| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9945205479452055, | |
| "eval_steps": 500, | |
| "global_step": 364, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 749.8044037682902, | |
| "learning_rate": 2.702702702702703e-10, | |
| "logits/chosen": -0.7030794620513916, | |
| "logits/rejected": -0.3951629400253296, | |
| "logps/chosen": -341.73382568359375, | |
| "logps/rejected": -292.9862060546875, | |
| "loss": 0.6931, | |
| "rewards/accuracies": 0.0, | |
| "rewards/chosen": 0.0, | |
| "rewards/margins": 0.0, | |
| "rewards/rejected": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 728.4025747943551, | |
| "learning_rate": 2.702702702702703e-09, | |
| "logits/chosen": -0.8550878167152405, | |
| "logits/rejected": -0.5013476610183716, | |
| "logps/chosen": -343.0583801269531, | |
| "logps/rejected": -297.6263427734375, | |
| "loss": 0.7129, | |
| "rewards/accuracies": 0.40625, | |
| "rewards/chosen": 0.02346261963248253, | |
| "rewards/margins": -0.025641746819019318, | |
| "rewards/rejected": 0.049104366451501846, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 769.1100121309379, | |
| "learning_rate": 5.405405405405406e-09, | |
| "logits/chosen": -0.89165860414505, | |
| "logits/rejected": -0.5214177966117859, | |
| "logps/chosen": -333.6175231933594, | |
| "logps/rejected": -287.69482421875, | |
| "loss": 0.7088, | |
| "rewards/accuracies": 0.512499988079071, | |
| "rewards/chosen": -0.0008101940038613975, | |
| "rewards/margins": 0.021183893084526062, | |
| "rewards/rejected": -0.02199408784508705, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 782.2455729371497, | |
| "learning_rate": 8.108108108108109e-09, | |
| "logits/chosen": -0.9365941882133484, | |
| "logits/rejected": -0.5470438599586487, | |
| "logps/chosen": -332.33966064453125, | |
| "logps/rejected": -289.5589904785156, | |
| "loss": 0.7083, | |
| "rewards/accuracies": 0.5, | |
| "rewards/chosen": -0.015217331238090992, | |
| "rewards/margins": -0.010174614377319813, | |
| "rewards/rejected": -0.005042716860771179, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 736.3539975893915, | |
| "learning_rate": 9.997923381619256e-09, | |
| "logits/chosen": -0.9017000198364258, | |
| "logits/rejected": -0.555226743221283, | |
| "logps/chosen": -337.62115478515625, | |
| "logps/rejected": -306.5302429199219, | |
| "loss": 0.7072, | |
| "rewards/accuracies": 0.5687500238418579, | |
| "rewards/chosen": 0.05695560574531555, | |
| "rewards/margins": 0.08540164679288864, | |
| "rewards/rejected": -0.02844604291021824, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 730.7089871756754, | |
| "learning_rate": 9.961053687802851e-09, | |
| "logits/chosen": -0.9294391870498657, | |
| "logits/rejected": -0.5007705688476562, | |
| "logps/chosen": -333.2597961425781, | |
| "logps/rejected": -295.4553527832031, | |
| "loss": 0.6941, | |
| "rewards/accuracies": 0.53125, | |
| "rewards/chosen": -0.01942090317606926, | |
| "rewards/margins": 0.017053481191396713, | |
| "rewards/rejected": -0.03647438436746597, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 730.7067078437899, | |
| "learning_rate": 9.878428410862483e-09, | |
| "logits/chosen": -0.8303865194320679, | |
| "logits/rejected": -0.45489081740379333, | |
| "logps/chosen": -331.8045349121094, | |
| "logps/rejected": -295.13055419921875, | |
| "loss": 0.6832, | |
| "rewards/accuracies": 0.6031249761581421, | |
| "rewards/chosen": -0.029834549874067307, | |
| "rewards/margins": 0.05674406886100769, | |
| "rewards/rejected": -0.0865786224603653, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 674.6624722402527, | |
| "learning_rate": 9.750809600145954e-09, | |
| "logits/chosen": -1.0535982847213745, | |
| "logits/rejected": -0.6284598112106323, | |
| "logps/chosen": -351.1028747558594, | |
| "logps/rejected": -304.6434631347656, | |
| "loss": 0.6804, | |
| "rewards/accuracies": 0.625, | |
| "rewards/chosen": 0.0078976359218359, | |
| "rewards/margins": 0.11121608316898346, | |
| "rewards/rejected": -0.10331843793392181, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 640.6205441818687, | |
| "learning_rate": 9.579374278412817e-09, | |
| "logits/chosen": -0.9343639612197876, | |
| "logits/rejected": -0.3806554079055786, | |
| "logps/chosen": -344.04443359375, | |
| "logps/rejected": -294.193359375, | |
| "loss": 0.6487, | |
| "rewards/accuracies": 0.659375011920929, | |
| "rewards/chosen": -0.01617306098341942, | |
| "rewards/margins": 0.14446857571601868, | |
| "rewards/rejected": -0.1606416255235672, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 629.6802089882239, | |
| "learning_rate": 9.365703586204494e-09, | |
| "logits/chosen": -1.0297319889068604, | |
| "logits/rejected": -0.654572606086731, | |
| "logps/chosen": -340.8974609375, | |
| "logps/rejected": -307.7338562011719, | |
| "loss": 0.639, | |
| "rewards/accuracies": 0.621874988079071, | |
| "rewards/chosen": 0.009362801909446716, | |
| "rewards/margins": 0.15911515057086945, | |
| "rewards/rejected": -0.14975234866142273, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 654.9042346572915, | |
| "learning_rate": 9.111768199053588e-09, | |
| "logits/chosen": -0.8516262173652649, | |
| "logits/rejected": -0.5497715473175049, | |
| "logps/chosen": -318.9173889160156, | |
| "logps/rejected": -284.2920837402344, | |
| "loss": 0.6303, | |
| "rewards/accuracies": 0.609375, | |
| "rewards/chosen": -0.07476776093244553, | |
| "rewards/margins": 0.15329131484031677, | |
| "rewards/rejected": -0.2280590981245041, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 568.2894000484466, | |
| "learning_rate": 8.819910152028871e-09, | |
| "logits/chosen": -0.7658065557479858, | |
| "logits/rejected": -0.4776793122291565, | |
| "logps/chosen": -335.7439270019531, | |
| "logps/rejected": -302.370849609375, | |
| "loss": 0.6175, | |
| "rewards/accuracies": 0.640625, | |
| "rewards/chosen": 0.008360857143998146, | |
| "rewards/margins": 0.20505543053150177, | |
| "rewards/rejected": -0.19669455289840698, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 569.4638082407581, | |
| "learning_rate": 8.492821239247364e-09, | |
| "logits/chosen": -0.851113498210907, | |
| "logits/rejected": -0.49246683716773987, | |
| "logps/chosen": -349.08477783203125, | |
| "logps/rejected": -308.5341491699219, | |
| "loss": 0.5935, | |
| "rewards/accuracies": 0.7437499761581421, | |
| "rewards/chosen": 0.11443378776311874, | |
| "rewards/margins": 0.3531562387943268, | |
| "rewards/rejected": -0.23872247338294983, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 581.8336234971125, | |
| "learning_rate": 8.133518187573863e-09, | |
| "logits/chosen": -0.8286861181259155, | |
| "logits/rejected": -0.5028008818626404, | |
| "logps/chosen": -328.44915771484375, | |
| "logps/rejected": -298.2557373046875, | |
| "loss": 0.5959, | |
| "rewards/accuracies": 0.643750011920929, | |
| "rewards/chosen": 0.06084731966257095, | |
| "rewards/margins": 0.24498350918293, | |
| "rewards/rejected": -0.18413618206977844, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 566.985090918969, | |
| "learning_rate": 7.745314833479833e-09, | |
| "logits/chosen": -1.0121524333953857, | |
| "logits/rejected": -0.5360809564590454, | |
| "logps/chosen": -338.01531982421875, | |
| "logps/rejected": -293.3200378417969, | |
| "loss": 0.5864, | |
| "rewards/accuracies": 0.7281249761581421, | |
| "rewards/chosen": 0.14776429533958435, | |
| "rewards/margins": 0.35846027731895447, | |
| "rewards/rejected": -0.21069595217704773, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 585.5307136387664, | |
| "learning_rate": 7.33179155967327e-09, | |
| "logits/chosen": -0.9024865031242371, | |
| "logits/rejected": -0.5908719301223755, | |
| "logps/chosen": -331.0682373046875, | |
| "logps/rejected": -298.38677978515625, | |
| "loss": 0.5718, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/chosen": 0.1406635046005249, | |
| "rewards/margins": 0.32861852645874023, | |
| "rewards/rejected": -0.18795502185821533, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 608.4424256652742, | |
| "learning_rate": 6.896762273384178e-09, | |
| "logits/chosen": -0.9404014348983765, | |
| "logits/rejected": -0.5414465069770813, | |
| "logps/chosen": -340.7105407714844, | |
| "logps/rejected": -301.7948303222656, | |
| "loss": 0.5625, | |
| "rewards/accuracies": 0.7406250238418579, | |
| "rewards/chosen": 0.29647737741470337, | |
| "rewards/margins": 0.45771312713623047, | |
| "rewards/rejected": -0.1612357348203659, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 571.5105228832468, | |
| "learning_rate": 6.444239230863505e-09, | |
| "logits/chosen": -0.6664124131202698, | |
| "logits/rejected": -0.3767244815826416, | |
| "logps/chosen": -326.7174377441406, | |
| "logps/rejected": -292.18304443359375, | |
| "loss": 0.5516, | |
| "rewards/accuracies": 0.75, | |
| "rewards/chosen": 0.3695653975009918, | |
| "rewards/margins": 0.49222081899642944, | |
| "rewards/rejected": -0.12265541404485703, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 486.04829364539904, | |
| "learning_rate": 5.97839603251764e-09, | |
| "logits/chosen": -0.8600166440010071, | |
| "logits/rejected": -0.5389689803123474, | |
| "logps/chosen": -323.1247863769531, | |
| "logps/rejected": -290.40802001953125, | |
| "loss": 0.5408, | |
| "rewards/accuracies": 0.784375011920929, | |
| "rewards/chosen": 0.3320290446281433, | |
| "rewards/margins": 0.5290471315383911, | |
| "rewards/rejected": -0.19701813161373138, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 524.5665762946036, | |
| "learning_rate": 5.5035291299727915e-09, | |
| "logits/chosen": -1.0205037593841553, | |
| "logits/rejected": -0.6305373907089233, | |
| "logps/chosen": -351.1410827636719, | |
| "logps/rejected": -313.13812255859375, | |
| "loss": 0.5258, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": 0.40980952978134155, | |
| "rewards/margins": 0.5211332440376282, | |
| "rewards/rejected": -0.11132367700338364, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 474.67341086960977, | |
| "learning_rate": 5.024018200087854e-09, | |
| "logits/chosen": -0.836185097694397, | |
| "logits/rejected": -0.33586248755455017, | |
| "logps/chosen": -321.29168701171875, | |
| "logps/rejected": -280.28753662109375, | |
| "loss": 0.512, | |
| "rewards/accuracies": 0.7562500238418579, | |
| "rewards/chosen": 0.3657322824001312, | |
| "rewards/margins": 0.5857880711555481, | |
| "rewards/rejected": -0.22005578875541687, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 480.69197567309544, | |
| "learning_rate": 4.544285751384584e-09, | |
| "logits/chosen": -0.9048161506652832, | |
| "logits/rejected": -0.6336894631385803, | |
| "logps/chosen": -329.5954895019531, | |
| "logps/rejected": -297.79901123046875, | |
| "loss": 0.5067, | |
| "rewards/accuracies": 0.721875011920929, | |
| "rewards/chosen": 0.41357460618019104, | |
| "rewards/margins": 0.5688098669052124, | |
| "rewards/rejected": -0.1552352011203766, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 498.26717868032813, | |
| "learning_rate": 4.068756335443199e-09, | |
| "logits/chosen": -0.8500760793685913, | |
| "logits/rejected": -0.501125693321228, | |
| "logps/chosen": -339.07012939453125, | |
| "logps/rejected": -299.48095703125, | |
| "loss": 0.514, | |
| "rewards/accuracies": 0.7906249761581421, | |
| "rewards/chosen": 0.5280696153640747, | |
| "rewards/margins": 0.6353160738945007, | |
| "rewards/rejected": -0.10724644362926483, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 522.8370181213115, | |
| "learning_rate": 3.6018157394549284e-09, | |
| "logits/chosen": -0.8433824777603149, | |
| "logits/rejected": -0.4627400040626526, | |
| "logps/chosen": -332.1639709472656, | |
| "logps/rejected": -297.5298156738281, | |
| "loss": 0.5207, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/chosen": 0.4683798849582672, | |
| "rewards/margins": 0.5844911336898804, | |
| "rewards/rejected": -0.11611130088567734, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 521.1145144981034, | |
| "learning_rate": 3.14777053629687e-09, | |
| "logits/chosen": -1.0663576126098633, | |
| "logits/rejected": -0.6788166761398315, | |
| "logps/chosen": -336.2250671386719, | |
| "logps/rejected": -296.2794494628906, | |
| "loss": 0.5124, | |
| "rewards/accuracies": 0.7593749761581421, | |
| "rewards/chosen": 0.5691989660263062, | |
| "rewards/margins": 0.702237069606781, | |
| "rewards/rejected": -0.13303814828395844, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 487.7677359334702, | |
| "learning_rate": 2.7108083651970002e-09, | |
| "logits/chosen": -0.7713569402694702, | |
| "logits/rejected": -0.4026997983455658, | |
| "logps/chosen": -327.7779235839844, | |
| "logps/rejected": -290.0624084472656, | |
| "loss": 0.5045, | |
| "rewards/accuracies": 0.7406250238418579, | |
| "rewards/chosen": 0.5247091054916382, | |
| "rewards/margins": 0.6842475533485413, | |
| "rewards/rejected": -0.1595384031534195, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 524.4673235373901, | |
| "learning_rate": 2.294959309319086e-09, | |
| "logits/chosen": -0.8702203035354614, | |
| "logits/rejected": -0.6658123135566711, | |
| "logps/chosen": -328.04638671875, | |
| "logps/rejected": -302.77777099609375, | |
| "loss": 0.5103, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/chosen": 0.6019162535667419, | |
| "rewards/margins": 0.5868763327598572, | |
| "rewards/rejected": 0.015039998106658459, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 553.8708647904535, | |
| "learning_rate": 1.9040587264803672e-09, | |
| "logits/chosen": -0.9641194343566895, | |
| "logits/rejected": -0.4711450934410095, | |
| "logps/chosen": -340.99169921875, | |
| "logps/rejected": -293.9861145019531, | |
| "loss": 0.4939, | |
| "rewards/accuracies": 0.831250011920929, | |
| "rewards/chosen": 0.56943279504776, | |
| "rewards/margins": 0.7665254473686218, | |
| "rewards/rejected": -0.1970926821231842, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 453.07875520502444, | |
| "learning_rate": 1.5417118758126409e-09, | |
| "logits/chosen": -0.8815242648124695, | |
| "logits/rejected": -0.4348044991493225, | |
| "logps/chosen": -342.6517028808594, | |
| "logps/rejected": -296.92169189453125, | |
| "loss": 0.4934, | |
| "rewards/accuracies": 0.7906249761581421, | |
| "rewards/chosen": 0.5705780982971191, | |
| "rewards/margins": 0.8008774518966675, | |
| "rewards/rejected": -0.23029938340187073, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 499.34891989016415, | |
| "learning_rate": 1.2112606666135601e-09, | |
| "logits/chosen": -0.9316185712814331, | |
| "logits/rejected": -0.5389292240142822, | |
| "logps/chosen": -333.5206604003906, | |
| "logps/rejected": -297.6076354980469, | |
| "loss": 0.4978, | |
| "rewards/accuracies": 0.765625, | |
| "rewards/chosen": 0.5433750748634338, | |
| "rewards/margins": 0.6790112257003784, | |
| "rewards/rejected": -0.135636106133461, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 475.94785473220173, | |
| "learning_rate": 9.157528360620415e-10, | |
| "logits/chosen": -0.8223875164985657, | |
| "logits/rejected": -0.5513488054275513, | |
| "logps/chosen": -312.7162780761719, | |
| "logps/rejected": -280.6097106933594, | |
| "loss": 0.4933, | |
| "rewards/accuracies": 0.7593749761581421, | |
| "rewards/chosen": 0.5738901495933533, | |
| "rewards/margins": 0.6515259146690369, | |
| "rewards/rejected": -0.07763569802045822, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 530.0260445258433, | |
| "learning_rate": 6.579138400703716e-10, | |
| "logits/chosen": -0.8587888479232788, | |
| "logits/rejected": -0.4476223587989807, | |
| "logps/chosen": -334.20648193359375, | |
| "logps/rejected": -295.112548828125, | |
| "loss": 0.4913, | |
| "rewards/accuracies": 0.7906249761581421, | |
| "rewards/chosen": 0.6548627018928528, | |
| "rewards/margins": 0.7542473077774048, | |
| "rewards/rejected": -0.09938466548919678, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 487.39892256915766, | |
| "learning_rate": 4.401217165224564e-10, | |
| "logits/chosen": -0.7274507284164429, | |
| "logits/rejected": -0.45758286118507385, | |
| "logps/chosen": -322.195068359375, | |
| "logps/rejected": -289.47064208984375, | |
| "loss": 0.4876, | |
| "rewards/accuracies": 0.78125, | |
| "rewards/chosen": 0.6047518849372864, | |
| "rewards/margins": 0.6844498515129089, | |
| "rewards/rejected": -0.07969798892736435, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 474.27503066220174, | |
| "learning_rate": 2.643851527335006e-10, | |
| "logits/chosen": -0.9080432653427124, | |
| "logits/rejected": -0.5377383232116699, | |
| "logps/chosen": -331.7919921875, | |
| "logps/rejected": -301.7752685546875, | |
| "loss": 0.4856, | |
| "rewards/accuracies": 0.7718750238418579, | |
| "rewards/chosen": 0.6742402911186218, | |
| "rewards/margins": 0.7511230111122131, | |
| "rewards/rejected": -0.07688269764184952, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 515.521744630777, | |
| "learning_rate": 1.3232495941396638e-10, | |
| "logits/chosen": -0.9773859977722168, | |
| "logits/rejected": -0.6425100564956665, | |
| "logps/chosen": -329.1192321777344, | |
| "logps/rejected": -293.9158020019531, | |
| "loss": 0.4902, | |
| "rewards/accuracies": 0.78125, | |
| "rewards/chosen": 0.5788453817367554, | |
| "rewards/margins": 0.6871310472488403, | |
| "rewards/rejected": -0.10828564316034317, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 474.472293237774, | |
| "learning_rate": 4.515912200264427e-11, | |
| "logits/chosen": -0.9029630422592163, | |
| "logits/rejected": -0.4482271075248718, | |
| "logps/chosen": -331.9292907714844, | |
| "logps/rejected": -287.7762451171875, | |
| "loss": 0.4845, | |
| "rewards/accuracies": 0.7906249761581421, | |
| "rewards/chosen": 0.5662914514541626, | |
| "rewards/margins": 0.7054949998855591, | |
| "rewards/rejected": -0.1392035186290741, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 466.2251927040291, | |
| "learning_rate": 3.691567239743621e-12, | |
| "logits/chosen": -0.866126537322998, | |
| "logits/rejected": -0.38964423537254333, | |
| "logps/chosen": -346.421875, | |
| "logps/rejected": -304.1325988769531, | |
| "loss": 0.4772, | |
| "rewards/accuracies": 0.8031250238418579, | |
| "rewards/chosen": 0.6508310437202454, | |
| "rewards/margins": 0.8615090250968933, | |
| "rewards/rejected": -0.21067801117897034, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "step": 364, | |
| "total_flos": 0.0, | |
| "train_loss": 0.5661277400923299, | |
| "train_runtime": 10889.322, | |
| "train_samples_per_second": 8.572, | |
| "train_steps_per_second": 0.033 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 364, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |