phi3m0128-cds-0.75-kendall-onof-ofif-corr-max-2-simpo-max1500-default
/
checkpoint-300
/trainer_state.json
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2664298401420959, | |
| "eval_steps": 50, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008880994671403197, | |
| "grad_norm": 0.04571289196610451, | |
| "learning_rate": 4.999451708687114e-06, | |
| "logits/chosen": 14.56671142578125, | |
| "logits/rejected": 15.112574577331543, | |
| "logps/chosen": -0.26506316661834717, | |
| "logps/rejected": -0.3439488410949707, | |
| "loss": 0.9267, | |
| "rewards/accuracies": 0.574999988079071, | |
| "rewards/chosen": -0.39759472012519836, | |
| "rewards/margins": 0.11832849681377411, | |
| "rewards/rejected": -0.5159232020378113, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017761989342806393, | |
| "grad_norm": 0.0512714721262455, | |
| "learning_rate": 4.997807075247147e-06, | |
| "logits/chosen": 14.376543045043945, | |
| "logits/rejected": 14.862703323364258, | |
| "logps/chosen": -0.2708089351654053, | |
| "logps/rejected": -0.32412824034690857, | |
| "loss": 0.936, | |
| "rewards/accuracies": 0.5, | |
| "rewards/chosen": -0.4062133729457855, | |
| "rewards/margins": 0.07997899502515793, | |
| "rewards/rejected": -0.4861923158168793, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02664298401420959, | |
| "grad_norm": 0.058383647352457047, | |
| "learning_rate": 4.9950668210706795e-06, | |
| "logits/chosen": 14.208717346191406, | |
| "logits/rejected": 15.370651245117188, | |
| "logps/chosen": -0.28206294775009155, | |
| "logps/rejected": -0.38387423753738403, | |
| "loss": 0.9215, | |
| "rewards/accuracies": 0.625, | |
| "rewards/chosen": -0.42309442162513733, | |
| "rewards/margins": 0.15271687507629395, | |
| "rewards/rejected": -0.5758112668991089, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.035523978685612786, | |
| "grad_norm": 0.06262075155973434, | |
| "learning_rate": 4.9912321481237616e-06, | |
| "logits/chosen": 14.768765449523926, | |
| "logits/rejected": 15.169331550598145, | |
| "logps/chosen": -0.27857059240341187, | |
| "logps/rejected": -0.3388269543647766, | |
| "loss": 0.9386, | |
| "rewards/accuracies": 0.5, | |
| "rewards/chosen": -0.4178559184074402, | |
| "rewards/margins": 0.09038447588682175, | |
| "rewards/rejected": -0.5082404017448425, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04440497335701599, | |
| "grad_norm": 0.06259036809206009, | |
| "learning_rate": 4.986304738420684e-06, | |
| "logits/chosen": 14.950456619262695, | |
| "logits/rejected": 15.232122421264648, | |
| "logps/chosen": -0.2961367070674896, | |
| "logps/rejected": -0.3322262465953827, | |
| "loss": 0.9317, | |
| "rewards/accuracies": 0.44999998807907104, | |
| "rewards/chosen": -0.44420504570007324, | |
| "rewards/margins": 0.054134320467710495, | |
| "rewards/rejected": -0.4983394145965576, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04440497335701599, | |
| "eval_logits/chosen": 14.56529426574707, | |
| "eval_logits/rejected": 14.895020484924316, | |
| "eval_logps/chosen": -0.2806546986103058, | |
| "eval_logps/rejected": -0.3486972451210022, | |
| "eval_loss": 0.9381324052810669, | |
| "eval_rewards/accuracies": 0.5274725556373596, | |
| "eval_rewards/chosen": -0.4209820330142975, | |
| "eval_rewards/margins": 0.10206379741430283, | |
| "eval_rewards/rejected": -0.5230458974838257, | |
| "eval_runtime": 25.2574, | |
| "eval_samples_per_second": 28.823, | |
| "eval_steps_per_second": 3.603, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05328596802841918, | |
| "grad_norm": 0.07301533967256546, | |
| "learning_rate": 4.980286753286196e-06, | |
| "logits/chosen": 14.195574760437012, | |
| "logits/rejected": 15.173194885253906, | |
| "logps/chosen": -0.2693648636341095, | |
| "logps/rejected": -0.33997970819473267, | |
| "loss": 0.9319, | |
| "rewards/accuracies": 0.512499988079071, | |
| "rewards/chosen": -0.40404725074768066, | |
| "rewards/margins": 0.10592226684093475, | |
| "rewards/rejected": -0.5099694728851318, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06216696269982238, | |
| "grad_norm": 0.0659889206290245, | |
| "learning_rate": 4.973180832407471e-06, | |
| "logits/chosen": 14.910173416137695, | |
| "logits/rejected": 15.361429214477539, | |
| "logps/chosen": -0.28456225991249084, | |
| "logps/rejected": -0.3702812194824219, | |
| "loss": 0.9185, | |
| "rewards/accuracies": 0.625, | |
| "rewards/chosen": -0.42684346437454224, | |
| "rewards/margins": 0.12857840955257416, | |
| "rewards/rejected": -0.5554218292236328, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07104795737122557, | |
| "grad_norm": 0.05815625935792923, | |
| "learning_rate": 4.964990092676263e-06, | |
| "logits/chosen": 14.407182693481445, | |
| "logits/rejected": 14.948204040527344, | |
| "logps/chosen": -0.292889267206192, | |
| "logps/rejected": -0.3381648063659668, | |
| "loss": 0.9388, | |
| "rewards/accuracies": 0.5375000238418579, | |
| "rewards/chosen": -0.43933385610580444, | |
| "rewards/margins": 0.06791339069604874, | |
| "rewards/rejected": -0.5072472095489502, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07992895204262877, | |
| "grad_norm": 0.06627190113067627, | |
| "learning_rate": 4.9557181268217225e-06, | |
| "logits/chosen": 14.622471809387207, | |
| "logits/rejected": 15.167770385742188, | |
| "logps/chosen": -0.28155821561813354, | |
| "logps/rejected": -0.33633899688720703, | |
| "loss": 0.9256, | |
| "rewards/accuracies": 0.5375000238418579, | |
| "rewards/chosen": -0.4223373532295227, | |
| "rewards/margins": 0.08217118680477142, | |
| "rewards/rejected": -0.5045084953308105, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.08880994671403197, | |
| "grad_norm": 0.0724545568227768, | |
| "learning_rate": 4.9453690018345144e-06, | |
| "logits/chosen": 14.289724349975586, | |
| "logits/rejected": 14.882037162780762, | |
| "logps/chosen": -0.2791440486907959, | |
| "logps/rejected": -0.35329627990722656, | |
| "loss": 0.9374, | |
| "rewards/accuracies": 0.5375000238418579, | |
| "rewards/chosen": -0.41871610283851624, | |
| "rewards/margins": 0.11122839152812958, | |
| "rewards/rejected": -0.5299445390701294, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08880994671403197, | |
| "eval_logits/chosen": 14.337930679321289, | |
| "eval_logits/rejected": 14.689269065856934, | |
| "eval_logps/chosen": -0.2726942300796509, | |
| "eval_logps/rejected": -0.34668418765068054, | |
| "eval_loss": 0.9302808046340942, | |
| "eval_rewards/accuracies": 0.5384615659713745, | |
| "eval_rewards/chosen": -0.40904131531715393, | |
| "eval_rewards/margins": 0.11098497360944748, | |
| "eval_rewards/rejected": -0.5200263261795044, | |
| "eval_runtime": 25.2585, | |
| "eval_samples_per_second": 28.822, | |
| "eval_steps_per_second": 3.603, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09769094138543517, | |
| "grad_norm": 0.08156246691942215, | |
| "learning_rate": 4.933947257182901e-06, | |
| "logits/chosen": 14.499124526977539, | |
| "logits/rejected": 14.916313171386719, | |
| "logps/chosen": -0.2798352837562561, | |
| "logps/rejected": -0.3477734327316284, | |
| "loss": 0.9243, | |
| "rewards/accuracies": 0.5625, | |
| "rewards/chosen": -0.4197530150413513, | |
| "rewards/margins": 0.10190720856189728, | |
| "rewards/rejected": -0.5216602087020874, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.10657193605683836, | |
| "grad_norm": 0.08161844313144684, | |
| "learning_rate": 4.921457902821578e-06, | |
| "logits/chosen": 13.595013618469238, | |
| "logits/rejected": 14.390353202819824, | |
| "logps/chosen": -0.26682502031326294, | |
| "logps/rejected": -0.3336995542049408, | |
| "loss": 0.9123, | |
| "rewards/accuracies": 0.5874999761581421, | |
| "rewards/chosen": -0.400237500667572, | |
| "rewards/margins": 0.10031183809041977, | |
| "rewards/rejected": -0.5005493760108948, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.11545293072824156, | |
| "grad_norm": 0.28624778985977173, | |
| "learning_rate": 4.907906416994146e-06, | |
| "logits/chosen": 13.711044311523438, | |
| "logits/rejected": 14.558542251586914, | |
| "logps/chosen": -0.27874043583869934, | |
| "logps/rejected": -0.3582325279712677, | |
| "loss": 0.9163, | |
| "rewards/accuracies": 0.5375000238418579, | |
| "rewards/chosen": -0.41811060905456543, | |
| "rewards/margins": 0.11923813819885254, | |
| "rewards/rejected": -0.537348747253418, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.12433392539964476, | |
| "grad_norm": 0.10971464216709137, | |
| "learning_rate": 4.893298743830168e-06, | |
| "logits/chosen": 14.18798828125, | |
| "logits/rejected": 14.993026733398438, | |
| "logps/chosen": -0.2750400900840759, | |
| "logps/rejected": -0.39451608061790466, | |
| "loss": 0.9098, | |
| "rewards/accuracies": 0.574999988079071, | |
| "rewards/chosen": -0.4125601351261139, | |
| "rewards/margins": 0.17921395599842072, | |
| "rewards/rejected": -0.5917741060256958, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.13321492007104796, | |
| "grad_norm": 0.09321591258049011, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "logits/chosen": 12.775139808654785, | |
| "logits/rejected": 13.751996994018555, | |
| "logps/chosen": -0.28446996212005615, | |
| "logps/rejected": -0.36404967308044434, | |
| "loss": 0.9104, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -0.42670494318008423, | |
| "rewards/margins": 0.11936960369348526, | |
| "rewards/rejected": -0.5460745096206665, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.13321492007104796, | |
| "eval_logits/chosen": 12.97266960144043, | |
| "eval_logits/rejected": 13.47339916229248, | |
| "eval_logps/chosen": -0.27297571301460266, | |
| "eval_logps/rejected": -0.36854612827301025, | |
| "eval_loss": 0.9143257737159729, | |
| "eval_rewards/accuracies": 0.5824176073074341, | |
| "eval_rewards/chosen": -0.4094635546207428, | |
| "eval_rewards/margins": 0.14335563778877258, | |
| "eval_rewards/rejected": -0.5528191924095154, | |
| "eval_runtime": 25.2406, | |
| "eval_samples_per_second": 28.842, | |
| "eval_steps_per_second": 3.605, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.14209591474245115, | |
| "grad_norm": 0.11029861867427826, | |
| "learning_rate": 4.860940925593703e-06, | |
| "logits/chosen": 12.677947998046875, | |
| "logits/rejected": 13.396716117858887, | |
| "logps/chosen": -0.2631794512271881, | |
| "logps/rejected": -0.37102141976356506, | |
| "loss": 0.9051, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/chosen": -0.3947691321372986, | |
| "rewards/margins": 0.161762997508049, | |
| "rewards/rejected": -0.5565321445465088, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.15097690941385436, | |
| "grad_norm": 0.15728294849395752, | |
| "learning_rate": 4.84320497372973e-06, | |
| "logits/chosen": 12.620219230651855, | |
| "logits/rejected": 13.189640998840332, | |
| "logps/chosen": -0.2947639524936676, | |
| "logps/rejected": -0.3843482732772827, | |
| "loss": 0.8906, | |
| "rewards/accuracies": 0.5625, | |
| "rewards/chosen": -0.442145973443985, | |
| "rewards/margins": 0.13437646627426147, | |
| "rewards/rejected": -0.5765224099159241, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.15985790408525755, | |
| "grad_norm": 0.31504154205322266, | |
| "learning_rate": 4.824441214720629e-06, | |
| "logits/chosen": 11.487619400024414, | |
| "logits/rejected": 12.33470344543457, | |
| "logps/chosen": -0.271095871925354, | |
| "logps/rejected": -0.4252637028694153, | |
| "loss": 0.8766, | |
| "rewards/accuracies": 0.5874999761581421, | |
| "rewards/chosen": -0.406643807888031, | |
| "rewards/margins": 0.2312517911195755, | |
| "rewards/rejected": -0.6378955245018005, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.16873889875666073, | |
| "grad_norm": 0.19222252070903778, | |
| "learning_rate": 4.804657878971252e-06, | |
| "logits/chosen": 10.093737602233887, | |
| "logits/rejected": 10.851752281188965, | |
| "logps/chosen": -0.2679918110370636, | |
| "logps/rejected": -0.437336266040802, | |
| "loss": 0.884, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/chosen": -0.4019877314567566, | |
| "rewards/margins": 0.2540166974067688, | |
| "rewards/rejected": -0.6560044288635254, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.17761989342806395, | |
| "grad_norm": 0.2275688648223877, | |
| "learning_rate": 4.783863644106502e-06, | |
| "logits/chosen": 9.483477592468262, | |
| "logits/rejected": 10.106366157531738, | |
| "logps/chosen": -0.2957404553890228, | |
| "logps/rejected": -0.40739065408706665, | |
| "loss": 0.8767, | |
| "rewards/accuracies": 0.5874999761581421, | |
| "rewards/chosen": -0.4436107575893402, | |
| "rewards/margins": 0.16747523844242096, | |
| "rewards/rejected": -0.6110859513282776, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.17761989342806395, | |
| "eval_logits/chosen": 8.491498947143555, | |
| "eval_logits/rejected": 8.999146461486816, | |
| "eval_logps/chosen": -0.3135836124420166, | |
| "eval_logps/rejected": -0.4829566180706024, | |
| "eval_loss": 0.8664290904998779, | |
| "eval_rewards/accuracies": 0.6263736486434937, | |
| "eval_rewards/chosen": -0.4703753888607025, | |
| "eval_rewards/margins": 0.2540595233440399, | |
| "eval_rewards/rejected": -0.7244349122047424, | |
| "eval_runtime": 25.2553, | |
| "eval_samples_per_second": 28.826, | |
| "eval_steps_per_second": 3.603, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.18650088809946713, | |
| "grad_norm": 0.27885496616363525, | |
| "learning_rate": 4.762067631165049e-06, | |
| "logits/chosen": 7.234966278076172, | |
| "logits/rejected": 8.313450813293457, | |
| "logps/chosen": -0.29102542996406555, | |
| "logps/rejected": -0.49241799116134644, | |
| "loss": 0.8556, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/chosen": -0.43653813004493713, | |
| "rewards/margins": 0.3020888566970825, | |
| "rewards/rejected": -0.7386269569396973, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.19538188277087035, | |
| "grad_norm": 0.29907363653182983, | |
| "learning_rate": 4.7392794005985324e-06, | |
| "logits/chosen": 7.907521724700928, | |
| "logits/rejected": 8.253190994262695, | |
| "logps/chosen": -0.33691853284835815, | |
| "logps/rejected": -0.4829257130622864, | |
| "loss": 0.8236, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/chosen": -0.5053777694702148, | |
| "rewards/margins": 0.21901080012321472, | |
| "rewards/rejected": -0.724388599395752, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.20426287744227353, | |
| "grad_norm": 0.282474547624588, | |
| "learning_rate": 4.715508948078037e-06, | |
| "logits/chosen": 6.367492198944092, | |
| "logits/rejected": 6.273728370666504, | |
| "logps/chosen": -0.3519875705242157, | |
| "logps/rejected": -0.5284813642501831, | |
| "loss": 0.8027, | |
| "rewards/accuracies": 0.625, | |
| "rewards/chosen": -0.5279813408851624, | |
| "rewards/margins": 0.2647407650947571, | |
| "rewards/rejected": -0.7927221059799194, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.21314387211367672, | |
| "grad_norm": 0.327765554189682, | |
| "learning_rate": 4.690766700109659e-06, | |
| "logits/chosen": 5.090893268585205, | |
| "logits/rejected": 4.768380165100098, | |
| "logps/chosen": -0.3851698040962219, | |
| "logps/rejected": -0.6464222073554993, | |
| "loss": 0.7898, | |
| "rewards/accuracies": 0.612500011920929, | |
| "rewards/chosen": -0.5777546167373657, | |
| "rewards/margins": 0.391878604888916, | |
| "rewards/rejected": -0.9696332812309265, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.22202486678507993, | |
| "grad_norm": 0.4895865321159363, | |
| "learning_rate": 4.665063509461098e-06, | |
| "logits/chosen": 4.056812286376953, | |
| "logits/rejected": 3.723601818084717, | |
| "logps/chosen": -0.4400455951690674, | |
| "logps/rejected": -0.7731422781944275, | |
| "loss": 0.7626, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/chosen": -0.6600683927536011, | |
| "rewards/margins": 0.49964505434036255, | |
| "rewards/rejected": -1.1597135066986084, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.22202486678507993, | |
| "eval_logits/chosen": 2.420060396194458, | |
| "eval_logits/rejected": 2.1626052856445312, | |
| "eval_logps/chosen": -0.4724067151546478, | |
| "eval_logps/rejected": -0.8418064117431641, | |
| "eval_loss": 0.7631083130836487, | |
| "eval_rewards/accuracies": 0.6483516693115234, | |
| "eval_rewards/chosen": -0.7086100578308105, | |
| "eval_rewards/margins": 0.5540997385978699, | |
| "eval_rewards/rejected": -1.2627097368240356, | |
| "eval_runtime": 25.2418, | |
| "eval_samples_per_second": 28.841, | |
| "eval_steps_per_second": 3.605, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.23090586145648312, | |
| "grad_norm": 0.46291017532348633, | |
| "learning_rate": 4.638410650401267e-06, | |
| "logits/chosen": 1.5297390222549438, | |
| "logits/rejected": 1.1381648778915405, | |
| "logps/chosen": -0.4418027997016907, | |
| "logps/rejected": -1.0542564392089844, | |
| "loss": 0.7026, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": -0.6627041697502136, | |
| "rewards/margins": 0.9186803698539734, | |
| "rewards/rejected": -1.5813844203948975, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.23978685612788633, | |
| "grad_norm": 0.9783313870429993, | |
| "learning_rate": 4.610819813755038e-06, | |
| "logits/chosen": 2.8311033248901367, | |
| "logits/rejected": 1.9742711782455444, | |
| "logps/chosen": -0.5430587530136108, | |
| "logps/rejected": -0.9841039776802063, | |
| "loss": 0.7317, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": -0.814588189125061, | |
| "rewards/margins": 0.6615679860115051, | |
| "rewards/rejected": -1.4761559963226318, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.24866785079928952, | |
| "grad_norm": 2.102562189102173, | |
| "learning_rate": 4.582303101775249e-06, | |
| "logits/chosen": 1.8241952657699585, | |
| "logits/rejected": 0.8777934312820435, | |
| "logps/chosen": -0.5624039769172668, | |
| "logps/rejected": -1.1460126638412476, | |
| "loss": 0.6887, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/chosen": -0.8436058163642883, | |
| "rewards/margins": 0.8754131197929382, | |
| "rewards/rejected": -1.7190189361572266, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.25754884547069273, | |
| "grad_norm": 0.9813026189804077, | |
| "learning_rate": 4.55287302283426e-06, | |
| "logits/chosen": 2.370732069015503, | |
| "logits/rejected": 1.4697134494781494, | |
| "logps/chosen": -0.6739786863327026, | |
| "logps/rejected": -1.6581566333770752, | |
| "loss": 0.5695, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/chosen": -1.0109679698944092, | |
| "rewards/margins": 1.476266622543335, | |
| "rewards/rejected": -2.487234592437744, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.2664298401420959, | |
| "grad_norm": 2.187314510345459, | |
| "learning_rate": 4.522542485937369e-06, | |
| "logits/chosen": 1.6230781078338623, | |
| "logits/rejected": 0.5460122227668762, | |
| "logps/chosen": -0.6433733701705933, | |
| "logps/rejected": -2.1001811027526855, | |
| "loss": 0.5366, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": -0.9650601148605347, | |
| "rewards/margins": 2.185211658477783, | |
| "rewards/rejected": -3.1502718925476074, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2664298401420959, | |
| "eval_logits/chosen": 1.4087599515914917, | |
| "eval_logits/rejected": 0.7888947129249573, | |
| "eval_logps/chosen": -0.7579545974731445, | |
| "eval_logps/rejected": -2.0049116611480713, | |
| "eval_loss": 0.551510214805603, | |
| "eval_rewards/accuracies": 0.6813187003135681, | |
| "eval_rewards/chosen": -1.1369318962097168, | |
| "eval_rewards/margins": 1.8704355955123901, | |
| "eval_rewards/rejected": -3.0073673725128174, | |
| "eval_runtime": 25.2647, | |
| "eval_samples_per_second": 28.815, | |
| "eval_steps_per_second": 3.602, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.085793279224054e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |