| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.37723986167871737, |
| "eval_steps": 300, |
| "global_step": 150, |
| "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 |
| } |
| ], |
| "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": 8.236846994895667e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
