "loss": 0.7473828196525574, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.4370650351047516, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": -0.05588718503713608, |
| "rewards/margins": 2.654069423675537, |
| "rewards/rejected": -2.709956645965576, |
| "step": 82, |
| "train_speed(iter/s)": 0.011234 |
| }, |
| { |
| "epoch": 0.20873939012889028, |
| "grad_norm": 2.3877530097961426, |
| "learning_rate": 0.0001997959895147077, |
| "logits/chosen": -0.36577096581459045, |
| "logits/rejected": -0.5359358787536621, |
| "logps/chosen": -4.45527458190918, |
| "logps/rejected": -46.861942291259766, |
| "loss": 0.5462505221366882, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.30273228883743286, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.15123440325260162, |
| "rewards/margins": 2.9262986183166504, |
| "rewards/rejected": -2.77506422996521, |
| "step": 83, |
| "train_speed(iter/s)": 0.011235 |
| }, |
| { |
| "epoch": 0.21125432254008172, |
| "grad_norm": 2.1806390285491943, |
| "learning_rate": 0.0001997778705326968, |
| "logits/chosen": -0.3485352396965027, |
| "logits/rejected": -0.5878627300262451, |
| "logps/chosen": -2.89451265335083, |
| "logps/rejected": -44.27880859375, |
| "loss": 0.6081856489181519, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.3298896849155426, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.05770353972911835, |
| "rewards/margins": 2.5825228691101074, |
| "rewards/rejected": -2.5248193740844727, |
| "step": 84, |
| "train_speed(iter/s)": 0.011235 |
| }, |
| { |
| "epoch": 0.2137692549512732, |
| "grad_norm": 2.80009388923645, |
| "learning_rate": 0.00019975898169647915, |
| "logits/chosen": -0.39257609844207764, |
| "logits/rejected": -0.5535434484481812, |
| "logps/chosen": -7.839548587799072, |
| "logps/rejected": -42.132286071777344, |
| "loss": 0.7175056338310242, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.405160129070282, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.025028400123119354, |
| "rewards/margins": 2.475644111633301, |
| "rewards/rejected": -2.450615644454956, |
| "step": 85, |
| "train_speed(iter/s)": 0.011235 |
| }, |
| { |
| "epoch": 0.21628418736246463, |
| "grad_norm": 3.3921735286712646, |
| "learning_rate": 0.000199739323151795, |
| "logits/chosen": -0.35620519518852234, |
| "logits/rejected": -0.6006304025650024, |
| "logps/chosen": -5.945646286010742, |
| "logps/rejected": -45.728271484375, |
| "loss": 0.6699403524398804, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.33112284541130066, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": -0.012618173845112324, |
| "rewards/margins": 2.700666666030884, |
| "rewards/rejected": -2.713285207748413, |
| "step": 86, |
| "train_speed(iter/s)": 0.011236 |
| }, |
| { |
| "epoch": 0.21879911977365607, |
| "grad_norm": 3.2411773204803467, |
| "learning_rate": 0.00019971889505032334, |
| "logits/chosen": -0.42666560411453247, |
| "logits/rejected": -0.6167599558830261, |
| "logps/chosen": -5.318458080291748, |
| "logps/rejected": -49.244285583496094, |
| "loss": 0.6356828808784485, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.39307594299316406, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": -0.1333954930305481, |
| "rewards/margins": 3.1458327770233154, |
| "rewards/rejected": -3.2792282104492188, |
| "step": 87, |
| "train_speed(iter/s)": 0.011237 |
| }, |
| { |
| "epoch": 0.22131405218484754, |
| "grad_norm": 1.924742341041565, |
| "learning_rate": 0.00019969769754968098, |
| "logits/chosen": -0.3413890600204468, |
| "logits/rejected": -0.5464233160018921, |
| "logps/chosen": -5.729033946990967, |
| "logps/rejected": -41.974422454833984, |
| "loss": 0.5986770987510681, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.3535672724246979, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.14028939604759216, |
| "rewards/margins": 2.51139235496521, |
| "rewards/rejected": -2.371102809906006, |
| "step": 88, |
| "train_speed(iter/s)": 0.011236 |
| }, |
| { |
| "epoch": 0.22382898459603898, |
| "grad_norm": 2.161083459854126, |
| "learning_rate": 0.00019967573081342103, |
| "logits/chosen": -0.38623473048210144, |
| "logits/rejected": -0.5679455399513245, |
| "logps/chosen": -6.484611511230469, |
| "logps/rejected": -38.930511474609375, |
| "loss": 0.7250155806541443, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.4377710521221161, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": -0.024773895740509033, |
| "rewards/margins": 2.3375205993652344, |
| "rewards/rejected": -2.3622944355010986, |
| "step": 89, |
| "train_speed(iter/s)": 0.011236 |
| }, |
| { |
| "epoch": 0.22634391700723044, |
| "grad_norm": 6.164645195007324, |
| "learning_rate": 0.00019965299501103177, |
| "logits/chosen": -0.33336132764816284, |
| "logits/rejected": -0.5168649554252625, |
| "logps/chosen": -11.845653533935547, |
| "logps/rejected": -55.690311431884766, |
| "loss": 1.0204803943634033, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.7011927962303162, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": -0.22887784242630005, |
| "rewards/margins": 3.111534357070923, |
| "rewards/rejected": -3.3404123783111572, |
| "step": 90, |
| "train_speed(iter/s)": 0.011236 |
| }, |
| { |
| "epoch": 0.22885884941842188, |
| "grad_norm": 2.4981861114501953, |
| "learning_rate": 0.00019962949031793542, |
| "logits/chosen": -0.4224125146865845, |
| "logits/rejected": -0.5427595376968384, |
| "logps/chosen": -5.719327926635742, |
| "logps/rejected": -33.303741455078125, |
| "loss": 0.7469587326049805, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.4206176996231079, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": -0.008410206064581871, |
| "rewards/margins": 1.994816541671753, |
| "rewards/rejected": -2.0032269954681396, |
| "step": 91, |
| "train_speed(iter/s)": 0.011237 |
| }, |
| { |
| "epoch": 0.23137378182961332, |
| "grad_norm": 2.5139830112457275, |
| "learning_rate": 0.00019960521691548674, |
| "logits/chosen": -0.34622836112976074, |
| "logits/rejected": -0.5427547097206116, |
| "logps/chosen": -5.069763660430908, |
| "logps/rejected": -41.81755828857422, |
| "loss": 0.6454588770866394, |
| "memory(GiB)": 40.85, |
| "nll_loss": 0.35349082946777344, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": -0.046083107590675354, |
| "rewards/margins": 2.2620620727539062, |
| "rewards/rejected": -2.30814528465271, |
| "step": 92, |
| "train_speed(iter/s)": 0.011237 |
| }, |
| { |
| "epoch": 0.2338887142408048, |
| "grad_norm": 2.1890244483947754, |
| "learning_rate": 0.0001995801749909715, |
| "logits/chosen": -0.3081744611263275, |
| "logits/rejected": -0.47990015149116516, |
| "logps/chosen": -6.5690107345581055, |
| "logps/rejected": -34.549991607666016, |
| "loss": 0.6765730381011963, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.3245474696159363, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.060123831033706665, |
| "rewards/margins": 1.8496551513671875, |
| "rewards/rejected": -1.7895313501358032, |
| "step": 93, |
| "train_speed(iter/s)": 0.011236 |
| }, |
| { |
| "epoch": 0.23640364665199623, |
| "grad_norm": 1.8172200918197632, |
| "learning_rate": 0.00019955436473760525, |
| "logits/chosen": -0.24766620993614197, |
| "logits/rejected": -0.49844813346862793, |
| "logps/chosen": -5.177490711212158, |
| "logps/rejected": -48.42265701293945, |
| "loss": 0.7104548811912537, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.4418777823448181, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.10037174820899963, |
| "rewards/margins": 2.629190683364868, |
| "rewards/rejected": -2.5288188457489014, |
| "step": 94, |
| "train_speed(iter/s)": 0.011236 |
| }, |
| { |
| "epoch": 0.23891857906318767, |
| "grad_norm": 2.0303428173065186, |
| "learning_rate": 0.0001995277863545316, |
| "logits/chosen": -0.3552500307559967, |
| "logits/rejected": -0.5088093876838684, |
| "logps/chosen": -3.972975730895996, |
| "logps/rejected": -29.582290649414062, |
| "loss": 0.5607516169548035, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.27718478441238403, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.09949840605258942, |
| "rewards/margins": 1.6923424005508423, |
| "rewards/rejected": -1.592844009399414, |
| "step": 95, |
| "train_speed(iter/s)": 0.011237 |
| }, |
| { |
| "epoch": 0.24143351147437914, |
| "grad_norm": 2.3172338008880615, |
| "learning_rate": 0.00019950044004682092, |
| "logits/chosen": -0.30597299337387085, |
| "logits/rejected": -0.4608762860298157, |
| "logps/chosen": -10.467157363891602, |
| "logps/rejected": -44.41074752807617, |
| "loss": 0.9089665412902832, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.5540332794189453, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": -0.0023995572701096535, |
| "rewards/margins": 2.6161789894104004, |
| "rewards/rejected": -2.6185781955718994, |
| "step": 96, |
| "train_speed(iter/s)": 0.011238 |
| }, |
| { |
| "epoch": 0.24394844388557058, |
| "grad_norm": 1.6338391304016113, |
| "learning_rate": 0.0001994723260254686, |
| "logits/chosen": -0.20743098855018616, |
| "logits/rejected": -0.4207964837551117, |
| "logps/chosen": -4.458022117614746, |
| "logps/rejected": -48.164268493652344, |
| "loss": 0.5020785927772522, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.2824496626853943, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.15383610129356384, |
| "rewards/margins": 3.0794906616210938, |
| "rewards/rejected": -2.925654172897339, |
| "step": 97, |
| "train_speed(iter/s)": 0.011238 |
| }, |
| { |
| "epoch": 0.24646337629676202, |
| "grad_norm": 2.5537126064300537, |
| "learning_rate": 0.0001994434445073934, |
| "logits/chosen": -0.1935003101825714, |
| "logits/rejected": -0.4715961217880249, |
| "logps/chosen": -3.131989002227783, |
| "logps/rejected": -61.07079315185547, |
| "loss": 0.3960198163986206, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.21717773377895355, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.07503610849380493, |
| "rewards/margins": 4.007692337036133, |
| "rewards/rejected": -3.9326562881469727, |
| "step": 98, |
| "train_speed(iter/s)": 0.011238 |
| }, |
| { |
| "epoch": 0.24897830870795348, |
| "grad_norm": 7.057893753051758, |
| "learning_rate": 0.00019941379571543596, |
| "logits/chosen": -0.21255502104759216, |
| "logits/rejected": -0.4117867946624756, |
| "logps/chosen": -5.764989852905273, |
| "logps/rejected": -59.11027908325195, |
| "loss": 0.7163435816764832, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.4923526346683502, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": -0.1150842159986496, |
| "rewards/margins": 3.945159912109375, |
| "rewards/rejected": -4.060243606567383, |
| "step": 99, |
| "train_speed(iter/s)": 0.011238 |
| }, |
| { |
| "epoch": 0.25149324111914495, |
| "grad_norm": 6.774058818817139, |
| "learning_rate": 0.00019938337987835688, |
| "logits/chosen": -0.2647398114204407, |
| "logits/rejected": -0.34906458854675293, |
| "logps/chosen": -10.037410736083984, |
| "logps/rejected": -37.84819030761719, |
| "loss": 1.0176275968551636, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.5385105609893799, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": -0.28268206119537354, |
| "rewards/margins": 2.0650789737701416, |
| "rewards/rejected": -2.3477611541748047, |
| "step": 100, |
| "train_speed(iter/s)": 0.011238 |
| }, |
| { |
| "epoch": 0.2540081735303364, |
| "grad_norm": 1.4746135473251343, |
| "learning_rate": 0.00019935219723083502, |
| "logits/chosen": -0.28873857855796814, |
| "logits/rejected": -0.4278784990310669, |
| "logps/chosen": -4.487892150878906, |
| "logps/rejected": -43.24613952636719, |
| "loss": 0.5632098317146301, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.31394267082214355, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.09316689521074295, |
| "rewards/margins": 3.0039639472961426, |
| "rewards/rejected": -2.910796880722046, |
| "step": 101, |
| "train_speed(iter/s)": 0.011219 |
| }, |
| { |
| "epoch": 0.25652310594152783, |
| "grad_norm": 2.2414140701293945, |
| "learning_rate": 0.0001993202480134658, |
| "logits/chosen": -0.286653995513916, |
| "logits/rejected": -0.4876902103424072, |
| "logps/chosen": -2.5823984146118164, |
| "logps/rejected": -50.10431671142578, |
| "loss": 0.3667687475681305, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.19701245427131653, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.11824626475572586, |
| "rewards/margins": 3.1774046421051025, |
| "rewards/rejected": -3.0591585636138916, |
| "step": 102, |
| "train_speed(iter/s)": 0.011219 |
| }, |
| { |
| "epoch": 0.25903803835271927, |
| "grad_norm": 2.5298242568969727, |
| "learning_rate": 0.0001992875324727591, |
| "logits/chosen": -0.2699410319328308, |
| "logits/rejected": -0.421194463968277, |
| "logps/chosen": -7.033985137939453, |
| "logps/rejected": -51.89061737060547, |
| "loss": 0.6059828400611877, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.37160247564315796, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": -0.07941240072250366, |
| "rewards/margins": 3.3084330558776855, |
| "rewards/rejected": -3.387845039367676, |
| "step": 103, |
| "train_speed(iter/s)": 0.01122 |
| }, |
| { |
| "epoch": 0.2615529707639107, |
| "grad_norm": 5.99639368057251, |
| "learning_rate": 0.00019925405086113768, |
| "logits/chosen": -0.23520317673683167, |
| "logits/rejected": -0.3863908052444458, |
| "logps/chosen": -6.1102681159973145, |
| "logps/rejected": -41.600799560546875, |
| "loss": 0.8184252381324768, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.5032728910446167, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": -0.09978590905666351, |
| "rewards/margins": 2.611102819442749, |
| "rewards/rejected": -2.7108888626098633, |
| "step": 104, |
| "train_speed(iter/s)": 0.011221 |
| }, |
| { |
| "epoch": 0.26406790317510215, |
| "grad_norm": 4.219518184661865, |
| "learning_rate": 0.0001992198034369349, |
| "logits/chosen": -0.2237715721130371, |
| "logits/rejected": -0.38729795813560486, |
| "logps/chosen": -6.913872718811035, |
| "logps/rejected": -42.98509979248047, |
| "loss": 0.769071638584137, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.5157548189163208, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.060354869812726974, |
| "rewards/margins": 2.590625762939453, |
| "rewards/rejected": -2.530271053314209, |
| "step": 105, |
| "train_speed(iter/s)": 0.011221 |
| }, |
| { |
| "epoch": 0.26658283558629364, |
| "grad_norm": 4.175528049468994, |
| "learning_rate": 0.000199184790464393, |
| "logits/chosen": -0.2919754683971405, |
| "logits/rejected": -0.4413781762123108, |
| "logps/chosen": -4.1272172927856445, |
| "logps/rejected": -32.008277893066406, |
| "loss": 0.7491403222084045, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.41593173146247864, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.08565365523099899, |
| "rewards/margins": 2.0251622200012207, |
| "rewards/rejected": -1.9395084381103516, |
| "step": 106, |
| "train_speed(iter/s)": 0.011222 |
| }, |
| { |
| "epoch": 0.2690977679974851, |
| "grad_norm": 2.857898473739624, |
| "learning_rate": 0.00019914901221366086, |
| "logits/chosen": -0.2756834924221039, |
| "logits/rejected": -0.4335779845714569, |
| "logps/chosen": -5.15769624710083, |
| "logps/rejected": -41.91234588623047, |
| "loss": 0.63164883852005, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.3513546586036682, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.06739385426044464, |
| "rewards/margins": 2.5824873447418213, |
| "rewards/rejected": -2.5150933265686035, |
| "step": 107, |
| "train_speed(iter/s)": 0.011223 |
| }, |
| { |
| "epoch": 0.2716127004086765, |
| "grad_norm": 1.9767286777496338, |
| "learning_rate": 0.0001991124689607921, |
| "logits/chosen": -0.23816093802452087, |
| "logits/rejected": -0.4088671803474426, |
| "logps/chosen": -6.058350563049316, |
| "logps/rejected": -36.48659133911133, |
| "loss": 0.795885443687439, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.4665300250053406, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.02518155239522457, |
| "rewards/margins": 2.0897223949432373, |
| "rewards/rejected": -2.0645408630371094, |
| "step": 108, |
| "train_speed(iter/s)": 0.011224 |
| }, |
| { |
| "epoch": 0.27412763281986796, |
| "grad_norm": 4.606684684753418, |
| "learning_rate": 0.00019907516098774275, |
| "logits/chosen": -0.3413383960723877, |
| "logits/rejected": -0.4257667064666748, |
| "logps/chosen": -5.4365692138671875, |
| "logps/rejected": -36.4229621887207, |
| "loss": 0.8568770885467529, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.528153121471405, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": 0.014822255820035934, |
| "rewards/margins": 2.660560369491577, |
| "rewards/rejected": -2.645737886428833, |
| "step": 109, |
| "train_speed(iter/s)": 0.011224 |
| }, |
| { |
| "epoch": 0.2766425652310594, |
| "grad_norm": 2.080709457397461, |
| "learning_rate": 0.00019903708858236925, |
| "logits/chosen": -0.22644048929214478, |
| "logits/rejected": -0.3494427800178528, |
| "logps/chosen": -6.887048721313477, |
| "logps/rejected": -39.19084167480469, |
| "loss": 0.7752804756164551, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.4188353717327118, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": -0.046474143862724304, |
| "rewards/margins": 2.0502114295959473, |
| "rewards/rejected": -2.0966856479644775, |
| "step": 110, |
| "train_speed(iter/s)": 0.011224 |
| }, |
| { |
| "epoch": 0.27915749764225084, |
| "grad_norm": 2.133538007736206, |
| "learning_rate": 0.00019899825203842613, |
| "logits/chosen": -0.24960362911224365, |
| "logits/rejected": -0.42648327350616455, |
| "logps/chosen": -4.220504283905029, |
| "logps/rejected": -38.22932815551758, |
| "loss": 0.7358196377754211, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.4154231548309326, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.12325219810009003, |
| "rewards/margins": 2.0720622539520264, |
| "rewards/rejected": -1.9488099813461304, |
| "step": 111, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.28167243005344234, |
| "grad_norm": 1.9261109828948975, |
| "learning_rate": 0.00019895865165556377, |
| "logits/chosen": -0.2359025776386261, |
| "logits/rejected": -0.4521249830722809, |
| "logps/chosen": -5.312178611755371, |
| "logps/rejected": -42.527828216552734, |
| "loss": 0.6443281769752502, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.33275920152664185, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": -0.00696786493062973, |
| "rewards/margins": 2.2711665630340576, |
| "rewards/rejected": -2.2781341075897217, |
| "step": 112, |
| "train_speed(iter/s)": 0.011224 |
| }, |
| { |
| "epoch": 0.2841873624646338, |
| "grad_norm": 1.973440170288086, |
| "learning_rate": 0.00019891828773932604, |
| "logits/chosen": -0.31173762679100037, |
| "logits/rejected": -0.4782518148422241, |
| "logps/chosen": -5.571796417236328, |
| "logps/rejected": -36.36091995239258, |
| "loss": 0.6021603345870972, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.3728388547897339, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.25308576226234436, |
| "rewards/margins": 2.2811777591705322, |
| "rewards/rejected": -2.0280919075012207, |
| "step": 113, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.2867022948758252, |
| "grad_norm": 2.1112029552459717, |
| "learning_rate": 0.0001988771606011481, |
| "logits/chosen": -0.29321083426475525, |
| "logits/rejected": -0.4459826946258545, |
| "logps/chosen": -7.568819046020508, |
| "logps/rejected": -36.86845016479492, |
| "loss": 0.8353914022445679, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.557527482509613, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.08000842481851578, |
| "rewards/margins": 2.1105971336364746, |
| "rewards/rejected": -2.0305888652801514, |
| "step": 114, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.28921722728701665, |
| "grad_norm": 1.5973310470581055, |
| "learning_rate": 0.0001988352705583538, |
| "logits/chosen": -0.35277947783470154, |
| "logits/rejected": -0.4771711826324463, |
| "logps/chosen": -6.40337610244751, |
| "logps/rejected": -36.56932830810547, |
| "loss": 0.7110580801963806, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.380901962518692, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.0295229684561491, |
| "rewards/margins": 2.1401078701019287, |
| "rewards/rejected": -2.1105847358703613, |
| "step": 115, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.2917321596982081, |
| "grad_norm": 2.2071542739868164, |
| "learning_rate": 0.0001987926179341533, |
| "logits/chosen": -0.3233400583267212, |
| "logits/rejected": -0.49479973316192627, |
| "logps/chosen": -7.279633522033691, |
| "logps/rejected": -42.67523956298828, |
| "loss": 0.6601336002349854, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.42307049036026, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.14696629345417023, |
| "rewards/margins": 2.9207940101623535, |
| "rewards/rejected": -2.77382755279541, |
| "step": 116, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.29424709210939953, |
| "grad_norm": 7.165996551513672, |
| "learning_rate": 0.00019874920305764068, |
| "logits/chosen": -0.34290945529937744, |
| "logits/rejected": -0.5152956247329712, |
| "logps/chosen": -7.311550140380859, |
| "logps/rejected": -41.441612243652344, |
| "loss": 0.9759319424629211, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.6613105535507202, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": -0.17784443497657776, |
| "rewards/margins": 2.404524803161621, |
| "rewards/rejected": -2.582369565963745, |
| "step": 117, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.29676202452059103, |
| "grad_norm": 2.9480412006378174, |
| "learning_rate": 0.00019870502626379127, |
| "logits/chosen": -0.3888930678367615, |
| "logits/rejected": -0.5601359009742737, |
| "logps/chosen": -6.752213954925537, |
| "logps/rejected": -42.02001190185547, |
| "loss": 0.6632174849510193, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.41683804988861084, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": -0.10449926555156708, |
| "rewards/margins": 2.6166954040527344, |
| "rewards/rejected": -2.721194267272949, |
| "step": 118, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.29927695693178247, |
| "grad_norm": 8.507670402526855, |
| "learning_rate": 0.00019866008789345917, |
| "logits/chosen": -0.40375155210494995, |
| "logits/rejected": -0.5714547634124756, |
| "logps/chosen": -6.916952610015869, |
| "logps/rejected": -41.485107421875, |
| "loss": 0.8475279211997986, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.5039829015731812, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": -0.07569311559200287, |
| "rewards/margins": 2.307457685470581, |
| "rewards/rejected": -2.383150577545166, |
| "step": 119, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.3017918893429739, |
| "grad_norm": 1.6022049188613892, |
| "learning_rate": 0.00019861438829337438, |
| "logits/chosen": -0.3536994159221649, |
| "logits/rejected": -0.5457285046577454, |
| "logps/chosen": -7.962162971496582, |
| "logps/rejected": -50.184635162353516, |
| "loss": 0.7923818826675415, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.5494890809059143, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.098821260035038, |
| "rewards/margins": 2.853030204772949, |
| "rewards/rejected": -2.75420880317688, |
| "step": 120, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.30430682175416535, |
| "grad_norm": 4.437849521636963, |
| "learning_rate": 0.00019856792781614054, |
| "logits/chosen": -0.4381689429283142, |
| "logits/rejected": -0.6431064605712891, |
| "logps/chosen": -3.382079601287842, |
| "logps/rejected": -36.976806640625, |
| "loss": 0.7761183977127075, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.43555858731269836, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.0065191928297281265, |
| "rewards/margins": 1.8534878492355347, |
| "rewards/rejected": -1.846968650817871, |
| "step": 121, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.3068217541653568, |
| "grad_norm": 2.79468035697937, |
| "learning_rate": 0.00019852070682023176, |
| "logits/chosen": -0.5022692680358887, |
| "logits/rejected": -0.6749197244644165, |
| "logps/chosen": -6.771264553070068, |
| "logps/rejected": -38.43341827392578, |
| "loss": 0.6576388478279114, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.40165674686431885, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.21301744878292084, |
| "rewards/margins": 2.2969624996185303, |
| "rewards/rejected": -2.0839452743530273, |
| "step": 122, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.3093366865765483, |
| "grad_norm": 1.964633822441101, |
| "learning_rate": 0.00019847272566999026, |
| "logits/chosen": -0.5233901739120483, |
| "logits/rejected": -0.6417133212089539, |
| "logps/chosen": -9.739703178405762, |
| "logps/rejected": -28.968997955322266, |
| "loss": 0.8914016485214233, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.5449220538139343, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.16006287932395935, |
| "rewards/margins": 1.5245118141174316, |
| "rewards/rejected": -1.3644486665725708, |
| "step": 123, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.3118516189877397, |
| "grad_norm": 1.871849775314331, |
| "learning_rate": 0.0001984239847356233, |
| "logits/chosen": -0.5555144548416138, |
| "logits/rejected": -0.6761674284934998, |
| "logps/chosen": -4.62461519241333, |
| "logps/rejected": -41.918800354003906, |
| "loss": 0.5709429383277893, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.3194217383861542, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.10139736533164978, |
| "rewards/margins": 3.0129401683807373, |
| "rewards/rejected": -2.9115428924560547, |
| "step": 124, |
| "train_speed(iter/s)": 0.011227 |
| }, |
| { |
| "epoch": 0.31436655139893116, |
| "grad_norm": 2.3828136920928955, |
| "learning_rate": 0.00019837448439320027, |
| "logits/chosen": -0.5682411789894104, |
| "logits/rejected": -0.7420387268066406, |
| "logps/chosen": -3.964232921600342, |
| "logps/rejected": -61.1876335144043, |
| "loss": 0.5395267605781555, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.3251190483570099, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.031132016330957413, |
| "rewards/margins": 4.458404541015625, |
| "rewards/rejected": -4.427271842956543, |
| "step": 125, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.3168814838101226, |
| "grad_norm": 2.152522325515747, |
| "learning_rate": 0.0001983242250246501, |
| "logits/chosen": -0.5287045240402222, |
| "logits/rejected": -0.7190724611282349, |
| "logps/chosen": -6.970052719116211, |
| "logps/rejected": -73.82839965820312, |
| "loss": 0.5324504971504211, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.40117147564888, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": -0.012534398585557938, |
| "rewards/margins": 5.6087493896484375, |
| "rewards/rejected": -5.621283054351807, |
| "step": 126, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.31939641622131404, |
| "grad_norm": 5.082659721374512, |
| "learning_rate": 0.00019827320701775806, |
| "logits/chosen": -0.4820547103881836, |
| "logits/rejected": -0.6797658205032349, |
| "logps/chosen": -6.213442802429199, |
| "logps/rejected": -70.91389465332031, |
| "loss": 0.6097095012664795, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.4043075144290924, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": -0.03578203544020653, |
| "rewards/margins": 4.8603901863098145, |
| "rewards/rejected": -4.896172046661377, |
| "step": 127, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.3219113486325055, |
| "grad_norm": 1.7538974285125732, |
| "learning_rate": 0.0001982214307661627, |
| "logits/chosen": -0.45252111554145813, |
| "logits/rejected": -0.6814027428627014, |
| "logps/chosen": -4.733944416046143, |
| "logps/rejected": -62.52580261230469, |
| "loss": 0.5949385166168213, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.3638124167919159, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.1602221429347992, |
| "rewards/margins": 4.626731872558594, |
| "rewards/rejected": -4.466509819030762, |
| "step": 128, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.324426281043697, |
| "grad_norm": 1.4243698120117188, |
| "learning_rate": 0.00019816889666935317, |
| "logits/chosen": -0.3787720203399658, |
| "logits/rejected": -0.6261472702026367, |
| "logps/chosen": -6.471246719360352, |
| "logps/rejected": -71.88873291015625, |
| "loss": 0.49682942032814026, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.33228519558906555, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.13370710611343384, |
| "rewards/margins": 4.678413391113281, |
| "rewards/rejected": -4.544705867767334, |
| "step": 129, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.3269412134548884, |
| "grad_norm": 2.5607693195343018, |
| "learning_rate": 0.00019811560513266572, |
| "logits/chosen": -0.4134800434112549, |
| "logits/rejected": -0.611393928527832, |
| "logps/chosen": -5.9260759353637695, |
| "logps/rejected": -60.01020431518555, |
| "loss": 0.601435124874115, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.4060709476470947, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.08814961463212967, |
| "rewards/margins": 4.3574066162109375, |
| "rewards/rejected": -4.269256591796875, |
| "step": 130, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.32945614586607985, |
| "grad_norm": 1.9927021265029907, |
| "learning_rate": 0.00019806155656728084, |
| "logits/chosen": -0.33065900206565857, |
| "logits/rejected": -0.6154841184616089, |
| "logps/chosen": -7.140951156616211, |
| "logps/rejected": -73.75382232666016, |
| "loss": 0.7812880277633667, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.5943235158920288, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": -0.07201401889324188, |
| "rewards/margins": 4.931735992431641, |
| "rewards/rejected": -5.003749370574951, |
| "step": 131, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.3319710782772713, |
| "grad_norm": 2.2726259231567383, |
| "learning_rate": 0.00019800675139022006, |
| "logits/chosen": -0.48140621185302734, |
| "logits/rejected": -0.5989112257957458, |
| "logps/chosen": -8.895767211914062, |
| "logps/rejected": -55.02824783325195, |
| "loss": 0.6833999156951904, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.3953901529312134, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": -0.2496323436498642, |
| "rewards/margins": 3.696012258529663, |
| "rewards/rejected": -3.9456448554992676, |
| "step": 132, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.33448601068846273, |
| "grad_norm": 2.0731728076934814, |
| "learning_rate": 0.00019795119002434262, |
| "logits/chosen": -0.4898430407047272, |
| "logits/rejected": -0.5940038561820984, |
| "logps/chosen": -6.4923415184021, |
| "logps/rejected": -53.08872985839844, |
| "loss": 0.6633037328720093, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.38765111565589905, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.014707805588841438, |
| "rewards/margins": 3.6382081508636475, |
| "rewards/rejected": -3.623500108718872, |
| "step": 133, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.33700094309965417, |
| "grad_norm": 2.124537467956543, |
| "learning_rate": 0.00019789487289834228, |
| "logits/chosen": -0.38429343700408936, |
| "logits/rejected": -0.587513267993927, |
| "logps/chosen": -3.70666241645813, |
| "logps/rejected": -56.821434020996094, |
| "loss": 0.5152694582939148, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.30610963702201843, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.09033096581697464, |
| "rewards/margins": 4.2761945724487305, |
| "rewards/rejected": -4.185863494873047, |
| "step": 134, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.33951587551084567, |
| "grad_norm": 1.165412425994873, |
| "learning_rate": 0.000197837800446744, |
| "logits/chosen": -0.2946363687515259, |
| "logits/rejected": -0.6158965229988098, |
| "logps/chosen": -5.17818021774292, |
| "logps/rejected": -85.47969818115234, |
| "loss": 0.34627044200897217, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.2048141062259674, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.022251788526773453, |
| "rewards/margins": 6.3592729568481445, |
| "rewards/rejected": -6.337022304534912, |
| "step": 135, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.3420308079220371, |
| "grad_norm": 1.6704083681106567, |
| "learning_rate": 0.00019777997310990063, |
| "logits/chosen": -0.34255802631378174, |
| "logits/rejected": -0.6556228995323181, |
| "logps/chosen": -2.7305595874786377, |
| "logps/rejected": -83.5248031616211, |
| "loss": 0.355721652507782, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.25845229625701904, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.13533437252044678, |
| "rewards/margins": 6.411257266998291, |
| "rewards/rejected": -6.275922775268555, |
| "step": 136, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.34454574033322855, |
| "grad_norm": 1.8042700290679932, |
| "learning_rate": 0.00019772139133398942, |
| "logits/chosen": -0.3927345275878906, |
| "logits/rejected": -0.6234123706817627, |
| "logps/chosen": -5.4586615562438965, |
| "logps/rejected": -81.85598754882812, |
| "loss": 0.4663994014263153, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.2979077696800232, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": -0.012417782098054886, |
| "rewards/margins": 6.194499492645264, |
| "rewards/rejected": -6.2069172859191895, |
| "step": 137, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.34706067274442, |
| "grad_norm": 2.92842960357666, |
| "learning_rate": 0.00019766205557100868, |
| "logits/chosen": -0.559550940990448, |
| "logits/rejected": -0.7328889966011047, |
| "logps/chosen": -9.122381210327148, |
| "logps/rejected": -70.6622314453125, |
| "loss": 0.7152190208435059, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.5275388956069946, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": -0.06365346908569336, |
| "rewards/margins": 5.660825729370117, |
| "rewards/rejected": -5.724478721618652, |
| "step": 138, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.3495756051556114, |
| "grad_norm": 1.7731250524520874, |
| "learning_rate": 0.00019760196627877422, |
| "logits/chosen": -0.3356359004974365, |
| "logits/rejected": -0.7464644908905029, |
| "logps/chosen": -3.0185112953186035, |
| "logps/rejected": -116.795654296875, |
| "loss": 0.4166179299354553, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.28380244970321655, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.07928900420665741, |
| "rewards/margins": 9.400187492370605, |
| "rewards/rejected": -9.32089900970459, |
| "step": 139, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.3520905375668029, |
| "grad_norm": 6.910381317138672, |
| "learning_rate": 0.0001975411239209158, |
| "logits/chosen": -0.6025805473327637, |
| "logits/rejected": -0.7230421900749207, |
| "logps/chosen": -13.585058212280273, |
| "logps/rejected": -62.04022979736328, |
| "loss": 1.3271528482437134, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.8942356109619141, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": -0.4771670699119568, |
| "rewards/margins": 4.614741802215576, |
| "rewards/rejected": -5.0919084548950195, |
| "step": 140, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.35460546997799436, |
| "grad_norm": 5.268382549285889, |
| "learning_rate": 0.0001974795289668737, |
| "logits/chosen": -0.47753405570983887, |
| "logits/rejected": -0.8787558674812317, |
| "logps/chosen": -8.216950416564941, |
| "logps/rejected": -102.49224090576172, |
| "loss": 0.7080188393592834, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.6081770658493042, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": -0.37120816111564636, |
| "rewards/margins": 7.621390342712402, |
| "rewards/rejected": -7.992597579956055, |
| "step": 141, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.3571204023891858, |
| "grad_norm": 6.239411354064941, |
| "learning_rate": 0.00019741718189189485, |
| "logits/chosen": -0.5375499725341797, |
| "logits/rejected": -0.7797288298606873, |
| "logps/chosen": -7.561271667480469, |
| "logps/rejected": -72.9504623413086, |
| "loss": 0.9173229932785034, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.6234984397888184, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": -0.2173769325017929, |
| "rewards/margins": 5.198176383972168, |
| "rewards/rejected": -5.415553092956543, |
| "step": 142, |
| "train_speed(iter/s)": 0.011231 |
| }, |
| { |
| "epoch": 0.35963533480037724, |
| "grad_norm": 4.152512073516846, |
| "learning_rate": 0.00019735408317702948, |
| "logits/chosen": -0.5347225069999695, |
| "logits/rejected": -0.7430693507194519, |
| "logps/chosen": -4.227977752685547, |
| "logps/rejected": -57.00012969970703, |
| "loss": 0.5255740284919739, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.34119245409965515, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.0003469698131084442, |
| "rewards/margins": 4.147022247314453, |
| "rewards/rejected": -4.1466755867004395, |
| "step": 143, |
| "train_speed(iter/s)": 0.011231 |
| }, |
| { |
| "epoch": 0.3621502672115687, |
| "grad_norm": 1.935512900352478, |
| "learning_rate": 0.0001972902333091271, |
| "logits/chosen": -0.4890541732311249, |
| "logits/rejected": -0.6482999920845032, |
| "logps/chosen": -8.091506958007812, |
| "logps/rejected": -47.94240951538086, |
| "loss": 0.6421104669570923, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.4184344708919525, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.008477868512272835, |
| "rewards/margins": 3.3832898139953613, |
| "rewards/rejected": -3.3748116493225098, |
| "step": 144, |
| "train_speed(iter/s)": 0.011232 |
| }, |
| { |
| "epoch": 0.3646651996227601, |
| "grad_norm": 3.257821559906006, |
| "learning_rate": 0.00019722563278083287, |
| "logits/chosen": -0.46462729573249817, |
| "logits/rejected": -0.71808260679245, |
| "logps/chosen": -3.831825017929077, |
| "logps/rejected": -43.67421340942383, |
| "loss": 0.6770502924919128, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.40698307752609253, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.03249932453036308, |
| "rewards/margins": 2.939378023147583, |
| "rewards/rejected": -2.9068784713745117, |
| "step": 145, |
| "train_speed(iter/s)": 0.011232 |
| }, |
| { |
| "epoch": 0.3671801320339516, |
| "grad_norm": 3.0926783084869385, |
| "learning_rate": 0.00019716028209058387, |
| "logits/chosen": -0.5261669158935547, |
| "logits/rejected": -0.6899480223655701, |
| "logps/chosen": -6.620856285095215, |
| "logps/rejected": -44.43523406982422, |
| "loss": 0.9013221263885498, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.658555269241333, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": -0.10268372297286987, |
| "rewards/margins": 2.719848155975342, |
| "rewards/rejected": -2.8225317001342773, |
| "step": 146, |
| "train_speed(iter/s)": 0.011233 |
| }, |
| { |
| "epoch": 0.36969506444514305, |
| "grad_norm": 1.952876329421997, |
| "learning_rate": 0.0001970941817426052, |
| "logits/chosen": -0.3797496557235718, |
| "logits/rejected": -0.6095885038375854, |
| "logps/chosen": -3.3423259258270264, |
| "logps/rejected": -51.2366943359375, |
| "loss": 0.3124345541000366, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.19474804401397705, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.15071216225624084, |
| "rewards/margins": 3.3171157836914062, |
| "rewards/rejected": -3.166403293609619, |
| "step": 147, |
| "train_speed(iter/s)": 0.011233 |
| }, |
| { |
| "epoch": 0.3722099968563345, |
| "grad_norm": 5.522589683532715, |
| "learning_rate": 0.00019702733224690605, |
| "logits/chosen": -0.4721255898475647, |
| "logits/rejected": -0.6467065215110779, |
| "logps/chosen": -8.671660423278809, |
| "logps/rejected": -41.544979095458984, |
| "loss": 0.7880657911300659, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.553983211517334, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": -0.06357112526893616, |
| "rewards/margins": 2.7004964351654053, |
| "rewards/rejected": -2.7640676498413086, |
| "step": 148, |
| "train_speed(iter/s)": 0.011233 |
| }, |
| { |
| "epoch": 0.37472492926752593, |
| "grad_norm": 1.7939379215240479, |
| "learning_rate": 0.00019695973411927578, |
| "logits/chosen": -0.518312394618988, |
| "logits/rejected": -0.689118504524231, |
| "logps/chosen": -2.949949026107788, |
| "logps/rejected": -47.91648864746094, |
| "loss": 0.3869367241859436, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.22588227689266205, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.06105111539363861, |
| "rewards/margins": 3.0687060356140137, |
| "rewards/rejected": -3.0076546669006348, |
| "step": 149, |
| "train_speed(iter/s)": 0.011234 |
| }, |
| { |
| "epoch": 0.37723986167871737, |
| "grad_norm": 1.6997706890106201, |
| "learning_rate": 0.00019689138788127995, |
| "logits/chosen": -0.49549129605293274, |
| "logits/rejected": -0.6151180267333984, |
| "logps/chosen": -6.0540666580200195, |
| "logps/rejected": -35.12141036987305, |
| "loss": 0.6853822469711304, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.4531955420970917, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.015824541449546814, |
| "rewards/margins": 2.214078903198242, |
| "rewards/rejected": -2.198254346847534, |
| "step": 150, |
| "train_speed(iter/s)": 0.011234 |
| }, |
| { |
| "epoch": 0.3797547940899088, |
| "grad_norm": 1.94599449634552, |
| "learning_rate": 0.00019682229406025635, |
| "logits/chosen": -0.44517412781715393, |
| "logits/rejected": -0.583071231842041, |
| "logps/chosen": -8.055398941040039, |
| "logps/rejected": -40.7237548828125, |
| "loss": 0.6454893350601196, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.38740435242652893, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.09544569253921509, |
| "rewards/margins": 2.4482340812683105, |
| "rewards/rejected": -2.3527884483337402, |
| "step": 151, |
| "train_speed(iter/s)": 0.011221 |
| }, |
| { |
| "epoch": 0.3822697265011003, |
| "grad_norm": 1.4162402153015137, |
| "learning_rate": 0.00019675245318931083, |
| "logits/chosen": -0.5134773254394531, |
| "logits/rejected": -0.6419417858123779, |
| "logps/chosen": -9.19031047821045, |
| "logps/rejected": -41.0048828125, |
| "loss": 0.6307085752487183, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.42102259397506714, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": -0.08155234903097153, |
| "rewards/margins": 2.483502149581909, |
| "rewards/rejected": -2.565054416656494, |
| "step": 152, |
| "train_speed(iter/s)": 0.011221 |
| }, |
| { |
| "epoch": 0.38478465891229174, |
| "grad_norm": 1.932735562324524, |
| "learning_rate": 0.0001966818658073133, |
| "logits/chosen": -0.5457805395126343, |
| "logits/rejected": -0.680858850479126, |
| "logps/chosen": -6.187590599060059, |
| "logps/rejected": -37.30434036254883, |
| "loss": 0.6069836020469666, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.3702396750450134, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.003183305263519287, |
| "rewards/margins": 2.3362035751342773, |
| "rewards/rejected": -2.3330204486846924, |
| "step": 153, |
| "train_speed(iter/s)": 0.011222 |
| }, |
| { |
| "epoch": 0.3872995913234832, |
| "grad_norm": 2.0515635013580322, |
| "learning_rate": 0.0001966105324588934, |
| "logits/chosen": -0.5253856182098389, |
| "logits/rejected": -0.6266660094261169, |
| "logps/chosen": -11.048845291137695, |
| "logps/rejected": -40.014915466308594, |
| "loss": 0.8203007578849792, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.56341153383255, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.09865356236696243, |
| "rewards/margins": 2.6950490474700928, |
| "rewards/rejected": -2.596395492553711, |
| "step": 154, |
| "train_speed(iter/s)": 0.011222 |
| }, |
| { |
| "epoch": 0.3898145237346746, |
| "grad_norm": 2.258105516433716, |
| "learning_rate": 0.00019653845369443657, |
| "logits/chosen": -0.49116846919059753, |
| "logits/rejected": -0.6502944231033325, |
| "logps/chosen": -6.3410539627075195, |
| "logps/rejected": -45.01954650878906, |
| "loss": 0.6601016521453857, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.4770495295524597, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.08940570056438446, |
| "rewards/margins": 2.79660701751709, |
| "rewards/rejected": -2.7072014808654785, |
| "step": 155, |
| "train_speed(iter/s)": 0.011222 |
| }, |
| { |
| "epoch": 0.39232945614586606, |
| "grad_norm": 1.9334651231765747, |
| "learning_rate": 0.00019646563007007952, |
| "logits/chosen": -0.5132689476013184, |
| "logits/rejected": -0.6826451420783997, |
| "logps/chosen": -4.647260665893555, |
| "logps/rejected": -35.987144470214844, |
| "loss": 0.5781624913215637, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.333342581987381, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.0551791712641716, |
| "rewards/margins": 1.9761953353881836, |
| "rewards/rejected": -1.9210160970687866, |
| "step": 156, |
| "train_speed(iter/s)": 0.011223 |
| }, |
| { |
| "epoch": 0.3948443885570575, |
| "grad_norm": 2.0030107498168945, |
| "learning_rate": 0.00019639206214770608, |
| "logits/chosen": -0.5250845551490784, |
| "logits/rejected": -0.6993058919906616, |
| "logps/chosen": -3.4496142864227295, |
| "logps/rejected": -45.091514587402344, |
| "loss": 0.4796870946884155, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.27256864309310913, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.039092980325222015, |
| "rewards/margins": 2.82478666305542, |
| "rewards/rejected": -2.785693645477295, |
| "step": 157, |
| "train_speed(iter/s)": 0.011223 |
| }, |
| { |
| "epoch": 0.397359320968249, |
| "grad_norm": 1.6849418878555298, |
| "learning_rate": 0.00019631775049494285, |
| "logits/chosen": -0.43024155497550964, |
| "logits/rejected": -0.6700482964515686, |
| "logps/chosen": -3.823197364807129, |
| "logps/rejected": -56.609588623046875, |
| "loss": 0.42021045088768005, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.24996069073677063, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.004662778228521347, |
| "rewards/margins": 3.1713931560516357, |
| "rewards/rejected": -3.1667304039001465, |
| "step": 158, |
| "train_speed(iter/s)": 0.011223 |
| }, |
| { |
| "epoch": 0.39987425337944044, |
| "grad_norm": 3.1281967163085938, |
| "learning_rate": 0.00019624269568515486, |
| "logits/chosen": -0.43441203236579895, |
| "logits/rejected": -0.6460458040237427, |
| "logps/chosen": -6.727141857147217, |
| "logps/rejected": -45.23570251464844, |
| "loss": 0.7260392904281616, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.5018711090087891, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.011816263198852539, |
| "rewards/margins": 2.4935953617095947, |
| "rewards/rejected": -2.4817793369293213, |
| "step": 159, |
| "train_speed(iter/s)": 0.011223 |
| }, |
| { |
| "epoch": 0.4023891857906319, |
| "grad_norm": 3.3100078105926514, |
| "learning_rate": 0.00019616689829744105, |
| "logits/chosen": -0.6007479429244995, |
| "logits/rejected": -0.7636129856109619, |
| "logps/chosen": -6.275008678436279, |
| "logps/rejected": -35.27611541748047, |
| "loss": 0.6686663627624512, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.4275904893875122, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.1287657767534256, |
| "rewards/margins": 2.2340850830078125, |
| "rewards/rejected": -2.1053192615509033, |
| "step": 160, |
| "train_speed(iter/s)": 0.011223 |
| }, |
| { |
| "epoch": 0.4049041182018233, |
| "grad_norm": 3.4858033657073975, |
| "learning_rate": 0.0001960903589166299, |
| "logits/chosen": -0.6405993700027466, |
| "logits/rejected": -0.697019100189209, |
| "logps/chosen": -9.289031982421875, |
| "logps/rejected": -38.57951736450195, |
| "loss": 0.7603179216384888, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.4232831597328186, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.159571573138237, |
| "rewards/margins": 2.720222234725952, |
| "rewards/rejected": -2.56065034866333, |
| "step": 161, |
| "train_speed(iter/s)": 0.011224 |
| }, |
| { |
| "epoch": 0.40741905061301475, |
| "grad_norm": 1.844115972518921, |
| "learning_rate": 0.00019601307813327482, |
| "logits/chosen": -0.5259416103363037, |
| "logits/rejected": -0.6975188255310059, |
| "logps/chosen": -2.951578140258789, |
| "logps/rejected": -41.11060333251953, |
| "loss": 0.4498739242553711, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.23409336805343628, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.14196570217609406, |
| "rewards/margins": 2.5788159370422363, |
| "rewards/rejected": -2.436850070953369, |
| "step": 162, |
| "train_speed(iter/s)": 0.011224 |
| }, |
| { |
| "epoch": 0.40993398302420625, |
| "grad_norm": 5.637467861175537, |
| "learning_rate": 0.00019593505654364965, |
| "logits/chosen": -0.45152366161346436, |
| "logits/rejected": -0.6798401474952698, |
| "logps/chosen": -4.170862674713135, |
| "logps/rejected": -53.169776916503906, |
| "loss": 0.6846017241477966, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.5021944642066956, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.010230405256152153, |
| "rewards/margins": 3.3515424728393555, |
| "rewards/rejected": -3.3413121700286865, |
| "step": 163, |
| "train_speed(iter/s)": 0.011224 |
| }, |
| { |
| "epoch": 0.4124489154353977, |
| "grad_norm": 1.4745384454727173, |
| "learning_rate": 0.00019585629474974415, |
| "logits/chosen": -0.4008867144584656, |
| "logits/rejected": -0.7353089451789856, |
| "logps/chosen": -0.4037323594093323, |
| "logps/rejected": -61.83756637573242, |
| "loss": 0.18311206996440887, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.05691269040107727, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.09548275917768478, |
| "rewards/margins": 4.11773157119751, |
| "rewards/rejected": -4.0222487449646, |
| "step": 164, |
| "train_speed(iter/s)": 0.011224 |
| }, |
| { |
| "epoch": 0.41496384784658913, |
| "grad_norm": 1.9870681762695312, |
| "learning_rate": 0.0001957767933592591, |
| "logits/chosen": -0.5013211965560913, |
| "logits/rejected": -0.6647384762763977, |
| "logps/chosen": -6.108734130859375, |
| "logps/rejected": -45.8098030090332, |
| "loss": 0.6409457921981812, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.3451662063598633, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": -0.025398313999176025, |
| "rewards/margins": 3.0071825981140137, |
| "rewards/rejected": -3.032581090927124, |
| "step": 165, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.41747878025778057, |
| "grad_norm": 3.7264280319213867, |
| "learning_rate": 0.00019569655298560195, |
| "logits/chosen": -0.5106596350669861, |
| "logits/rejected": -0.7329829931259155, |
| "logps/chosen": -4.24332857131958, |
| "logps/rejected": -48.86112594604492, |
| "loss": 0.5813378691673279, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.3752741515636444, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.06557303667068481, |
| "rewards/margins": 3.4898738861083984, |
| "rewards/rejected": -3.4243011474609375, |
| "step": 166, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.419993712668972, |
| "grad_norm": 11.64145278930664, |
| "learning_rate": 0.0001956155742478817, |
| "logits/chosen": -0.4935857653617859, |
| "logits/rejected": -0.7044666409492493, |
| "logps/chosen": -2.654214382171631, |
| "logps/rejected": -57.629425048828125, |
| "loss": 0.3905934691429138, |
| "memory(GiB)": 42.61, |
| "nll_loss": 0.22700335085391998, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.1508655548095703, |
| "rewards/margins": 4.179229736328125, |
| "rewards/rejected": -4.028364181518555, |
| "step": 167, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.42250864508016345, |
| "grad_norm": 1.6378587484359741, |
| "learning_rate": 0.00019553385777090458, |
| "logits/chosen": -0.4575374722480774, |
| "logits/rejected": -0.6927694082260132, |
| "logps/chosen": -9.244451522827148, |
| "logps/rejected": -63.81715774536133, |
| "loss": 0.6180571913719177, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.47105246782302856, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.12050072848796844, |
| "rewards/margins": 4.137886047363281, |
| "rewards/rejected": -4.017385005950928, |
| "step": 168, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.42502357749135494, |
| "grad_norm": 6.146910667419434, |
| "learning_rate": 0.00019545140418516873, |
| "logits/chosen": -0.6766417622566223, |
| "logits/rejected": -0.7711372971534729, |
| "logps/chosen": -6.37576961517334, |
| "logps/rejected": -45.8558349609375, |
| "loss": 0.6669228672981262, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.5145984888076782, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.18157291412353516, |
| "rewards/margins": 3.766644239425659, |
| "rewards/rejected": -3.585071563720703, |
| "step": 169, |
| "train_speed(iter/s)": 0.011227 |
| }, |
| { |
| "epoch": 0.4275385099025464, |
| "grad_norm": 1.6984812021255493, |
| "learning_rate": 0.0001953682141268598, |
| "logits/chosen": -0.5011512637138367, |
| "logits/rejected": -0.688590943813324, |
| "logps/chosen": -3.602705478668213, |
| "logps/rejected": -55.99202346801758, |
| "loss": 0.3990403413772583, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.2418036162853241, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.027019452303647995, |
| "rewards/margins": 3.8597612380981445, |
| "rewards/rejected": -3.8327417373657227, |
| "step": 170, |
| "train_speed(iter/s)": 0.011227 |
| }, |
| { |
| "epoch": 0.4300534423137378, |
| "grad_norm": 5.023574352264404, |
| "learning_rate": 0.00019528428823784567, |
| "logits/chosen": -0.4159168004989624, |
| "logits/rejected": -0.7052143216133118, |
| "logps/chosen": -2.2552971839904785, |
| "logps/rejected": -71.4410400390625, |
| "loss": 0.29148706793785095, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.19378283619880676, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.13933303952217102, |
| "rewards/margins": 5.2820634841918945, |
| "rewards/rejected": -5.142730236053467, |
| "step": 171, |
| "train_speed(iter/s)": 0.011227 |
| }, |
| { |
| "epoch": 0.43256837472492926, |
| "grad_norm": 1.4866183996200562, |
| "learning_rate": 0.0001951996271656717, |
| "logits/chosen": -0.5606605410575867, |
| "logits/rejected": -0.7212972044944763, |
| "logps/chosen": -3.804295539855957, |
| "logps/rejected": -51.83647537231445, |
| "loss": 0.3623957335948944, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.21611489355564117, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.12722836434841156, |
| "rewards/margins": 3.714401960372925, |
| "rewards/rejected": -3.5871734619140625, |
| "step": 172, |
| "train_speed(iter/s)": 0.011227 |
| }, |
| { |
| "epoch": 0.4350833071361207, |
| "grad_norm": 3.7671830654144287, |
| "learning_rate": 0.00019511423156355577, |
| "logits/chosen": -0.4943828582763672, |
| "logits/rejected": -0.68037348985672, |
| "logps/chosen": -5.188858509063721, |
| "logps/rejected": -62.85913848876953, |
| "loss": 0.41962915658950806, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.2764420509338379, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.1342807114124298, |
| "rewards/margins": 4.525426387786865, |
| "rewards/rejected": -4.391145706176758, |
| "step": 173, |
| "train_speed(iter/s)": 0.011227 |
| }, |
| { |
| "epoch": 0.43759823954731214, |
| "grad_norm": 9.907013893127441, |
| "learning_rate": 0.00019502810209038303, |
| "logits/chosen": -0.5515968799591064, |
| "logits/rejected": -0.6605091691017151, |
| "logps/chosen": -9.89529800415039, |
| "logps/rejected": -54.34276580810547, |
| "loss": 0.9658512473106384, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.7056573033332825, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": -0.028916141018271446, |
| "rewards/margins": 3.5635647773742676, |
| "rewards/rejected": -3.5924811363220215, |
| "step": 174, |
| "train_speed(iter/s)": 0.011227 |
| }, |
| { |
| "epoch": 0.44011317195850364, |
| "grad_norm": 2.1124749183654785, |
| "learning_rate": 0.00019494123941070108, |
| "logits/chosen": -0.689885675907135, |
| "logits/rejected": -0.7663485407829285, |
| "logps/chosen": -5.329808712005615, |
| "logps/rejected": -39.43062210083008, |
| "loss": 0.6925463676452637, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.473371297121048, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.10141712427139282, |
| "rewards/margins": 3.0223309993743896, |
| "rewards/rejected": -2.9209136962890625, |
| "step": 175, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.4426281043696951, |
| "grad_norm": 36.679805755615234, |
| "learning_rate": 0.00019485364419471454, |
| "logits/chosen": -0.6628389954566956, |
| "logits/rejected": -0.7602969408035278, |
| "logps/chosen": -7.741974353790283, |
| "logps/rejected": -50.05625915527344, |
| "loss": 1.0915241241455078, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.7456662654876709, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": -0.35289716720581055, |
| "rewards/margins": 3.5574560165405273, |
| "rewards/rejected": -3.910353422164917, |
| "step": 176, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.4451430367808865, |
| "grad_norm": 2.4835803508758545, |
| "learning_rate": 0.00019476531711828027, |
| "logits/chosen": -0.5590236186981201, |
| "logits/rejected": -0.6718421578407288, |
| "logps/chosen": -5.849733352661133, |
| "logps/rejected": -51.53736114501953, |
| "loss": 0.40270960330963135, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.2558823227882385, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.11730007827281952, |
| "rewards/margins": 3.6312365531921387, |
| "rewards/rejected": -3.5139362812042236, |
| "step": 177, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.44765796919207795, |
| "grad_norm": 2.382329225540161, |
| "learning_rate": 0.00019467625886290167, |
| "logits/chosen": -0.5211893916130066, |
| "logits/rejected": -0.6878003478050232, |
| "logps/chosen": -11.300158500671387, |
| "logps/rejected": -52.15276336669922, |
| "loss": 0.7076267004013062, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.5078485012054443, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.07471176981925964, |
| "rewards/margins": 3.560542583465576, |
| "rewards/rejected": -3.485830783843994, |
| "step": 178, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.4501729016032694, |
| "grad_norm": 4.822922706604004, |
| "learning_rate": 0.0001945864701157239, |
| "logits/chosen": -0.5776659250259399, |
| "logits/rejected": -0.6799846291542053, |
| "logps/chosen": -4.035768032073975, |
| "logps/rejected": -54.64043426513672, |
| "loss": 0.48212817311286926, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.2608688175678253, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.17263993620872498, |
| "rewards/margins": 4.305383682250977, |
| "rewards/rejected": -4.132743835449219, |
| "step": 179, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.4526878340144609, |
| "grad_norm": 1.466308832168579, |
| "learning_rate": 0.00019449595156952827, |
| "logits/chosen": -0.6198251247406006, |
| "logits/rejected": -0.7188805341720581, |
| "logps/chosen": -7.5114359855651855, |
| "logps/rejected": -50.14148712158203, |
| "loss": 0.5570878982543945, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.3523883819580078, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.18179449439048767, |
| "rewards/margins": 3.7667787075042725, |
| "rewards/rejected": -3.584984302520752, |
| "step": 180, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.4552027664256523, |
| "grad_norm": 1.5548723936080933, |
| "learning_rate": 0.00019440470392272696, |
| "logits/chosen": -0.5984869003295898, |
| "logits/rejected": -0.7039155960083008, |
| "logps/chosen": -4.1996378898620605, |
| "logps/rejected": -45.629638671875, |
| "loss": 0.47419819235801697, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.31078362464904785, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.1542869210243225, |
| "rewards/margins": 3.5583298206329346, |
| "rewards/rejected": -3.404043197631836, |
| "step": 181, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.45771769883684377, |
| "grad_norm": 2.250375747680664, |
| "learning_rate": 0.00019431272787935773, |
| "logits/chosen": -0.5019629597663879, |
| "logits/rejected": -0.7356317639350891, |
| "logps/chosen": -10.908112525939941, |
| "logps/rejected": -52.47066116333008, |
| "loss": 1.0049289464950562, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.7764756083488464, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.024810096248984337, |
| "rewards/margins": 3.2386226654052734, |
| "rewards/rejected": -3.213812828063965, |
| "step": 182, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.4602326312480352, |
| "grad_norm": 22.676647186279297, |
| "learning_rate": 0.00019422002414907837, |
| "logits/chosen": -0.5647466778755188, |
| "logits/rejected": -0.7478159070014954, |
| "logps/chosen": -5.912107944488525, |
| "logps/rejected": -47.091400146484375, |
| "loss": 0.699102520942688, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.4706324338912964, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.08286911249160767, |
| "rewards/margins": 3.223126173019409, |
| "rewards/rejected": -3.140256881713867, |
| "step": 183, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.46274756365922665, |
| "grad_norm": 3.388159990310669, |
| "learning_rate": 0.00019412659344716124, |
| "logits/chosen": -0.5706430673599243, |
| "logits/rejected": -0.6877136826515198, |
| "logps/chosen": -11.683382987976074, |
| "logps/rejected": -46.81083297729492, |
| "loss": 1.3097541332244873, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.8712559342384338, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": -0.2759455144405365, |
| "rewards/margins": 3.09993839263916, |
| "rewards/rejected": -3.3758838176727295, |
| "step": 184, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.4652624960704181, |
| "grad_norm": 2.6059823036193848, |
| "learning_rate": 0.00019403243649448787, |
| "logits/chosen": -0.47367703914642334, |
| "logits/rejected": -0.7172597050666809, |
| "logps/chosen": -3.135293483734131, |
| "logps/rejected": -64.97146606445312, |
| "loss": 0.4278358221054077, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.2768169641494751, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.1706126630306244, |
| "rewards/margins": 4.8074727058410645, |
| "rewards/rejected": -4.636859893798828, |
| "step": 185, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.4677774284816096, |
| "grad_norm": 2.2509593963623047, |
| "learning_rate": 0.00019393755401754322, |
| "logits/chosen": -0.48067784309387207, |
| "logits/rejected": -0.6601268649101257, |
| "logps/chosen": -3.7737672328948975, |
| "logps/rejected": -61.828006744384766, |
| "loss": 0.44278520345687866, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.3135760426521301, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.05582159385085106, |
| "rewards/margins": 4.652613162994385, |
| "rewards/rejected": -4.5967912673950195, |
| "step": 186, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.470292360892801, |
| "grad_norm": 2.220067262649536, |
| "learning_rate": 0.00019384194674841026, |
| "logits/chosen": -0.5368369221687317, |
| "logits/rejected": -0.7164134383201599, |
| "logps/chosen": -4.382404804229736, |
| "logps/rejected": -63.785423278808594, |
| "loss": 0.5859192609786987, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.4215310215950012, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.042068447917699814, |
| "rewards/margins": 5.157468795776367, |
| "rewards/rejected": -5.115400314331055, |
| "step": 187, |
| "train_speed(iter/s)": 0.011231 |
| }, |
| { |
| "epoch": 0.47280729330399246, |
| "grad_norm": 1.3244057893753052, |
| "learning_rate": 0.0001937456154247641, |
| "logits/chosen": -0.5555019974708557, |
| "logits/rejected": -0.682890772819519, |
| "logps/chosen": -4.023111343383789, |
| "logps/rejected": -66.17463684082031, |
| "loss": 0.3469849228858948, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.22850053012371063, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.08244925737380981, |
| "rewards/margins": 5.2128143310546875, |
| "rewards/rejected": -5.130365371704102, |
| "step": 188, |
| "train_speed(iter/s)": 0.011231 |
| }, |
| { |
| "epoch": 0.4753222257151839, |
| "grad_norm": 5.5003886222839355, |
| "learning_rate": 0.00019364856078986652, |
| "logits/chosen": -0.504755437374115, |
| "logits/rejected": -0.6091613173484802, |
| "logps/chosen": -13.118067741394043, |
| "logps/rejected": -52.780235290527344, |
| "loss": 0.970127284526825, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.7232432961463928, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": -0.04733971506357193, |
| "rewards/margins": 3.863572120666504, |
| "rewards/rejected": -3.910911798477173, |
| "step": 189, |
| "train_speed(iter/s)": 0.011232 |
| }, |
| { |
| "epoch": 0.47783715812637534, |
| "grad_norm": 2.35336971282959, |
| "learning_rate": 0.0001935507835925601, |
| "logits/chosen": -0.4966239631175995, |
| "logits/rejected": -0.6422093510627747, |
| "logps/chosen": -5.089540004730225, |
| "logps/rejected": -60.03197479248047, |
| "loss": 0.48357081413269043, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.29401686787605286, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.06470837444067001, |
| "rewards/margins": 4.633599758148193, |
| "rewards/rejected": -4.568891525268555, |
| "step": 190, |
| "train_speed(iter/s)": 0.011232 |
| }, |
| { |
| "epoch": 0.4803520905375668, |
| "grad_norm": 2.2711422443389893, |
| "learning_rate": 0.00019345228458726252, |
| "logits/chosen": -0.41524171829223633, |
| "logits/rejected": -0.5779014229774475, |
| "logps/chosen": -6.11699914932251, |
| "logps/rejected": -65.24181365966797, |
| "loss": 0.5390986800193787, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.2827398180961609, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.04118676483631134, |
| "rewards/margins": 4.437079906463623, |
| "rewards/rejected": -4.395893096923828, |
| "step": 191, |
| "train_speed(iter/s)": 0.011232 |
| }, |
| { |
| "epoch": 0.4828670229487583, |
| "grad_norm": 3.4174418449401855, |
| "learning_rate": 0.00019335306453396064, |
| "logits/chosen": -0.3581904470920563, |
| "logits/rejected": -0.5604187250137329, |
| "logps/chosen": -4.7871503829956055, |
| "logps/rejected": -56.127437591552734, |
| "loss": 0.6041537523269653, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.35478317737579346, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.0018234718590974808, |
| "rewards/margins": 3.8149027824401855, |
| "rewards/rejected": -3.8130791187286377, |
| "step": 192, |
| "train_speed(iter/s)": 0.011232 |
| }, |
| { |
| "epoch": 0.4853819553599497, |
| "grad_norm": 1.6018799543380737, |
| "learning_rate": 0.00019325312419820473, |
| "logits/chosen": -0.40660223364830017, |
| "logits/rejected": -0.5828196406364441, |
| "logps/chosen": -4.125640869140625, |
| "logps/rejected": -52.407806396484375, |
| "loss": 0.4834650158882141, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.2773113250732422, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.08193957805633545, |
| "rewards/margins": 3.58589506149292, |
| "rewards/rejected": -3.503955602645874, |
| "step": 193, |
| "train_speed(iter/s)": 0.011232 |
| }, |
| { |
| "epoch": 0.48789688777114115, |
| "grad_norm": 2.956265926361084, |
| "learning_rate": 0.00019315246435110256, |
| "logits/chosen": -0.41891956329345703, |
| "logits/rejected": -0.5709394812583923, |
| "logps/chosen": -6.136990547180176, |
| "logps/rejected": -54.53316116333008, |
| "loss": 0.5783406496047974, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.4396575689315796, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.22025173902511597, |
| "rewards/margins": 3.940415143966675, |
| "rewards/rejected": -3.7201638221740723, |
| "step": 194, |
| "train_speed(iter/s)": 0.011233 |
| }, |
| { |
| "epoch": 0.4904118201823326, |
| "grad_norm": 2.4830644130706787, |
| "learning_rate": 0.00019305108576931336, |
| "logits/chosen": -0.4251477122306824, |
| "logits/rejected": -0.5646131038665771, |
| "logps/chosen": -6.740220069885254, |
| "logps/rejected": -59.58277893066406, |
| "loss": 0.6179866194725037, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.39784371852874756, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.03337670490145683, |
| "rewards/margins": 4.295322418212891, |
| "rewards/rejected": -4.261946201324463, |
| "step": 195, |
| "train_speed(iter/s)": 0.011233 |
| }, |
| { |
| "epoch": 0.49292675259352403, |
| "grad_norm": 2.0805859565734863, |
| "learning_rate": 0.0001929489892350419, |
| "logits/chosen": -0.4012482464313507, |
| "logits/rejected": -0.5744894742965698, |
| "logps/chosen": -3.9474775791168213, |
| "logps/rejected": -64.57502746582031, |
| "loss": 0.4640367329120636, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.32923948764801025, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.11397141218185425, |
| "rewards/margins": 4.956214904785156, |
| "rewards/rejected": -4.842243194580078, |
| "step": 196, |
| "train_speed(iter/s)": 0.011233 |
| }, |
| { |
| "epoch": 0.49544168500471547, |
| "grad_norm": 1.0079342126846313, |
| "learning_rate": 0.00019284617553603242, |
| "logits/chosen": -0.40687650442123413, |
| "logits/rejected": -0.5095179677009583, |
| "logps/chosen": -5.0278239250183105, |
| "logps/rejected": -57.115501403808594, |
| "loss": 0.5296419262886047, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.3394710123538971, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.223480224609375, |
| "rewards/margins": 4.145529270172119, |
| "rewards/rejected": -3.9220495223999023, |
| "step": 197, |
| "train_speed(iter/s)": 0.011233 |
| }, |
| { |
| "epoch": 0.49795661741590697, |
| "grad_norm": 4.113004207611084, |
| "learning_rate": 0.0001927426454655627, |
| "logits/chosen": -0.35911667346954346, |
| "logits/rejected": -0.5175841450691223, |
| "logps/chosen": -7.666455268859863, |
| "logps/rejected": -67.4910659790039, |
| "loss": 0.5694496035575867, |
| "memory(GiB)": 44.38, |
| "nll_loss": 0.4178715944290161, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": -0.04037248343229294, |
| "rewards/margins": 4.807923793792725, |
| "rewards/rejected": -4.848296165466309, |
| "step": 198, |
| "train_speed(iter/s)": 0.011233 |
| }, |
| { |
| "epoch": 0.5004715498270984, |
| "grad_norm": 0.9368858933448792, |
| "learning_rate": 0.0001926383998224377, |
| "logits/chosen": -0.3456733524799347, |
| "logits/rejected": -0.5820738077163696, |
| "logps/chosen": -1.7521214485168457, |
| "logps/rejected": -69.5865249633789, |
| "loss": 0.225211039185524, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.13497470319271088, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.19091293215751648, |
| "rewards/margins": 5.2458882331848145, |
| "rewards/rejected": -5.0549750328063965, |
| "step": 199, |
| "train_speed(iter/s)": 0.011233 |
| }, |
| { |
| "epoch": 0.5029864822382899, |
| "grad_norm": 2.017502784729004, |
| "learning_rate": 0.0001925334394109835, |
| "logits/chosen": -0.34290656447410583, |
| "logits/rejected": -0.5616070032119751, |
| "logps/chosen": -5.75649881362915, |
| "logps/rejected": -66.36112213134766, |
| "loss": 0.5342864990234375, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3393324017524719, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": -0.017528314143419266, |
| "rewards/margins": 4.61277437210083, |
| "rewards/rejected": -4.630302906036377, |
| "step": 200, |
| "train_speed(iter/s)": 0.011234 |
| }, |
| { |
| "epoch": 0.5055014146494813, |
| "grad_norm": 11.226442337036133, |
| "learning_rate": 0.00019242776504104118, |
| "logits/chosen": -0.35404524207115173, |
| "logits/rejected": -0.5164979696273804, |
| "logps/chosen": -6.239109992980957, |
| "logps/rejected": -57.19633102416992, |
| "loss": 0.751146674156189, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.5300025939941406, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.03473217412829399, |
| "rewards/margins": 4.055646896362305, |
| "rewards/rejected": -4.020914554595947, |
| "step": 201, |
| "train_speed(iter/s)": 0.011223 |
| }, |
| { |
| "epoch": 0.5080163470606728, |
| "grad_norm": 2.073298454284668, |
| "learning_rate": 0.00019232137752796044, |
| "logits/chosen": -0.4284801483154297, |
| "logits/rejected": -0.5613614916801453, |
| "logps/chosen": -4.676477909088135, |
| "logps/rejected": -53.5533447265625, |
| "loss": 0.6112902164459229, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.47125840187072754, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.11576966941356659, |
| "rewards/margins": 3.918217420578003, |
| "rewards/rejected": -3.80244779586792, |
| "step": 202, |
| "train_speed(iter/s)": 0.011224 |
| }, |
| { |
| "epoch": 0.5105312794718642, |
| "grad_norm": 1.5557101964950562, |
| "learning_rate": 0.00019221427769259333, |
| "logits/chosen": -0.34159645438194275, |
| "logits/rejected": -0.539400577545166, |
| "logps/chosen": -3.861686944961548, |
| "logps/rejected": -61.914703369140625, |
| "loss": 0.40771356225013733, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.29954829812049866, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.2123047411441803, |
| "rewards/margins": 4.397878646850586, |
| "rewards/rejected": -4.185573577880859, |
| "step": 203, |
| "train_speed(iter/s)": 0.011224 |
| }, |
| { |
| "epoch": 0.5130462118830557, |
| "grad_norm": 9.60893726348877, |
| "learning_rate": 0.00019210646636128807, |
| "logits/chosen": -0.37730276584625244, |
| "logits/rejected": -0.4876512885093689, |
| "logps/chosen": -4.578537464141846, |
| "logps/rejected": -47.36624526977539, |
| "loss": 0.45369648933410645, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.274221271276474, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.08797872066497803, |
| "rewards/margins": 3.566829204559326, |
| "rewards/rejected": -3.4788498878479004, |
| "step": 204, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.515561144294247, |
| "grad_norm": 1.5941282510757446, |
| "learning_rate": 0.00019199794436588243, |
| "logits/chosen": -0.27956530451774597, |
| "logits/rejected": -0.4699462652206421, |
| "logps/chosen": -7.073207378387451, |
| "logps/rejected": -68.29771423339844, |
| "loss": 0.3854275047779083, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.2786342203617096, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.12901465594768524, |
| "rewards/margins": 4.810124397277832, |
| "rewards/rejected": -4.68110990524292, |
| "step": 205, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.5180760767054385, |
| "grad_norm": 5.089592456817627, |
| "learning_rate": 0.00019188871254369752, |
| "logits/chosen": -0.31783169507980347, |
| "logits/rejected": -0.427703857421875, |
| "logps/chosen": -5.960029602050781, |
| "logps/rejected": -43.00883102416992, |
| "loss": 0.8745622634887695, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.5852820873260498, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": -0.11267540603876114, |
| "rewards/margins": 2.461634635925293, |
| "rewards/rejected": -2.574310064315796, |
| "step": 206, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.52059100911663, |
| "grad_norm": 2.929906129837036, |
| "learning_rate": 0.00019177877173753128, |
| "logits/chosen": -0.35540899634361267, |
| "logits/rejected": -0.4668577313423157, |
| "logps/chosen": -5.586899757385254, |
| "logps/rejected": -46.6971435546875, |
| "loss": 0.5985509753227234, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3464246988296509, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": -0.003932179883122444, |
| "rewards/margins": 3.3567466735839844, |
| "rewards/rejected": -3.3606786727905273, |
| "step": 207, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.5231059415278214, |
| "grad_norm": 1.8040342330932617, |
| "learning_rate": 0.00019166812279565178, |
| "logits/chosen": -0.3284756541252136, |
| "logits/rejected": -0.43804702162742615, |
| "logps/chosen": -5.879787445068359, |
| "logps/rejected": -52.28423309326172, |
| "loss": 0.6572303175926208, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.46364596486091614, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.10764454305171967, |
| "rewards/margins": 3.84014892578125, |
| "rewards/rejected": -3.732503890991211, |
| "step": 208, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.5256208739390129, |
| "grad_norm": 2.197678565979004, |
| "learning_rate": 0.000191556766571791, |
| "logits/chosen": -0.2658138871192932, |
| "logits/rejected": -0.4723971486091614, |
| "logps/chosen": -6.082084655761719, |
| "logps/rejected": -70.72124481201172, |
| "loss": 0.563379168510437, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.4301711916923523, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": -0.03504669666290283, |
| "rewards/margins": 4.98071813583374, |
| "rewards/rejected": -5.0157647132873535, |
| "step": 209, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.5281358063502043, |
| "grad_norm": 1.8066035509109497, |
| "learning_rate": 0.000191444703925138, |
| "logits/chosen": -0.266013503074646, |
| "logits/rejected": -0.4869195520877838, |
| "logps/chosen": -3.5636188983917236, |
| "logps/rejected": -65.75146484375, |
| "loss": 0.41913098096847534, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.29366493225097656, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.20083719491958618, |
| "rewards/margins": 4.579287052154541, |
| "rewards/rejected": -4.3784499168396, |
| "step": 210, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.5306507387613958, |
| "grad_norm": 2.058502197265625, |
| "learning_rate": 0.00019133193572033242, |
| "logits/chosen": -0.2633608877658844, |
| "logits/rejected": -0.4534919857978821, |
| "logps/chosen": -5.140444278717041, |
| "logps/rejected": -65.33726501464844, |
| "loss": 0.4311324954032898, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.25075870752334595, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": -0.013513857498764992, |
| "rewards/margins": 4.880782127380371, |
| "rewards/rejected": -4.894296169281006, |
| "step": 211, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.5331656711725873, |
| "grad_norm": 4.458026885986328, |
| "learning_rate": 0.00019121846282745778, |
| "logits/chosen": -0.31052568554878235, |
| "logits/rejected": -0.40828073024749756, |
| "logps/chosen": -6.845982074737549, |
| "logps/rejected": -55.935951232910156, |
| "loss": 0.6287424564361572, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.47837764024734497, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": -0.0341886430978775, |
| "rewards/margins": 4.157693862915039, |
| "rewards/rejected": -4.191883087158203, |
| "step": 212, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.5356806035837787, |
| "grad_norm": 1.700737476348877, |
| "learning_rate": 0.00019110428612203464, |
| "logits/chosen": -0.3173929452896118, |
| "logits/rejected": -0.49177926778793335, |
| "logps/chosen": -6.933238506317139, |
| "logps/rejected": -63.277774810791016, |
| "loss": 0.48178917169570923, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.32791826128959656, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.009786809794604778, |
| "rewards/margins": 4.001126289367676, |
| "rewards/rejected": -3.991339683532715, |
| "step": 213, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.5381955359949702, |
| "grad_norm": 2.141183614730835, |
| "learning_rate": 0.00019098940648501405, |
| "logits/chosen": -0.34126630425453186, |
| "logits/rejected": -0.5091477036476135, |
| "logps/chosen": -2.5000686645507812, |
| "logps/rejected": -56.68462371826172, |
| "loss": 0.26290345191955566, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.13039958477020264, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.0922369658946991, |
| "rewards/margins": 4.214053153991699, |
| "rewards/rejected": -4.1218156814575195, |
| "step": 214, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.5407104684061615, |
| "grad_norm": 1.0281932353973389, |
| "learning_rate": 0.0001908738248027706, |
| "logits/chosen": -0.31923872232437134, |
| "logits/rejected": -0.5267022252082825, |
| "logps/chosen": -3.376938819885254, |
| "logps/rejected": -68.53611755371094, |
| "loss": 0.3598852753639221, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.2368268519639969, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.13397309184074402, |
| "rewards/margins": 5.190869331359863, |
| "rewards/rejected": -5.056896209716797, |
| "step": 215, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.543225400817353, |
| "grad_norm": 1.979490876197815, |
| "learning_rate": 0.00019075754196709572, |
| "logits/chosen": -0.3671177327632904, |
| "logits/rejected": -0.5938350558280945, |
| "logps/chosen": -2.393630266189575, |
| "logps/rejected": -76.2723388671875, |
| "loss": 0.3168295919895172, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.20362113416194916, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.1339578777551651, |
| "rewards/margins": 5.975349426269531, |
| "rewards/rejected": -5.8413920402526855, |
| "step": 216, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.5457403332285444, |
| "grad_norm": 7.617611408233643, |
| "learning_rate": 0.00019064055887519062, |
| "logits/chosen": -0.4243953227996826, |
| "logits/rejected": -0.5465304851531982, |
| "logps/chosen": -8.081028938293457, |
| "logps/rejected": -70.03741455078125, |
| "loss": 0.7748145461082458, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.5802915096282959, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": -0.02728523313999176, |
| "rewards/margins": 5.3238701820373535, |
| "rewards/rejected": -5.3511552810668945, |
| "step": 217, |
| "train_speed(iter/s)": 0.011227 |
| }, |
| { |
| "epoch": 0.5482552656397359, |
| "grad_norm": 2.162104845046997, |
| "learning_rate": 0.00019052287642965952, |
| "logits/chosen": -0.40015673637390137, |
| "logits/rejected": -0.5828264355659485, |
| "logps/chosen": -5.614627838134766, |
| "logps/rejected": -72.79359436035156, |
| "loss": 0.4646216928958893, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3376343548297882, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.10579778999090195, |
| "rewards/margins": 5.431089878082275, |
| "rewards/rejected": -5.325291633605957, |
| "step": 218, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.5507701980509274, |
| "grad_norm": 7.270425319671631, |
| "learning_rate": 0.00019040449553850257, |
| "logits/chosen": -0.4019389748573303, |
| "logits/rejected": -0.6102054715156555, |
| "logps/chosen": -8.833084106445312, |
| "logps/rejected": -68.63448333740234, |
| "loss": 0.931887686252594, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.6732166409492493, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": -0.29061418771743774, |
| "rewards/margins": 4.946336269378662, |
| "rewards/rejected": -5.236949920654297, |
| "step": 219, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.5532851304621188, |
| "grad_norm": 1.4706538915634155, |
| "learning_rate": 0.000190285417115109, |
| "logits/chosen": -0.44927898049354553, |
| "logits/rejected": -0.6523910164833069, |
| "logps/chosen": -6.016222953796387, |
| "logps/rejected": -71.89757537841797, |
| "loss": 0.5478033423423767, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.45914456248283386, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.15853077173233032, |
| "rewards/margins": 5.350086212158203, |
| "rewards/rejected": -5.191555500030518, |
| "step": 220, |
| "train_speed(iter/s)": 0.011227 |
| }, |
| { |
| "epoch": 0.5558000628733103, |
| "grad_norm": 4.954250812530518, |
| "learning_rate": 0.00019016564207824992, |
| "logits/chosen": -0.49154138565063477, |
| "logits/rejected": -0.5963756442070007, |
| "logps/chosen": -6.144622325897217, |
| "logps/rejected": -47.65474319458008, |
| "loss": 0.753817081451416, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.5517919659614563, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": -0.045755282044410706, |
| "rewards/margins": 3.4072749614715576, |
| "rewards/rejected": -3.4530303478240967, |
| "step": 221, |
| "train_speed(iter/s)": 0.011227 |
| }, |
| { |
| "epoch": 0.5583149952845017, |
| "grad_norm": 20.300432205200195, |
| "learning_rate": 0.00019004517135207127, |
| "logits/chosen": -0.4070438742637634, |
| "logits/rejected": -0.6205348372459412, |
| "logps/chosen": -4.287306308746338, |
| "logps/rejected": -71.27021789550781, |
| "loss": 0.3889833390712738, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.2950345575809479, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.24340416491031647, |
| "rewards/margins": 5.386775493621826, |
| "rewards/rejected": -5.143371105194092, |
| "step": 222, |
| "train_speed(iter/s)": 0.011227 |
| }, |
| { |
| "epoch": 0.5608299276956932, |
| "grad_norm": 4.125121116638184, |
| "learning_rate": 0.00018992400586608676, |
| "logits/chosen": -0.39273932576179504, |
| "logits/rejected": -0.6418203115463257, |
| "logps/chosen": -2.4810829162597656, |
| "logps/rejected": -68.2148208618164, |
| "loss": 0.44946739077568054, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.2778445780277252, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": -0.022916745394468307, |
| "rewards/margins": 4.892718315124512, |
| "rewards/rejected": -4.915634632110596, |
| "step": 223, |
| "train_speed(iter/s)": 0.011227 |
| }, |
| { |
| "epoch": 0.5633448601068847, |
| "grad_norm": 1.3127343654632568, |
| "learning_rate": 0.00018980214655517057, |
| "logits/chosen": -0.3633681833744049, |
| "logits/rejected": -0.6210101246833801, |
| "logps/chosen": -2.5004661083221436, |
| "logps/rejected": -63.47230911254883, |
| "loss": 0.2738821506500244, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.1929439902305603, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.16036228835582733, |
| "rewards/margins": 4.588406085968018, |
| "rewards/rejected": -4.428044319152832, |
| "step": 224, |
| "train_speed(iter/s)": 0.011227 |
| }, |
| { |
| "epoch": 0.565859792518076, |
| "grad_norm": 1.8078713417053223, |
| "learning_rate": 0.00018967959435955026, |
| "logits/chosen": -0.401949405670166, |
| "logits/rejected": -0.654238224029541, |
| "logps/chosen": -2.999825954437256, |
| "logps/rejected": -78.48786926269531, |
| "loss": 0.30304455757141113, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.22698336839675903, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.11030103266239166, |
| "rewards/margins": 6.056008338928223, |
| "rewards/rejected": -5.945706844329834, |
| "step": 225, |
| "train_speed(iter/s)": 0.011227 |
| }, |
| { |
| "epoch": 0.5683747249292675, |
| "grad_norm": 1.1858668327331543, |
| "learning_rate": 0.0001895563502247995, |
| "logits/chosen": -0.42564502358436584, |
| "logits/rejected": -0.617318868637085, |
| "logps/chosen": -4.143329620361328, |
| "logps/rejected": -63.9769287109375, |
| "loss": 0.4845999479293823, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3030940592288971, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.05418945848941803, |
| "rewards/margins": 4.7669267654418945, |
| "rewards/rejected": -4.712737083435059, |
| "step": 226, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.5708896573404589, |
| "grad_norm": 10.818222045898438, |
| "learning_rate": 0.00018943241510183063, |
| "logits/chosen": -0.4244062006473541, |
| "logits/rejected": -0.5733806490898132, |
| "logps/chosen": -6.869604587554932, |
| "logps/rejected": -59.63373565673828, |
| "loss": 0.5700305700302124, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.42680811882019043, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.11073963344097137, |
| "rewards/margins": 4.200588226318359, |
| "rewards/rejected": -4.089848518371582, |
| "step": 227, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.5734045897516504, |
| "grad_norm": 1.6835912466049194, |
| "learning_rate": 0.00018930778994688757, |
| "logits/chosen": -0.43102747201919556, |
| "logits/rejected": -0.5742402076721191, |
| "logps/chosen": -5.771162986755371, |
| "logps/rejected": -63.63447952270508, |
| "loss": 0.5969828963279724, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.43208059668540955, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.05310658738017082, |
| "rewards/margins": 4.736733436584473, |
| "rewards/rejected": -4.683626651763916, |
| "step": 228, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.5759195221628419, |
| "grad_norm": 11.73387336730957, |
| "learning_rate": 0.00018918247572153823, |
| "logits/chosen": -0.40985164046287537, |
| "logits/rejected": -0.5588063597679138, |
| "logps/chosen": -4.359460830688477, |
| "logps/rejected": -66.97330474853516, |
| "loss": 0.4700680375099182, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.352486252784729, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.08524496108293533, |
| "rewards/margins": 5.1315016746521, |
| "rewards/rejected": -5.046257019042969, |
| "step": 229, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.5784344545740333, |
| "grad_norm": 3.2223124504089355, |
| "learning_rate": 0.0001890564733926672, |
| "logits/chosen": -0.28104835748672485, |
| "logits/rejected": -0.4876455068588257, |
| "logps/chosen": -10.071537017822266, |
| "logps/rejected": -77.56631469726562, |
| "loss": 0.5610992908477783, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.38141241669654846, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": -0.04872121661901474, |
| "rewards/margins": 5.269710063934326, |
| "rewards/rejected": -5.3184309005737305, |
| "step": 230, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.5809493869852248, |
| "grad_norm": 2.0458524227142334, |
| "learning_rate": 0.00018892978393246818, |
| "logits/chosen": -0.43532639741897583, |
| "logits/rejected": -0.4986593723297119, |
| "logps/chosen": -9.826902389526367, |
| "logps/rejected": -54.27751541137695, |
| "loss": 0.5817813873291016, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3644365966320038, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.17297013103961945, |
| "rewards/margins": 4.145596981048584, |
| "rewards/rejected": -3.972626209259033, |
| "step": 231, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.5834643193964162, |
| "grad_norm": 1.3154174089431763, |
| "learning_rate": 0.00018880240831843666, |
| "logits/chosen": -0.3312157690525055, |
| "logits/rejected": -0.538334310054779, |
| "logps/chosen": -7.209171295166016, |
| "logps/rejected": -73.7807846069336, |
| "loss": 0.4854442775249481, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.35912996530532837, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.1784784197807312, |
| "rewards/margins": 5.071676254272461, |
| "rewards/rejected": -4.893198013305664, |
| "step": 232, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.5859792518076077, |
| "grad_norm": 2.2449073791503906, |
| "learning_rate": 0.00018867434753336223, |
| "logits/chosen": -0.4506746828556061, |
| "logits/rejected": -0.5418546795845032, |
| "logps/chosen": -6.671032428741455, |
| "logps/rejected": -43.13252639770508, |
| "loss": 0.6598604917526245, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.4920580983161926, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.15326479077339172, |
| "rewards/margins": 3.1810433864593506, |
| "rewards/rejected": -3.0277788639068604, |
| "step": 233, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.5884941842187991, |
| "grad_norm": 2.0205371379852295, |
| "learning_rate": 0.000188545602565321, |
| "logits/chosen": -0.44379571080207825, |
| "logits/rejected": -0.5399007797241211, |
| "logps/chosen": -6.668996810913086, |
| "logps/rejected": -44.872074127197266, |
| "loss": 0.47623366117477417, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3232463002204895, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.21571332216262817, |
| "rewards/margins": 3.2807154655456543, |
| "rewards/rejected": -3.065002202987671, |
| "step": 234, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.5910091166299906, |
| "grad_norm": 2.841298818588257, |
| "learning_rate": 0.0001884161744076681, |
| "logits/chosen": -0.33942893147468567, |
| "logits/rejected": -0.5364092588424683, |
| "logps/chosen": -5.104942321777344, |
| "logps/rejected": -50.68601989746094, |
| "loss": 0.5965795516967773, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.4035502076148987, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.029007025063037872, |
| "rewards/margins": 3.369378089904785, |
| "rewards/rejected": -3.3403711318969727, |
| "step": 235, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.5935240490411821, |
| "grad_norm": 1.2584537267684937, |
| "learning_rate": 0.00018828606405902986, |
| "logits/chosen": -0.36284250020980835, |
| "logits/rejected": -0.5811104774475098, |
| "logps/chosen": -2.7690603733062744, |
| "logps/rejected": -57.4227294921875, |
| "loss": 0.287708044052124, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.19668889045715332, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.1330767720937729, |
| "rewards/margins": 4.162973880767822, |
| "rewards/rejected": -4.029897212982178, |
| "step": 236, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.5960389814523734, |
| "grad_norm": 1.2746140956878662, |
| "learning_rate": 0.00018815527252329624, |
| "logits/chosen": -0.43088293075561523, |
| "logits/rejected": -0.5826693177223206, |
| "logps/chosen": -6.570635795593262, |
| "logps/rejected": -57.39180374145508, |
| "loss": 0.6008946895599365, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.4163006544113159, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.07822921127080917, |
| "rewards/margins": 4.272268772125244, |
| "rewards/rejected": -4.194039821624756, |
| "step": 237, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.5985539138635649, |
| "grad_norm": 2.0402894020080566, |
| "learning_rate": 0.00018802380080961296, |
| "logits/chosen": -0.3829416036605835, |
| "logits/rejected": -0.6285839676856995, |
| "logps/chosen": -2.684177875518799, |
| "logps/rejected": -72.15119934082031, |
| "loss": 0.38798508048057556, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.28602004051208496, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.056711360812187195, |
| "rewards/margins": 5.393987655639648, |
| "rewards/rejected": -5.337275981903076, |
| "step": 238, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.6010688462747563, |
| "grad_norm": 1.6787519454956055, |
| "learning_rate": 0.00018789164993237382, |
| "logits/chosen": -0.4566512107849121, |
| "logits/rejected": -0.6156482100486755, |
| "logps/chosen": -4.155914783477783, |
| "logps/rejected": -73.04944610595703, |
| "loss": 0.37050700187683105, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.2093135416507721, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.13006967306137085, |
| "rewards/margins": 5.779219150543213, |
| "rewards/rejected": -5.649148941040039, |
| "step": 239, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.6035837786859478, |
| "grad_norm": 2.6302237510681152, |
| "learning_rate": 0.0001877588209112128, |
| "logits/chosen": -0.37822332978248596, |
| "logits/rejected": -0.6501820087432861, |
| "logps/chosen": -3.1933681964874268, |
| "logps/rejected": -80.41326904296875, |
| "loss": 0.43696874380111694, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.2772809863090515, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.16505186259746552, |
| "rewards/margins": 6.543651103973389, |
| "rewards/rejected": -6.378600120544434, |
| "step": 240, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.6060987110971393, |
| "grad_norm": 1.6916310787200928, |
| "learning_rate": 0.00018762531477099626, |
| "logits/chosen": -0.29892975091934204, |
| "logits/rejected": -0.6198312640190125, |
| "logps/chosen": -5.560736656188965, |
| "logps/rejected": -102.83201599121094, |
| "loss": 0.4650719165802002, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.33948570489883423, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.010243753902614117, |
| "rewards/margins": 7.854136943817139, |
| "rewards/rejected": -7.843893051147461, |
| "step": 241, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.6086136435083307, |
| "grad_norm": 5.208255290985107, |
| "learning_rate": 0.00018749113254181498, |
| "logits/chosen": -0.5256325006484985, |
| "logits/rejected": -0.7164933681488037, |
| "logps/chosen": -2.9781463146209717, |
| "logps/rejected": -80.5984878540039, |
| "loss": 0.5060344338417053, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3545001149177551, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.0441756509244442, |
| "rewards/margins": 7.027956485748291, |
| "rewards/rejected": -6.983780860900879, |
| "step": 242, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.6111285759195222, |
| "grad_norm": 2.999555826187134, |
| "learning_rate": 0.0001873562752589762, |
| "logits/chosen": -0.4497723877429962, |
| "logits/rejected": -0.6424503326416016, |
| "logps/chosen": -9.136008262634277, |
| "logps/rejected": -83.97636413574219, |
| "loss": 0.5317915678024292, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.45959895849227905, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": -0.0020806342363357544, |
| "rewards/margins": 6.646152496337891, |
| "rewards/rejected": -6.648233890533447, |
| "step": 243, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.6136435083307136, |
| "grad_norm": 1.6152504682540894, |
| "learning_rate": 0.00018722074396299566, |
| "logits/chosen": -0.4504960775375366, |
| "logits/rejected": -0.6728327870368958, |
| "logps/chosen": -8.307985305786133, |
| "logps/rejected": -92.50747680664062, |
| "loss": 0.3881627023220062, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.27829721570014954, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.1872478723526001, |
| "rewards/margins": 7.5645575523376465, |
| "rewards/rejected": -7.377309799194336, |
| "step": 244, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.6161584407419051, |
| "grad_norm": 1.9773950576782227, |
| "learning_rate": 0.00018708453969958958, |
| "logits/chosen": -0.48630112409591675, |
| "logits/rejected": -0.6566104888916016, |
| "logps/chosen": -6.018984317779541, |
| "logps/rejected": -62.95851516723633, |
| "loss": 0.6716858744621277, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.48807603120803833, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.0030519720166921616, |
| "rewards/margins": 4.69732141494751, |
| "rewards/rejected": -4.694269180297852, |
| "step": 245, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.6186733731530966, |
| "grad_norm": 2.007908821105957, |
| "learning_rate": 0.00018694766351966667, |
| "logits/chosen": -0.4003494679927826, |
| "logits/rejected": -0.6231962442398071, |
| "logps/chosen": -6.337024688720703, |
| "logps/rejected": -75.96829223632812, |
| "loss": 0.49646520614624023, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.39788398146629333, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.2538176476955414, |
| "rewards/margins": 5.768869876861572, |
| "rewards/rejected": -5.515052318572998, |
| "step": 246, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.621188305564288, |
| "grad_norm": 1.3329335451126099, |
| "learning_rate": 0.00018681011647931974, |
| "logits/chosen": -0.35181480646133423, |
| "logits/rejected": -0.6176152229309082, |
| "logps/chosen": -5.239382266998291, |
| "logps/rejected": -74.54182434082031, |
| "loss": 0.5128018856048584, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3926093578338623, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.14708997309207916, |
| "rewards/margins": 5.654610633850098, |
| "rewards/rejected": -5.5075201988220215, |
| "step": 247, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.6237032379754794, |
| "grad_norm": 2.318981170654297, |
| "learning_rate": 0.00018667189963981793, |
| "logits/chosen": -0.4104291498661041, |
| "logits/rejected": -0.6699872016906738, |
| "logps/chosen": -4.179399013519287, |
| "logps/rejected": -62.75163269042969, |
| "loss": 0.595816969871521, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.4384332001209259, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.17818482220172882, |
| "rewards/margins": 4.639157772064209, |
| "rewards/rejected": -4.460972309112549, |
| "step": 248, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.6262181703866708, |
| "grad_norm": 1.3054991960525513, |
| "learning_rate": 0.00018653301406759825, |
| "logits/chosen": -0.45266249775886536, |
| "logits/rejected": -0.7092356085777283, |
| "logps/chosen": -4.101914882659912, |
| "logps/rejected": -68.14440155029297, |
| "loss": 0.38595661520957947, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.2959481179714203, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.18340018391609192, |
| "rewards/margins": 5.416258335113525, |
| "rewards/rejected": -5.232857704162598, |
| "step": 249, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.6287331027978623, |
| "grad_norm": 2.184175968170166, |
| "learning_rate": 0.00018639346083425748, |
| "logits/chosen": -0.5093356370925903, |
| "logits/rejected": -0.6794995665550232, |
| "logps/chosen": -8.688965797424316, |
| "logps/rejected": -66.35594940185547, |
| "loss": 0.8350189328193665, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.6493321657180786, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.0820498839020729, |
| "rewards/margins": 5.020396709442139, |
| "rewards/rejected": -4.9383463859558105, |
| "step": 250, |
| "train_speed(iter/s)": 0.011231 |
| }, |
| { |
| "epoch": 0.6312480352090537, |
| "grad_norm": 1.0683221817016602, |
| "learning_rate": 0.00018625324101654377, |
| "logits/chosen": -0.37649020552635193, |
| "logits/rejected": -0.6572071313858032, |
| "logps/chosen": -4.348738193511963, |
| "logps/rejected": -87.71903228759766, |
| "loss": 0.40204933285713196, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3149075210094452, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.15514017641544342, |
| "rewards/margins": 7.00824499130249, |
| "rewards/rejected": -6.853104591369629, |
| "step": 251, |
| "train_speed(iter/s)": 0.011222 |
| }, |
| { |
| "epoch": 0.6337629676202452, |
| "grad_norm": 2.92044997215271, |
| "learning_rate": 0.00018611235569634854, |
| "logits/chosen": -0.43412554264068604, |
| "logits/rejected": -0.6498897075653076, |
| "logps/chosen": -5.39566707611084, |
| "logps/rejected": -92.27975463867188, |
| "loss": 0.3511677384376526, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.2868626117706299, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.19005966186523438, |
| "rewards/margins": 7.602224349975586, |
| "rewards/rejected": -7.412164688110352, |
| "step": 252, |
| "train_speed(iter/s)": 0.011223 |
| }, |
| { |
| "epoch": 0.6362779000314367, |
| "grad_norm": 6.411540508270264, |
| "learning_rate": 0.00018597080596069793, |
| "logits/chosen": -0.5317556262016296, |
| "logits/rejected": -0.7095096111297607, |
| "logps/chosen": -9.501699447631836, |
| "logps/rejected": -75.72296142578125, |
| "loss": 0.7277939319610596, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.5560886859893799, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.10351304709911346, |
| "rewards/margins": 6.114856719970703, |
| "rewards/rejected": -6.011343479156494, |
| "step": 253, |
| "train_speed(iter/s)": 0.011223 |
| }, |
| { |
| "epoch": 0.6387928324426281, |
| "grad_norm": 1.3415000438690186, |
| "learning_rate": 0.00018582859290174452, |
| "logits/chosen": -0.5152278542518616, |
| "logits/rejected": -0.6576297283172607, |
| "logps/chosen": -4.799291133880615, |
| "logps/rejected": -65.77213287353516, |
| "loss": 0.5212017893791199, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.37971436977386475, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.1788114607334137, |
| "rewards/margins": 5.149197578430176, |
| "rewards/rejected": -4.970386028289795, |
| "step": 254, |
| "train_speed(iter/s)": 0.011223 |
| }, |
| { |
| "epoch": 0.6413077648538196, |
| "grad_norm": 2.0600571632385254, |
| "learning_rate": 0.00018568571761675893, |
| "logits/chosen": -0.5194295644760132, |
| "logits/rejected": -0.6636701822280884, |
| "logps/chosen": -6.026893615722656, |
| "logps/rejected": -72.3927993774414, |
| "loss": 0.6823182106018066, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.4406730830669403, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": -0.013813409954309464, |
| "rewards/margins": 5.530622482299805, |
| "rewards/rejected": -5.544435501098633, |
| "step": 255, |
| "train_speed(iter/s)": 0.011223 |
| }, |
| { |
| "epoch": 0.643822697265011, |
| "grad_norm": 1.9565048217773438, |
| "learning_rate": 0.00018554218120812123, |
| "logits/chosen": -0.481246680021286, |
| "logits/rejected": -0.6363787651062012, |
| "logps/chosen": -9.490486145019531, |
| "logps/rejected": -75.51252746582031, |
| "loss": 0.6278063058853149, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.4966178238391876, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.2284890115261078, |
| "rewards/margins": 5.836487293243408, |
| "rewards/rejected": -5.607998847961426, |
| "step": 256, |
| "train_speed(iter/s)": 0.011223 |
| }, |
| { |
| "epoch": 0.6463376296762025, |
| "grad_norm": 1.4044089317321777, |
| "learning_rate": 0.00018539798478331253, |
| "logits/chosen": -0.4915826916694641, |
| "logits/rejected": -0.6845091581344604, |
| "logps/chosen": -5.873336315155029, |
| "logps/rejected": -88.4930419921875, |
| "loss": 0.44303250312805176, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3297483026981354, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.1546323597431183, |
| "rewards/margins": 7.295997142791748, |
| "rewards/rejected": -7.141365051269531, |
| "step": 257, |
| "train_speed(iter/s)": 0.011223 |
| }, |
| { |
| "epoch": 0.648852562087394, |
| "grad_norm": 3.9914138317108154, |
| "learning_rate": 0.00018525312945490648, |
| "logits/chosen": -0.5438416004180908, |
| "logits/rejected": -0.6368093490600586, |
| "logps/chosen": -8.48979377746582, |
| "logps/rejected": -51.59290313720703, |
| "loss": 0.8118419647216797, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.5555844306945801, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.0014183670282363892, |
| "rewards/margins": 3.946876049041748, |
| "rewards/rejected": -3.9454574584960938, |
| "step": 258, |
| "train_speed(iter/s)": 0.011224 |
| }, |
| { |
| "epoch": 0.6513674944985853, |
| "grad_norm": 1.5120611190795898, |
| "learning_rate": 0.0001851076163405605, |
| "logits/chosen": -0.4779820442199707, |
| "logits/rejected": -0.6549505591392517, |
| "logps/chosen": -5.458694934844971, |
| "logps/rejected": -67.10589599609375, |
| "loss": 0.5383408069610596, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.34656140208244324, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.06555496156215668, |
| "rewards/margins": 5.2232513427734375, |
| "rewards/rejected": -5.157696723937988, |
| "step": 259, |
| "train_speed(iter/s)": 0.011224 |
| }, |
| { |
| "epoch": 0.6538824269097768, |
| "grad_norm": 1.8427090644836426, |
| "learning_rate": 0.0001849614465630074, |
| "logits/chosen": -0.5466744303703308, |
| "logits/rejected": -0.7123967409133911, |
| "logps/chosen": -4.491105079650879, |
| "logps/rejected": -75.23402404785156, |
| "loss": 0.43553516268730164, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.29759523272514343, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.1540081650018692, |
| "rewards/margins": 6.407083988189697, |
| "rewards/rejected": -6.25307559967041, |
| "step": 260, |
| "train_speed(iter/s)": 0.011224 |
| }, |
| { |
| "epoch": 0.6563973593209682, |
| "grad_norm": 1.5477027893066406, |
| "learning_rate": 0.00018481462125004647, |
| "logits/chosen": -0.493845134973526, |
| "logits/rejected": -0.687497615814209, |
| "logps/chosen": -6.834686279296875, |
| "logps/rejected": -85.95507049560547, |
| "loss": 0.5149559378623962, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.2903035581111908, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": -0.049691248685121536, |
| "rewards/margins": 6.8722639083862305, |
| "rewards/rejected": -6.9219560623168945, |
| "step": 261, |
| "train_speed(iter/s)": 0.011224 |
| }, |
| { |
| "epoch": 0.6589122917321597, |
| "grad_norm": 2.615581512451172, |
| "learning_rate": 0.00018466714153453503, |
| "logits/chosen": -0.402892142534256, |
| "logits/rejected": -0.6777759194374084, |
| "logps/chosen": -3.014004945755005, |
| "logps/rejected": -93.15167236328125, |
| "loss": 0.34462472796440125, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.2536306083202362, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.15657053887844086, |
| "rewards/margins": 7.013685703277588, |
| "rewards/rejected": -6.857114791870117, |
| "step": 262, |
| "train_speed(iter/s)": 0.011224 |
| }, |
| { |
| "epoch": 0.6614272241433512, |
| "grad_norm": 3.427328586578369, |
| "learning_rate": 0.0001845190085543795, |
| "logits/chosen": -0.5253512859344482, |
| "logits/rejected": -0.7107342481613159, |
| "logps/chosen": -11.115226745605469, |
| "logps/rejected": -88.85804748535156, |
| "loss": 0.6678985953330994, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.48055583238601685, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": -0.28667983412742615, |
| "rewards/margins": 6.657105445861816, |
| "rewards/rejected": -6.943784713745117, |
| "step": 263, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.6639421565545426, |
| "grad_norm": 1.1444027423858643, |
| "learning_rate": 0.00018437022345252664, |
| "logits/chosen": -0.5300915837287903, |
| "logits/rejected": -0.7409610748291016, |
| "logps/chosen": -3.0393667221069336, |
| "logps/rejected": -97.51324462890625, |
| "loss": 0.33918118476867676, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.24477338790893555, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.08205480128526688, |
| "rewards/margins": 8.255426406860352, |
| "rewards/rejected": -8.173370361328125, |
| "step": 264, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.6664570889657341, |
| "grad_norm": 4.637787342071533, |
| "learning_rate": 0.0001842207873769548, |
| "logits/chosen": -0.5017226934432983, |
| "logits/rejected": -0.6932743787765503, |
| "logps/chosen": -5.375912189483643, |
| "logps/rejected": -72.31993865966797, |
| "loss": 0.6298449635505676, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.44052040576934814, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.06435458362102509, |
| "rewards/margins": 5.378176689147949, |
| "rewards/rejected": -5.313821792602539, |
| "step": 265, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.6689720213769255, |
| "grad_norm": 4.79957389831543, |
| "learning_rate": 0.00018407070148066513, |
| "logits/chosen": -0.426089882850647, |
| "logits/rejected": -0.639220118522644, |
| "logps/chosen": -5.063274383544922, |
| "logps/rejected": -87.9122085571289, |
| "loss": 0.4773625135421753, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3494463562965393, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.08732649683952332, |
| "rewards/margins": 7.158117294311523, |
| "rewards/rejected": -7.0707902908325195, |
| "step": 266, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.671486953788117, |
| "grad_norm": 2.3448801040649414, |
| "learning_rate": 0.00018391996692167242, |
| "logits/chosen": -0.5341528058052063, |
| "logits/rejected": -0.741336464881897, |
| "logps/chosen": -4.58453369140625, |
| "logps/rejected": -77.93905639648438, |
| "loss": 0.39634108543395996, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.26042404770851135, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.2408846765756607, |
| "rewards/margins": 6.696462154388428, |
| "rewards/rejected": -6.455577373504639, |
| "step": 267, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.6740018861993083, |
| "grad_norm": 3.913471221923828, |
| "learning_rate": 0.00018376858486299647, |
| "logits/chosen": -0.44522032141685486, |
| "logits/rejected": -0.7187605500221252, |
| "logps/chosen": -5.051987648010254, |
| "logps/rejected": -110.36135864257812, |
| "loss": 0.45356252789497375, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.32329580187797546, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.0719699114561081, |
| "rewards/margins": 9.275440216064453, |
| "rewards/rejected": -9.203469276428223, |
| "step": 268, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.6765168186104998, |
| "grad_norm": 5.869787216186523, |
| "learning_rate": 0.00018361655647265295, |
| "logits/chosen": -0.5306439399719238, |
| "logits/rejected": -0.7627276182174683, |
| "logps/chosen": -4.171728134155273, |
| "logps/rejected": -88.16104125976562, |
| "loss": 0.43114253878593445, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3357262909412384, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.06204725801944733, |
| "rewards/margins": 7.2651519775390625, |
| "rewards/rejected": -7.2031049728393555, |
| "step": 269, |
| "train_speed(iter/s)": 0.011225 |
| }, |
| { |
| "epoch": 0.6790317510216913, |
| "grad_norm": 4.243189334869385, |
| "learning_rate": 0.00018346388292364435, |
| "logits/chosen": -0.4333181083202362, |
| "logits/rejected": -0.704163670539856, |
| "logps/chosen": -2.6535372734069824, |
| "logps/rejected": -95.77774810791016, |
| "loss": 0.29697632789611816, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.17106658220291138, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.18806029856204987, |
| "rewards/margins": 7.7735371589660645, |
| "rewards/rejected": -7.585476875305176, |
| "step": 270, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.6815466834328827, |
| "grad_norm": 1.7140799760818481, |
| "learning_rate": 0.00018331056539395112, |
| "logits/chosen": -0.556128740310669, |
| "logits/rejected": -0.7013101577758789, |
| "logps/chosen": -4.00136137008667, |
| "logps/rejected": -67.00804901123047, |
| "loss": 0.5140962600708008, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3367845118045807, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.10617542266845703, |
| "rewards/margins": 5.6274027824401855, |
| "rewards/rejected": -5.5212273597717285, |
| "step": 271, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.6840616158440742, |
| "grad_norm": 1.9975121021270752, |
| "learning_rate": 0.00018315660506652232, |
| "logits/chosen": -0.5180048942565918, |
| "logits/rejected": -0.7096535563468933, |
| "logps/chosen": -4.446587562561035, |
| "logps/rejected": -89.62254333496094, |
| "loss": 0.3145523965358734, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.23890048265457153, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.19064153730869293, |
| "rewards/margins": 7.726916313171387, |
| "rewards/rejected": -7.5362749099731445, |
| "step": 272, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.6865765482552656, |
| "grad_norm": 2.6164450645446777, |
| "learning_rate": 0.00018300200312926674, |
| "logits/chosen": -0.4427982568740845, |
| "logits/rejected": -0.6760357618331909, |
| "logps/chosen": -4.68469762802124, |
| "logps/rejected": -69.42048645019531, |
| "loss": 0.6788820028305054, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.44468939304351807, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.06053057312965393, |
| "rewards/margins": 5.069634437561035, |
| "rewards/rejected": -5.0091047286987305, |
| "step": 273, |
| "train_speed(iter/s)": 0.011227 |
| }, |
| { |
| "epoch": 0.6890914806664571, |
| "grad_norm": 3.0418243408203125, |
| "learning_rate": 0.00018284676077504362, |
| "logits/chosen": -0.443393349647522, |
| "logits/rejected": -0.6204345226287842, |
| "logps/chosen": -7.827211380004883, |
| "logps/rejected": -61.0114631652832, |
| "loss": 0.6672328114509583, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.5125250816345215, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.12237226963043213, |
| "rewards/margins": 4.810492515563965, |
| "rewards/rejected": -4.688120365142822, |
| "step": 274, |
| "train_speed(iter/s)": 0.011227 |
| }, |
| { |
| "epoch": 0.6916064130776486, |
| "grad_norm": 4.901159763336182, |
| "learning_rate": 0.00018269087920165332, |
| "logits/chosen": -0.41514497995376587, |
| "logits/rejected": -0.6380784511566162, |
| "logps/chosen": -6.606781482696533, |
| "logps/rejected": -82.10425567626953, |
| "loss": 0.49194085597991943, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.33267742395401, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.15449321269989014, |
| "rewards/margins": 6.2364373207092285, |
| "rewards/rejected": -6.081944942474365, |
| "step": 275, |
| "train_speed(iter/s)": 0.011226 |
| }, |
| { |
| "epoch": 0.69412134548884, |
| "grad_norm": 1.3309578895568848, |
| "learning_rate": 0.00018253435961182845, |
| "logits/chosen": -0.5140801668167114, |
| "logits/rejected": -0.6796289086341858, |
| "logps/chosen": -5.0471296310424805, |
| "logps/rejected": -85.82859802246094, |
| "loss": 0.47967594861984253, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3782137930393219, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.17723581194877625, |
| "rewards/margins": 6.987857341766357, |
| "rewards/rejected": -6.810622215270996, |
| "step": 276, |
| "train_speed(iter/s)": 0.011227 |
| }, |
| { |
| "epoch": 0.6966362779000315, |
| "grad_norm": 1.0236581563949585, |
| "learning_rate": 0.00018237720321322409, |
| "logits/chosen": -0.42819637060165405, |
| "logits/rejected": -0.5975549221038818, |
| "logps/chosen": -5.334194183349609, |
| "logps/rejected": -66.20035552978516, |
| "loss": 0.4676276445388794, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.34695690870285034, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.38220563530921936, |
| "rewards/margins": 5.525548458099365, |
| "rewards/rejected": -5.143343448638916, |
| "step": 277, |
| "train_speed(iter/s)": 0.011227 |
| }, |
| { |
| "epoch": 0.6991512103112228, |
| "grad_norm": 2.6781225204467773, |
| "learning_rate": 0.00018221941121840892, |
| "logits/chosen": -0.49049457907676697, |
| "logits/rejected": -0.7119749188423157, |
| "logps/chosen": -3.930919885635376, |
| "logps/rejected": -84.6829833984375, |
| "loss": 0.46516090631484985, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.34264886379241943, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.15465623140335083, |
| "rewards/margins": 7.022001266479492, |
| "rewards/rejected": -6.867344856262207, |
| "step": 278, |
| "train_speed(iter/s)": 0.011227 |
| }, |
| { |
| "epoch": 0.7016661427224143, |
| "grad_norm": 0.9837477207183838, |
| "learning_rate": 0.00018206098484485563, |
| "logits/chosen": -0.4659290313720703, |
| "logits/rejected": -0.6759628653526306, |
| "logps/chosen": -3.7083301544189453, |
| "logps/rejected": -81.18896484375, |
| "loss": 0.33244359493255615, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.24541471898555756, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.05203983187675476, |
| "rewards/margins": 6.756404399871826, |
| "rewards/rejected": -6.704365253448486, |
| "step": 279, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.7041810751336058, |
| "grad_norm": 1.9367793798446655, |
| "learning_rate": 0.00018190192531493152, |
| "logits/chosen": -0.4372798502445221, |
| "logits/rejected": -0.6702994704246521, |
| "logps/chosen": -3.2311387062072754, |
| "logps/rejected": -81.85215759277344, |
| "loss": 0.3242435157299042, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.18884681165218353, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.14998643100261688, |
| "rewards/margins": 6.440362453460693, |
| "rewards/rejected": -6.290376663208008, |
| "step": 280, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.7066960075447972, |
| "grad_norm": 6.8672566413879395, |
| "learning_rate": 0.00018174223385588917, |
| "logits/chosen": -0.4230336844921112, |
| "logits/rejected": -0.6848682761192322, |
| "logps/chosen": -6.529013156890869, |
| "logps/rejected": -90.91963195800781, |
| "loss": 0.501898467540741, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3414127826690674, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.014151861891150475, |
| "rewards/margins": 6.871521472930908, |
| "rewards/rejected": -6.857369422912598, |
| "step": 281, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.7092109399559887, |
| "grad_norm": 1.8030977249145508, |
| "learning_rate": 0.00018158191169985696, |
| "logits/chosen": -0.5189124941825867, |
| "logits/rejected": -0.6720729470252991, |
| "logps/chosen": -3.5770914554595947, |
| "logps/rejected": -72.2397689819336, |
| "loss": 0.3821221888065338, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.26037099957466125, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.1488955020904541, |
| "rewards/margins": 6.099178314208984, |
| "rewards/rejected": -5.950283050537109, |
| "step": 282, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.7117258723671801, |
| "grad_norm": 1.3741241693496704, |
| "learning_rate": 0.00018142096008382942, |
| "logits/chosen": -0.504133403301239, |
| "logits/rejected": -0.7275675535202026, |
| "logps/chosen": -3.2252137660980225, |
| "logps/rejected": -85.62193298339844, |
| "loss": 0.4202941358089447, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.31953656673431396, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.163682222366333, |
| "rewards/margins": 6.74496603012085, |
| "rewards/rejected": -6.5812835693359375, |
| "step": 283, |
| "train_speed(iter/s)": 0.011228 |
| }, |
| { |
| "epoch": 0.7142408047783716, |
| "grad_norm": 2.163975954055786, |
| "learning_rate": 0.00018125938024965793, |
| "logits/chosen": -0.5000174045562744, |
| "logits/rejected": -0.6639881134033203, |
| "logps/chosen": -4.828487396240234, |
| "logps/rejected": -76.62934875488281, |
| "loss": 0.640762448310852, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.42961040139198303, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.11060743778944016, |
| "rewards/margins": 6.323296546936035, |
| "rewards/rejected": -6.21268892288208, |
| "step": 284, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.716755737189563, |
| "grad_norm": 2.45220685005188, |
| "learning_rate": 0.0001810971734440408, |
| "logits/chosen": -0.5609660744667053, |
| "logits/rejected": -0.7155238389968872, |
| "logps/chosen": -5.233462333679199, |
| "logps/rejected": -67.92847442626953, |
| "loss": 0.46715691685676575, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.31150108575820923, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.1065329983830452, |
| "rewards/margins": 5.596135139465332, |
| "rewards/rejected": -5.489602088928223, |
| "step": 285, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.7192706696007545, |
| "grad_norm": 3.306640386581421, |
| "learning_rate": 0.0001809343409185141, |
| "logits/chosen": -0.48307013511657715, |
| "logits/rejected": -0.7068489193916321, |
| "logps/chosen": -4.671525955200195, |
| "logps/rejected": -86.49360656738281, |
| "loss": 0.45381927490234375, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3168652355670929, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.32458728551864624, |
| "rewards/margins": 7.187753200531006, |
| "rewards/rejected": -6.863165378570557, |
| "step": 286, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.721785602011946, |
| "grad_norm": 8.64627742767334, |
| "learning_rate": 0.00018077088392944157, |
| "logits/chosen": -0.4658992886543274, |
| "logits/rejected": -0.6729714274406433, |
| "logps/chosen": -6.4438018798828125, |
| "logps/rejected": -103.12019348144531, |
| "loss": 0.7503845691680908, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.5230257511138916, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": -0.06617186963558197, |
| "rewards/margins": 8.38872241973877, |
| "rewards/rejected": -8.454893112182617, |
| "step": 287, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.7243005344231374, |
| "grad_norm": 13.93918514251709, |
| "learning_rate": 0.00018060680373800517, |
| "logits/chosen": -0.550601601600647, |
| "logits/rejected": -0.7022511959075928, |
| "logps/chosen": -8.245074272155762, |
| "logps/rejected": -75.76158905029297, |
| "loss": 1.1637423038482666, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.71792072057724, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": -0.2617635130882263, |
| "rewards/margins": 6.171159744262695, |
| "rewards/rejected": -6.432923316955566, |
| "step": 288, |
| "train_speed(iter/s)": 0.011229 |
| }, |
| { |
| "epoch": 0.7268154668343288, |
| "grad_norm": 0.9253904819488525, |
| "learning_rate": 0.00018044210161019536, |
| "logits/chosen": -0.557449996471405, |
| "logits/rejected": -0.7140588164329529, |
| "logps/chosen": -4.058953285217285, |
| "logps/rejected": -82.31138610839844, |
| "loss": 0.4642924666404724, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3196372389793396, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.24701666831970215, |
| "rewards/margins": 6.999866962432861, |
| "rewards/rejected": -6.75285005569458, |
| "step": 289, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.7293303992455202, |
| "grad_norm": 1.6528226137161255, |
| "learning_rate": 0.0001802767788168011, |
| "logits/chosen": -0.4495914578437805, |
| "logits/rejected": -0.6348967552185059, |
| "logps/chosen": -5.4721455574035645, |
| "logps/rejected": -72.90061950683594, |
| "loss": 0.5594840049743652, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3900570571422577, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.03378419950604439, |
| "rewards/margins": 5.539588928222656, |
| "rewards/rejected": -5.505805015563965, |
| "step": 290, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.7318453316567117, |
| "grad_norm": 2.687760353088379, |
| "learning_rate": 0.0001801108366334004, |
| "logits/chosen": -0.4720868468284607, |
| "logits/rejected": -0.7254785299301147, |
| "logps/chosen": -3.6542224884033203, |
| "logps/rejected": -90.37942504882812, |
| "loss": 0.3632267117500305, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.25571519136428833, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.04553738981485367, |
| "rewards/margins": 7.5396728515625, |
| "rewards/rejected": -7.49413537979126, |
| "step": 291, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.7343602640679032, |
| "grad_norm": 2.385871410369873, |
| "learning_rate": 0.00017994427634035015, |
| "logits/chosen": -0.43004167079925537, |
| "logits/rejected": -0.6407785415649414, |
| "logps/chosen": -5.274074554443359, |
| "logps/rejected": -73.99935913085938, |
| "loss": 0.5132104754447937, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.40467336773872375, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.04765544831752777, |
| "rewards/margins": 5.948093891143799, |
| "rewards/rejected": -5.9004387855529785, |
| "step": 292, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.7368751964790946, |
| "grad_norm": 1.4301080703735352, |
| "learning_rate": 0.00017977709922277634, |
| "logits/chosen": -0.522111713886261, |
| "logits/rejected": -0.7116501331329346, |
| "logps/chosen": -3.2741823196411133, |
| "logps/rejected": -75.16236877441406, |
| "loss": 0.30991509556770325, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.18252958357334137, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.1758219599723816, |
| "rewards/margins": 6.132888317108154, |
| "rewards/rejected": -5.957066059112549, |
| "step": 293, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.7393901288902861, |
| "grad_norm": 0.9421151876449585, |
| "learning_rate": 0.00017960930657056438, |
| "logits/chosen": -0.4752303957939148, |
| "logits/rejected": -0.763075053691864, |
| "logps/chosen": -2.069356918334961, |
| "logps/rejected": -101.09730529785156, |
| "loss": 0.273615300655365, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.1774016171693802, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.18013092875480652, |
| "rewards/margins": 8.264806747436523, |
| "rewards/rejected": -8.084675788879395, |
| "step": 294, |
| "train_speed(iter/s)": 0.01123 |
| }, |
| { |
| "epoch": 0.7419050613014775, |
| "grad_norm": 1.586992859840393, |
| "learning_rate": 0.00017944089967834875, |
| "logits/chosen": -0.5891596674919128, |
| "logits/rejected": -0.7932709455490112, |
| "logps/chosen": -4.589641094207764, |
| "logps/rejected": -86.26122283935547, |
| "loss": 0.40633922815322876, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.2850261628627777, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.16272488236427307, |
| "rewards/margins": 7.014225482940674, |
| "rewards/rejected": -6.851500511169434, |
| "step": 295, |
| "train_speed(iter/s)": 0.011231 |
| }, |
| { |
| "epoch": 0.744419993712669, |
| "grad_norm": 5.1989850997924805, |
| "learning_rate": 0.00017927187984550334, |
| "logits/chosen": -0.4999873638153076, |
| "logits/rejected": -0.7794056534767151, |
| "logps/chosen": -5.444850921630859, |
| "logps/rejected": -99.01435852050781, |
| "loss": 0.4726611077785492, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3788090646266937, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.03491847217082977, |
| "rewards/margins": 8.243888854980469, |
| "rewards/rejected": -8.208970069885254, |
| "step": 296, |
| "train_speed(iter/s)": 0.011231 |
| }, |
| { |
| "epoch": 0.7469349261238605, |
| "grad_norm": 1.32076895236969, |
| "learning_rate": 0.00017910224837613118, |
| "logits/chosen": -0.5675287246704102, |
| "logits/rejected": -0.7462685704231262, |
| "logps/chosen": -5.531588554382324, |
| "logps/rejected": -90.58869171142578, |
| "loss": 0.3903141915798187, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.2512432634830475, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.1347513198852539, |
| "rewards/margins": 7.417156219482422, |
| "rewards/rejected": -7.282405853271484, |
| "step": 297, |
| "train_speed(iter/s)": 0.011231 |
| }, |
| { |
| "epoch": 0.7494498585350519, |
| "grad_norm": 12.773048400878906, |
| "learning_rate": 0.0001789320065790546, |
| "logits/chosen": -0.5981060266494751, |
| "logits/rejected": -0.8135245442390442, |
| "logps/chosen": -6.99806547164917, |
| "logps/rejected": -108.45048522949219, |
| "loss": 0.4520961344242096, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3480715751647949, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.1965925544500351, |
| "rewards/margins": 9.141500473022461, |
| "rewards/rejected": -8.944907188415527, |
| "step": 298, |
| "train_speed(iter/s)": 0.011231 |
| }, |
| { |
| "epoch": 0.7519647909462434, |
| "grad_norm": 11.585864067077637, |
| "learning_rate": 0.00017876115576780498, |
| "logits/chosen": -0.6520665884017944, |
| "logits/rejected": -0.8114386796951294, |
| "logps/chosen": -11.475854873657227, |
| "logps/rejected": -93.8547134399414, |
| "loss": 1.136841893196106, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.9128180146217346, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": -0.3643069267272949, |
| "rewards/margins": 7.67158317565918, |
| "rewards/rejected": -8.035890579223633, |
| "step": 299, |
| "train_speed(iter/s)": 0.011231 |
| }, |
| { |
| "epoch": 0.7544797233574347, |
| "grad_norm": 10.311992645263672, |
| "learning_rate": 0.0001785896972606126, |
| "logits/chosen": -0.7280598282814026, |
| "logits/rejected": -0.9233004450798035, |
| "logps/chosen": -9.302474975585938, |
| "logps/rejected": -110.05669403076172, |
| "loss": 0.8829553723335266, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.6579189896583557, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": -0.04713385924696922, |
| "rewards/margins": 9.603901863098145, |
| "rewards/rejected": -9.651037216186523, |
| "step": 300, |
| "train_speed(iter/s)": 0.011231 |
| }, |
| { |
| "epoch": 0.7544797233574347, |
| "eval_logits/chosen": -0.6994932889938354, |
| "eval_logits/rejected": -0.9091920852661133, |
| "eval_logps/chosen": -7.593709468841553, |
| "eval_logps/rejected": -103.9007797241211, |
| "eval_loss": 0.6852853894233704, |
| "eval_nll_loss": 0.48945868015289307, |
| "eval_rewards/accuracies": 0.9375, |
| "eval_rewards/chosen": -0.08310390263795853, |
| "eval_rewards/margins": 8.748055458068848, |
| "eval_rewards/rejected": -8.831159591674805, |
| "eval_runtime": 138.8625, |
| "eval_samples_per_second": 0.922, |
| "eval_steps_per_second": 0.461, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.7569946557686262, |
| "grad_norm": 4.718209743499756, |
| "learning_rate": 0.00017841763238039663, |
| "logits/chosen": -0.6275457739830017, |
| "logits/rejected": -0.9186823964118958, |
| "logps/chosen": -12.871590614318848, |
| "logps/rejected": -112.10943603515625, |
| "loss": 0.719530463218689, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.5595242977142334, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": -0.18099750578403473, |
| "rewards/margins": 9.218995094299316, |
| "rewards/rejected": -9.399992942810059, |
| "step": 301, |
| "train_speed(iter/s)": 0.011166 |
| }, |
| { |
| "epoch": 0.7595095881798176, |
| "grad_norm": 2.1542508602142334, |
| "learning_rate": 0.00017824496245475477, |
| "logits/chosen": -0.646737813949585, |
| "logits/rejected": -0.8969013690948486, |
| "logps/chosen": -5.7762556076049805, |
| "logps/rejected": -97.33111572265625, |
| "loss": 0.5689316987991333, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.438076913356781, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.00827467255294323, |
| "rewards/margins": 8.17311954498291, |
| "rewards/rejected": -8.164844512939453, |
| "step": 302, |
| "train_speed(iter/s)": 0.011167 |
| }, |
| { |
| "epoch": 0.7620245205910091, |
| "grad_norm": 3.397379159927368, |
| "learning_rate": 0.00017807168881595303, |
| "logits/chosen": -0.5890093445777893, |
| "logits/rejected": -0.8686433434486389, |
| "logps/chosen": -3.385796546936035, |
| "logps/rejected": -108.06370544433594, |
| "loss": 0.3380297124385834, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.2262319028377533, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": -0.01376427710056305, |
| "rewards/margins": 8.914027214050293, |
| "rewards/rejected": -8.9277925491333, |
| "step": 303, |
| "train_speed(iter/s)": 0.011167 |
| }, |
| { |
| "epoch": 0.7645394530022006, |
| "grad_norm": 1.465338110923767, |
| "learning_rate": 0.00017789781280091557, |
| "logits/chosen": -0.6118184328079224, |
| "logits/rejected": -0.8406589031219482, |
| "logps/chosen": -3.1348047256469727, |
| "logps/rejected": -79.62229919433594, |
| "loss": 0.39135175943374634, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.2855513095855713, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.07680860161781311, |
| "rewards/margins": 6.500816345214844, |
| "rewards/rejected": -6.424009323120117, |
| "step": 304, |
| "train_speed(iter/s)": 0.011167 |
| }, |
| { |
| "epoch": 0.767054385413392, |
| "grad_norm": 2.457659959793091, |
| "learning_rate": 0.0001777233357512142, |
| "logits/chosen": -0.5555245280265808, |
| "logits/rejected": -0.7983438372612, |
| "logps/chosen": -5.093034267425537, |
| "logps/rejected": -92.61869812011719, |
| "loss": 0.4847222566604614, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.422935426235199, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.07793700695037842, |
| "rewards/margins": 7.504522800445557, |
| "rewards/rejected": -7.426586151123047, |
| "step": 305, |
| "train_speed(iter/s)": 0.011168 |
| }, |
| { |
| "epoch": 0.7695693178245835, |
| "grad_norm": 1.6642144918441772, |
| "learning_rate": 0.00017754825901305813, |
| "logits/chosen": -0.5577365159988403, |
| "logits/rejected": -0.6896043419837952, |
| "logps/chosen": -9.644157409667969, |
| "logps/rejected": -58.60102462768555, |
| "loss": 0.6450366377830505, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.4952359199523926, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.2571660280227661, |
| "rewards/margins": 4.676360130310059, |
| "rewards/rejected": -4.419194221496582, |
| "step": 306, |
| "train_speed(iter/s)": 0.011168 |
| }, |
| { |
| "epoch": 0.7720842502357749, |
| "grad_norm": 1.6156450510025024, |
| "learning_rate": 0.00017737258393728364, |
| "logits/chosen": -0.44825202226638794, |
| "logits/rejected": -0.7190597057342529, |
| "logps/chosen": -3.3316762447357178, |
| "logps/rejected": -79.71031188964844, |
| "loss": 0.3546125590801239, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.25914254784584045, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.1541021317243576, |
| "rewards/margins": 5.745656967163086, |
| "rewards/rejected": -5.591554641723633, |
| "step": 307, |
| "train_speed(iter/s)": 0.011168 |
| }, |
| { |
| "epoch": 0.7745991826469664, |
| "grad_norm": 1.6676106452941895, |
| "learning_rate": 0.00017719631187934352, |
| "logits/chosen": -0.48865610361099243, |
| "logits/rejected": -0.6960019469261169, |
| "logps/chosen": -5.700809478759766, |
| "logps/rejected": -73.01457214355469, |
| "loss": 0.581813395023346, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.4443373382091522, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.01655534654855728, |
| "rewards/margins": 5.344724655151367, |
| "rewards/rejected": -5.328168869018555, |
| "step": 308, |
| "train_speed(iter/s)": 0.011169 |
| }, |
| { |
| "epoch": 0.7771141150581579, |
| "grad_norm": 7.093632698059082, |
| "learning_rate": 0.00017701944419929672, |
| "logits/chosen": -0.5656027793884277, |
| "logits/rejected": -0.744474470615387, |
| "logps/chosen": -5.30854606628418, |
| "logps/rejected": -66.55186462402344, |
| "loss": 0.5189223289489746, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3126901686191559, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.012391818687319756, |
| "rewards/margins": 4.805446624755859, |
| "rewards/rejected": -4.793054580688477, |
| "step": 309, |
| "train_speed(iter/s)": 0.011169 |
| }, |
| { |
| "epoch": 0.7796290474693492, |
| "grad_norm": 5.8190016746521, |
| "learning_rate": 0.00017684198226179784, |
| "logits/chosen": -0.5459531545639038, |
| "logits/rejected": -0.7102005481719971, |
| "logps/chosen": -5.777270317077637, |
| "logps/rejected": -73.569091796875, |
| "loss": 0.3673727810382843, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.2682158648967743, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": -0.005160713568329811, |
| "rewards/margins": 5.717585563659668, |
| "rewards/rejected": -5.722745895385742, |
| "step": 310, |
| "train_speed(iter/s)": 0.01117 |
| }, |
| { |
| "epoch": 0.7821439798805407, |
| "grad_norm": 1.8922319412231445, |
| "learning_rate": 0.00017666392743608656, |
| "logits/chosen": -0.594789445400238, |
| "logits/rejected": -0.6599074602127075, |
| "logps/chosen": -10.497507095336914, |
| "logps/rejected": -49.53678894042969, |
| "loss": 0.6126048564910889, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.4225066006183624, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.2926208972930908, |
| "rewards/margins": 3.908644676208496, |
| "rewards/rejected": -3.6160240173339844, |
| "step": 311, |
| "train_speed(iter/s)": 0.01117 |
| }, |
| { |
| "epoch": 0.7846589122917321, |
| "grad_norm": 3.8677096366882324, |
| "learning_rate": 0.00017648528109597705, |
| "logits/chosen": -0.5457702279090881, |
| "logits/rejected": -0.6197797060012817, |
| "logps/chosen": -6.788382053375244, |
| "logps/rejected": -42.95294189453125, |
| "loss": 0.6690109372138977, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.40374916791915894, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.044411513954401016, |
| "rewards/margins": 3.1033527851104736, |
| "rewards/rejected": -3.05894136428833, |
| "step": 312, |
| "train_speed(iter/s)": 0.01117 |
| }, |
| { |
| "epoch": 0.7871738447029236, |
| "grad_norm": 1.0135570764541626, |
| "learning_rate": 0.00017630604461984746, |
| "logits/chosen": -0.5280042886734009, |
| "logits/rejected": -0.7244092226028442, |
| "logps/chosen": -4.014311790466309, |
| "logps/rejected": -68.12934875488281, |
| "loss": 0.3465278744697571, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.27361059188842773, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.14259541034698486, |
| "rewards/margins": 5.263729095458984, |
| "rewards/rejected": -5.121134281158447, |
| "step": 313, |
| "train_speed(iter/s)": 0.011171 |
| }, |
| { |
| "epoch": 0.789688777114115, |
| "grad_norm": 4.7270283699035645, |
| "learning_rate": 0.00017612621939062928, |
| "logits/chosen": -0.5396519303321838, |
| "logits/rejected": -0.7206518650054932, |
| "logps/chosen": -5.555117130279541, |
| "logps/rejected": -73.57891082763672, |
| "loss": 0.6602690815925598, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.5206518173217773, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": -0.0014735832810401917, |
| "rewards/margins": 5.42769193649292, |
| "rewards/rejected": -5.429165840148926, |
| "step": 314, |
| "train_speed(iter/s)": 0.011171 |
| }, |
| { |
| "epoch": 0.7922037095253065, |
| "grad_norm": 1.428287386894226, |
| "learning_rate": 0.00017594580679579656, |
| "logits/chosen": -0.4950787127017975, |
| "logits/rejected": -0.7107822299003601, |
| "logps/chosen": -3.5974302291870117, |
| "logps/rejected": -74.10302734375, |
| "loss": 0.4180299937725067, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.2984779179096222, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.08340106159448624, |
| "rewards/margins": 5.900142192840576, |
| "rewards/rejected": -5.8167405128479, |
| "step": 315, |
| "train_speed(iter/s)": 0.011171 |
| }, |
| { |
| "epoch": 0.794718641936498, |
| "grad_norm": 1.647938847541809, |
| "learning_rate": 0.00017576480822735532, |
| "logits/chosen": -0.5975894927978516, |
| "logits/rejected": -0.7487577199935913, |
| "logps/chosen": -6.398176670074463, |
| "logps/rejected": -77.47513580322266, |
| "loss": 0.494728684425354, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.4415830969810486, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.16486969590187073, |
| "rewards/margins": 6.55712890625, |
| "rewards/rejected": -6.39225959777832, |
| "step": 316, |
| "train_speed(iter/s)": 0.011172 |
| }, |
| { |
| "epoch": 0.7972335743476894, |
| "grad_norm": 3.1385247707366943, |
| "learning_rate": 0.00017558322508183275, |
| "logits/chosen": -0.5611414909362793, |
| "logits/rejected": -0.7583786249160767, |
| "logps/chosen": -10.28195571899414, |
| "logps/rejected": -80.05876159667969, |
| "loss": 0.5074371695518494, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.3455233871936798, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": -0.034254290163517, |
| "rewards/margins": 6.353381156921387, |
| "rewards/rejected": -6.387635707855225, |
| "step": 317, |
| "train_speed(iter/s)": 0.011172 |
| }, |
| { |
| "epoch": 0.7997485067588809, |
| "grad_norm": 4.7420196533203125, |
| "learning_rate": 0.00017540105876026648, |
| "logits/chosen": -0.5814342498779297, |
| "logits/rejected": -0.7620936036109924, |
| "logps/chosen": -5.382750034332275, |
| "logps/rejected": -78.29422760009766, |
| "loss": 0.5510153770446777, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.40605586767196655, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.0036928970366716385, |
| "rewards/margins": 6.385010719299316, |
| "rewards/rejected": -6.381317615509033, |
| "step": 318, |
| "train_speed(iter/s)": 0.011172 |
| }, |
| { |
| "epoch": 0.8022634391700723, |
| "grad_norm": 8.547826766967773, |
| "learning_rate": 0.00017521831066819363, |
| "logits/chosen": -0.6748584508895874, |
| "logits/rejected": -0.751319944858551, |
| "logps/chosen": -10.142738342285156, |
| "logps/rejected": -62.902137756347656, |
| "loss": 0.7446877956390381, |
| "memory(GiB)": 46.14, |
| "nll_loss": 0.4347481429576874, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": -0.3501091003417969, |
| "rewards/margins": 4.718851089477539, |
| "rewards/rejected": -5.068960189819336, |
| "step": 319, |
| "train_speed(iter/s)": 0.011173 |
| }, |
| { |
| "epoch": 0.8047783715812638, |
| "grad_norm": 2.8475148677825928, |
| "learning_rate": 0.00017503498221564025, |
| "logits/chosen": -0.5278587937355042, |
| "logits/rejected": -0.7719522714614868, |
| "logps/chosen": -5.870185375213623, |
| "logps/rejected": -83.85944366455078, |
| "loss": 0.661263644695282, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.46991419792175293, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.10902933776378632, |
| "rewards/margins": 6.237672328948975, |
| "rewards/rejected": -6.128643035888672, |
| "step": 320, |
| "train_speed(iter/s)": 0.011173 |
| }, |
| { |
| "epoch": 0.8072933039924552, |
| "grad_norm": 2.305772542953491, |
| "learning_rate": 0.00017485107481711012, |
| "logits/chosen": -0.5994943976402283, |
| "logits/rejected": -0.7459429502487183, |
| "logps/chosen": -5.2525315284729, |
| "logps/rejected": -73.49571228027344, |
| "loss": 0.4045717120170593, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.28694650530815125, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.041447557508945465, |
| "rewards/margins": 6.024381637573242, |
| "rewards/rejected": -5.98293399810791, |
| "step": 321, |
| "train_speed(iter/s)": 0.011173 |
| }, |
| { |
| "epoch": 0.8098082364036466, |
| "grad_norm": 1.735187292098999, |
| "learning_rate": 0.00017466658989157406, |
| "logits/chosen": -0.5249663591384888, |
| "logits/rejected": -0.7108433842658997, |
| "logps/chosen": -4.704793453216553, |
| "logps/rejected": -72.97203063964844, |
| "loss": 0.4518013298511505, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.3283430337905884, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.07784826308488846, |
| "rewards/margins": 5.81508731842041, |
| "rewards/rejected": -5.737238883972168, |
| "step": 322, |
| "train_speed(iter/s)": 0.011173 |
| }, |
| { |
| "epoch": 0.8123231688148381, |
| "grad_norm": 0.9543433785438538, |
| "learning_rate": 0.00017448152886245888, |
| "logits/chosen": -0.5041825771331787, |
| "logits/rejected": -0.6829778552055359, |
| "logps/chosen": -4.729351997375488, |
| "logps/rejected": -76.31644439697266, |
| "loss": 0.3558841347694397, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.281302273273468, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.249185249209404, |
| "rewards/margins": 6.1249003410339355, |
| "rewards/rejected": -5.875715255737305, |
| "step": 323, |
| "train_speed(iter/s)": 0.011173 |
| }, |
| { |
| "epoch": 0.8148381012260295, |
| "grad_norm": 5.0823750495910645, |
| "learning_rate": 0.00017429589315763638, |
| "logits/chosen": -0.4357600510120392, |
| "logits/rejected": -0.700524091720581, |
| "logps/chosen": -3.877192258834839, |
| "logps/rejected": -68.90542602539062, |
| "loss": 0.5542052984237671, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.41005879640579224, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.02913202904164791, |
| "rewards/margins": 5.158620357513428, |
| "rewards/rejected": -5.129488945007324, |
| "step": 324, |
| "train_speed(iter/s)": 0.011174 |
| }, |
| { |
| "epoch": 0.817353033637221, |
| "grad_norm": 1.3050035238265991, |
| "learning_rate": 0.00017410968420941244, |
| "logits/chosen": -0.3421289622783661, |
| "logits/rejected": -0.6473272442817688, |
| "logps/chosen": -5.135888576507568, |
| "logps/rejected": -74.2640151977539, |
| "loss": 0.48740285634994507, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.38718196749687195, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.24520042538642883, |
| "rewards/margins": 5.387969493865967, |
| "rewards/rejected": -5.1427693367004395, |
| "step": 325, |
| "train_speed(iter/s)": 0.011174 |
| }, |
| { |
| "epoch": 0.8198679660484125, |
| "grad_norm": 11.92521858215332, |
| "learning_rate": 0.00017392290345451592, |
| "logits/chosen": -0.38754820823669434, |
| "logits/rejected": -0.607338547706604, |
| "logps/chosen": -6.677229404449463, |
| "logps/rejected": -71.38823699951172, |
| "loss": 0.5474317073822021, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.40050551295280457, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.13461363315582275, |
| "rewards/margins": 5.393355846405029, |
| "rewards/rejected": -5.258741855621338, |
| "step": 326, |
| "train_speed(iter/s)": 0.011174 |
| }, |
| { |
| "epoch": 0.8223828984596039, |
| "grad_norm": 1.5031628608703613, |
| "learning_rate": 0.0001737355523340875, |
| "logits/chosen": -0.5126341581344604, |
| "logits/rejected": -0.6609553694725037, |
| "logps/chosen": -3.9447288513183594, |
| "logps/rejected": -60.175750732421875, |
| "loss": 0.4619714617729187, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.35617318749427795, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.17950919270515442, |
| "rewards/margins": 4.923368453979492, |
| "rewards/rejected": -4.743858814239502, |
| "step": 327, |
| "train_speed(iter/s)": 0.011174 |
| }, |
| { |
| "epoch": 0.8248978308707954, |
| "grad_norm": 1.3256229162216187, |
| "learning_rate": 0.0001735476322936686, |
| "logits/chosen": -0.3694300651550293, |
| "logits/rejected": -0.6536751389503479, |
| "logps/chosen": -4.688364505767822, |
| "logps/rejected": -76.19749450683594, |
| "loss": 0.4076545834541321, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.325284868478775, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.1420704424381256, |
| "rewards/margins": 5.678350448608398, |
| "rewards/rejected": -5.536280155181885, |
| "step": 328, |
| "train_speed(iter/s)": 0.011174 |
| }, |
| { |
| "epoch": 0.8274127632819868, |
| "grad_norm": 1.3037030696868896, |
| "learning_rate": 0.00017335914478319028, |
| "logits/chosen": -0.41062769293785095, |
| "logits/rejected": -0.6642740368843079, |
| "logps/chosen": -5.453380584716797, |
| "logps/rejected": -74.66622924804688, |
| "loss": 0.44521886110305786, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.3608228862285614, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.11086025834083557, |
| "rewards/margins": 5.619003772735596, |
| "rewards/rejected": -5.508144378662109, |
| "step": 329, |
| "train_speed(iter/s)": 0.011175 |
| }, |
| { |
| "epoch": 0.8299276956931783, |
| "grad_norm": 1.4347755908966064, |
| "learning_rate": 0.00017317009125696208, |
| "logits/chosen": -0.4672892689704895, |
| "logits/rejected": -0.6743369698524475, |
| "logps/chosen": -4.6292266845703125, |
| "logps/rejected": -73.22108459472656, |
| "loss": 0.2870956063270569, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.23536254465579987, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.18421661853790283, |
| "rewards/margins": 6.022341728210449, |
| "rewards/rejected": -5.838125228881836, |
| "step": 330, |
| "train_speed(iter/s)": 0.011175 |
| }, |
| { |
| "epoch": 0.8324426281043696, |
| "grad_norm": 2.6831681728363037, |
| "learning_rate": 0.00017298047317366061, |
| "logits/chosen": -0.46991387009620667, |
| "logits/rejected": -0.6954001784324646, |
| "logps/chosen": -4.487226963043213, |
| "logps/rejected": -70.13626861572266, |
| "loss": 0.5644213557243347, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.4404352903366089, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.0725957453250885, |
| "rewards/margins": 5.4586405754089355, |
| "rewards/rejected": -5.386044502258301, |
| "step": 331, |
| "train_speed(iter/s)": 0.011175 |
| }, |
| { |
| "epoch": 0.8349575605155611, |
| "grad_norm": 0.9778565764427185, |
| "learning_rate": 0.00017279029199631857, |
| "logits/chosen": -0.40650704503059387, |
| "logits/rejected": -0.6795352697372437, |
| "logps/chosen": -2.2717714309692383, |
| "logps/rejected": -77.46300506591797, |
| "loss": 0.29844945669174194, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.1882498562335968, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.16533461213111877, |
| "rewards/margins": 6.410762310028076, |
| "rewards/rejected": -6.24542760848999, |
| "step": 332, |
| "train_speed(iter/s)": 0.011176 |
| }, |
| { |
| "epoch": 0.8374724929267526, |
| "grad_norm": 2.472064971923828, |
| "learning_rate": 0.0001725995491923131, |
| "logits/chosen": -0.4610061049461365, |
| "logits/rejected": -0.6507254838943481, |
| "logps/chosen": -11.14199447631836, |
| "logps/rejected": -77.41361999511719, |
| "loss": 0.7604877352714539, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.5936329960823059, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": -0.011591670103371143, |
| "rewards/margins": 6.023037433624268, |
| "rewards/rejected": -6.034628868103027, |
| "step": 333, |
| "train_speed(iter/s)": 0.011176 |
| }, |
| { |
| "epoch": 0.839987425337944, |
| "grad_norm": 4.791397571563721, |
| "learning_rate": 0.0001724082462333549, |
| "logits/chosen": -0.4945090115070343, |
| "logits/rejected": -0.6786508560180664, |
| "logps/chosen": -4.583111763000488, |
| "logps/rejected": -70.58711242675781, |
| "loss": 0.4426124095916748, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.3457377851009369, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.06782704591751099, |
| "rewards/margins": 5.740070819854736, |
| "rewards/rejected": -5.672244071960449, |
| "step": 334, |
| "train_speed(iter/s)": 0.011176 |
| }, |
| { |
| "epoch": 0.8425023577491355, |
| "grad_norm": 7.941857814788818, |
| "learning_rate": 0.00017221638459547655, |
| "logits/chosen": -0.5508913397789001, |
| "logits/rejected": -0.7254266142845154, |
| "logps/chosen": -5.333986759185791, |
| "logps/rejected": -66.42805480957031, |
| "loss": 0.6611946225166321, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.5266276001930237, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.258667916059494, |
| "rewards/margins": 5.6560516357421875, |
| "rewards/rejected": -5.397383689880371, |
| "step": 335, |
| "train_speed(iter/s)": 0.011176 |
| }, |
| { |
| "epoch": 0.8450172901603269, |
| "grad_norm": 1.9054502248764038, |
| "learning_rate": 0.00017202396575902116, |
| "logits/chosen": -0.5157940983772278, |
| "logits/rejected": -0.662640392780304, |
| "logps/chosen": -9.51154899597168, |
| "logps/rejected": -77.71415710449219, |
| "loss": 0.6165091395378113, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.498354434967041, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": -0.054273076355457306, |
| "rewards/margins": 5.92840576171875, |
| "rewards/rejected": -5.98267936706543, |
| "step": 336, |
| "train_speed(iter/s)": 0.011177 |
| }, |
| { |
| "epoch": 0.8475322225715184, |
| "grad_norm": 5.0429582595825195, |
| "learning_rate": 0.00017183099120863116, |
| "logits/chosen": -0.4925355017185211, |
| "logits/rejected": -0.7224594950675964, |
| "logps/chosen": -3.7566463947296143, |
| "logps/rejected": -82.92442321777344, |
| "loss": 0.37845250964164734, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.27013376355171204, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.047135189175605774, |
| "rewards/margins": 6.651348114013672, |
| "rewards/rejected": -6.604212760925293, |
| "step": 337, |
| "train_speed(iter/s)": 0.011177 |
| }, |
| { |
| "epoch": 0.8500471549827099, |
| "grad_norm": 1.3209309577941895, |
| "learning_rate": 0.0001716374624332365, |
| "logits/chosen": -0.43844541907310486, |
| "logits/rejected": -0.7345193028450012, |
| "logps/chosen": -3.03592848777771, |
| "logps/rejected": -88.54313659667969, |
| "loss": 0.3141745626926422, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.24039344489574432, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.189487487077713, |
| "rewards/margins": 6.713014602661133, |
| "rewards/rejected": -6.523527145385742, |
| "step": 338, |
| "train_speed(iter/s)": 0.011177 |
| }, |
| { |
| "epoch": 0.8525620873939013, |
| "grad_norm": 3.733077049255371, |
| "learning_rate": 0.0001714433809260435, |
| "logits/chosen": -0.541033923625946, |
| "logits/rejected": -0.6785414814949036, |
| "logps/chosen": -13.735635757446289, |
| "logps/rejected": -80.87117767333984, |
| "loss": 0.6797083616256714, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.6222865581512451, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.15373513102531433, |
| "rewards/margins": 6.620373249053955, |
| "rewards/rejected": -6.466638088226318, |
| "step": 339, |
| "train_speed(iter/s)": 0.011177 |
| }, |
| { |
| "epoch": 0.8550770198050928, |
| "grad_norm": 4.67393159866333, |
| "learning_rate": 0.0001712487481845231, |
| "logits/chosen": -0.3521523177623749, |
| "logits/rejected": -0.6670207977294922, |
| "logps/chosen": -6.3595123291015625, |
| "logps/rejected": -96.03783416748047, |
| "loss": 0.3294995427131653, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.22724169492721558, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.025615770369768143, |
| "rewards/margins": 7.826894760131836, |
| "rewards/rejected": -7.801278591156006, |
| "step": 340, |
| "train_speed(iter/s)": 0.011177 |
| }, |
| { |
| "epoch": 0.8575919522162841, |
| "grad_norm": 0.8247130513191223, |
| "learning_rate": 0.00017105356571039945, |
| "logits/chosen": -0.4443299174308777, |
| "logits/rejected": -0.7191017866134644, |
| "logps/chosen": -7.833669662475586, |
| "logps/rejected": -86.58798217773438, |
| "loss": 0.42601728439331055, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.3831000328063965, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.07022079825401306, |
| "rewards/margins": 6.889365196228027, |
| "rewards/rejected": -6.8191447257995605, |
| "step": 341, |
| "train_speed(iter/s)": 0.011177 |
| }, |
| { |
| "epoch": 0.8601068846274756, |
| "grad_norm": 0.8711926341056824, |
| "learning_rate": 0.00017085783500963824, |
| "logits/chosen": -0.41609716415405273, |
| "logits/rejected": -0.7125498652458191, |
| "logps/chosen": -3.1712937355041504, |
| "logps/rejected": -77.74504089355469, |
| "loss": 0.21924850344657898, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.1784050464630127, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.20674246549606323, |
| "rewards/margins": 6.209396839141846, |
| "rewards/rejected": -6.002654552459717, |
| "step": 342, |
| "train_speed(iter/s)": 0.011177 |
| }, |
| { |
| "epoch": 0.8626218170386671, |
| "grad_norm": 5.732574939727783, |
| "learning_rate": 0.00017066155759243507, |
| "logits/chosen": -0.5378013849258423, |
| "logits/rejected": -0.7252504825592041, |
| "logps/chosen": -5.074343204498291, |
| "logps/rejected": -75.13893127441406, |
| "loss": 0.37449705600738525, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.28582653403282166, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": -0.06149884685873985, |
| "rewards/margins": 6.032390117645264, |
| "rewards/rejected": -6.093888759613037, |
| "step": 343, |
| "train_speed(iter/s)": 0.011178 |
| }, |
| { |
| "epoch": 0.8651367494498585, |
| "grad_norm": 1.0474615097045898, |
| "learning_rate": 0.00017046473497320385, |
| "logits/chosen": -0.5175920724868774, |
| "logits/rejected": -0.7067053914070129, |
| "logps/chosen": -4.754598140716553, |
| "logps/rejected": -72.19132232666016, |
| "loss": 0.398180216550827, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.3198007643222809, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.03717122972011566, |
| "rewards/margins": 5.711915969848633, |
| "rewards/rejected": -5.674744129180908, |
| "step": 344, |
| "train_speed(iter/s)": 0.011178 |
| }, |
| { |
| "epoch": 0.86765168186105, |
| "grad_norm": 1.3896440267562866, |
| "learning_rate": 0.0001702673686705651, |
| "logits/chosen": -0.5148175954818726, |
| "logits/rejected": -0.7209337949752808, |
| "logps/chosen": -3.864173650741577, |
| "logps/rejected": -69.10660552978516, |
| "loss": 0.27238431572914124, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.19631227850914001, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.0761566311120987, |
| "rewards/margins": 5.610742092132568, |
| "rewards/rejected": -5.534584999084473, |
| "step": 345, |
| "train_speed(iter/s)": 0.011178 |
| }, |
| { |
| "epoch": 0.8701666142722414, |
| "grad_norm": 1.14860999584198, |
| "learning_rate": 0.00017006946020733425, |
| "logits/chosen": -0.45313283801078796, |
| "logits/rejected": -0.6407146453857422, |
| "logps/chosen": -4.239717483520508, |
| "logps/rejected": -68.09969329833984, |
| "loss": 0.29144588112831116, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.22455181181430817, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.2668611407279968, |
| "rewards/margins": 5.458950042724609, |
| "rewards/rejected": -5.192089080810547, |
| "step": 346, |
| "train_speed(iter/s)": 0.011178 |
| }, |
| { |
| "epoch": 0.8726815466834329, |
| "grad_norm": 1.542136788368225, |
| "learning_rate": 0.00016987101111050982, |
| "logits/chosen": -0.48639586567878723, |
| "logits/rejected": -0.6774500608444214, |
| "logps/chosen": -6.492711067199707, |
| "logps/rejected": -60.656402587890625, |
| "loss": 0.4538443088531494, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.34202519059181213, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.27481359243392944, |
| "rewards/margins": 4.575342655181885, |
| "rewards/rejected": -4.3005290031433105, |
| "step": 347, |
| "train_speed(iter/s)": 0.011178 |
| }, |
| { |
| "epoch": 0.8751964790946243, |
| "grad_norm": 2.576685667037964, |
| "learning_rate": 0.00016967202291126173, |
| "logits/chosen": -0.42330560088157654, |
| "logits/rejected": -0.7439920902252197, |
| "logps/chosen": -3.36045241355896, |
| "logps/rejected": -69.37139129638672, |
| "loss": 0.34409311413764954, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.26893264055252075, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.2507910132408142, |
| "rewards/margins": 4.905345916748047, |
| "rewards/rejected": -4.654554843902588, |
| "step": 348, |
| "train_speed(iter/s)": 0.011178 |
| }, |
| { |
| "epoch": 0.8777114115058158, |
| "grad_norm": 1.1091530323028564, |
| "learning_rate": 0.00016947249714491938, |
| "logits/chosen": -0.4069375991821289, |
| "logits/rejected": -0.7425306439399719, |
| "logps/chosen": -3.862551689147949, |
| "logps/rejected": -80.9285659790039, |
| "loss": 0.36630380153656006, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.2950875759124756, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.15249909460544586, |
| "rewards/margins": 5.997171401977539, |
| "rewards/rejected": -5.844672679901123, |
| "step": 349, |
| "train_speed(iter/s)": 0.011178 |
| }, |
| { |
| "epoch": 0.8802263439170073, |
| "grad_norm": 3.5830211639404297, |
| "learning_rate": 0.00016927243535095997, |
| "logits/chosen": -0.5977684259414673, |
| "logits/rejected": -0.7476451992988586, |
| "logps/chosen": -5.81241512298584, |
| "logps/rejected": -62.173587799072266, |
| "loss": 0.6108379364013672, |
| "memory(GiB)": 46.74, |
| "nll_loss": 0.4931432604789734, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.10844524204730988, |
| "rewards/margins": 5.111351013183594, |
| "rewards/rejected": -5.00290584564209, |
| "step": 350, |
| "train_speed(iter/s)": 0.011179 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 1191, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.9184784764829696e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
