| { | |
| "best_metric": 5.759253978729248, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.05201222287237501, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000260061114361875, | |
| "grad_norm": 4.700757026672363, | |
| "learning_rate": 5e-06, | |
| "loss": 6.7348, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000260061114361875, | |
| "eval_loss": 6.605810642242432, | |
| "eval_runtime": 49.1131, | |
| "eval_samples_per_second": 131.879, | |
| "eval_steps_per_second": 65.95, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00052012222872375, | |
| "grad_norm": 4.639775276184082, | |
| "learning_rate": 1e-05, | |
| "loss": 6.8599, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007801833430856252, | |
| "grad_norm": 5.271045684814453, | |
| "learning_rate": 1.5e-05, | |
| "loss": 6.6529, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010402444574475, | |
| "grad_norm": 5.043214797973633, | |
| "learning_rate": 2e-05, | |
| "loss": 6.4242, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001300305571809375, | |
| "grad_norm": 4.489984512329102, | |
| "learning_rate": 2.5e-05, | |
| "loss": 6.4993, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015603666861712503, | |
| "grad_norm": 4.286848545074463, | |
| "learning_rate": 3e-05, | |
| "loss": 6.7653, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018204278005331254, | |
| "grad_norm": 4.734979152679443, | |
| "learning_rate": 3.5e-05, | |
| "loss": 6.7299, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002080488914895, | |
| "grad_norm": 4.462507724761963, | |
| "learning_rate": 4e-05, | |
| "loss": 6.3463, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0023405500292568754, | |
| "grad_norm": 3.9474422931671143, | |
| "learning_rate": 4.5e-05, | |
| "loss": 6.5243, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00260061114361875, | |
| "grad_norm": 4.359175682067871, | |
| "learning_rate": 5e-05, | |
| "loss": 6.7619, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0028606722579806254, | |
| "grad_norm": 3.6640963554382324, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 6.4133, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0031207333723425007, | |
| "grad_norm": 3.34222412109375, | |
| "learning_rate": 6e-05, | |
| "loss": 6.0977, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0033807944867043755, | |
| "grad_norm": 3.309803009033203, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 6.1704, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0036408556010662507, | |
| "grad_norm": 3.5255839824676514, | |
| "learning_rate": 7e-05, | |
| "loss": 6.4846, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0039009167154281255, | |
| "grad_norm": 2.9046642780303955, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 6.4176, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00416097782979, | |
| "grad_norm": 3.0866973400115967, | |
| "learning_rate": 8e-05, | |
| "loss": 5.9843, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004421038944151876, | |
| "grad_norm": 2.954580545425415, | |
| "learning_rate": 8.5e-05, | |
| "loss": 6.2319, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004681100058513751, | |
| "grad_norm": 2.644932746887207, | |
| "learning_rate": 9e-05, | |
| "loss": 6.5849, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004941161172875626, | |
| "grad_norm": 2.613598346710205, | |
| "learning_rate": 9.5e-05, | |
| "loss": 6.1687, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0052012222872375, | |
| "grad_norm": 2.6821439266204834, | |
| "learning_rate": 0.0001, | |
| "loss": 6.3548, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005461283401599376, | |
| "grad_norm": 2.6434664726257324, | |
| "learning_rate": 9.999238475781957e-05, | |
| "loss": 6.1017, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005721344515961251, | |
| "grad_norm": 2.6511456966400146, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 6.0292, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005981405630323126, | |
| "grad_norm": 2.6858441829681396, | |
| "learning_rate": 9.99314767377287e-05, | |
| "loss": 6.1429, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006241466744685001, | |
| "grad_norm": 2.4335083961486816, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 5.9954, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006501527859046876, | |
| "grad_norm": 2.553853988647461, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 6.2822, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006761588973408751, | |
| "grad_norm": 2.6574552059173584, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 6.0658, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007021650087770626, | |
| "grad_norm": 2.649275779724121, | |
| "learning_rate": 9.962730758206611e-05, | |
| "loss": 6.1537, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0072817112021325014, | |
| "grad_norm": 2.73947811126709, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 6.2567, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007541772316494376, | |
| "grad_norm": 2.5566582679748535, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 6.0508, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.007801833430856251, | |
| "grad_norm": 2.3408713340759277, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 6.1741, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008061894545218126, | |
| "grad_norm": 2.44429087638855, | |
| "learning_rate": 9.908135917238321e-05, | |
| "loss": 6.0916, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.00832195565958, | |
| "grad_norm": 2.625361442565918, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 5.9718, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.008582016773941877, | |
| "grad_norm": 2.38539457321167, | |
| "learning_rate": 9.871850323926177e-05, | |
| "loss": 6.0312, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.008842077888303752, | |
| "grad_norm": 2.4743857383728027, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 6.0379, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009102139002665627, | |
| "grad_norm": 2.776047468185425, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.1597, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009362200117027502, | |
| "grad_norm": 2.8223772048950195, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 6.0539, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009622261231389376, | |
| "grad_norm": 2.7097480297088623, | |
| "learning_rate": 9.781523779815179e-05, | |
| "loss": 5.7932, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.009882322345751251, | |
| "grad_norm": 2.4470372200012207, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 6.0691, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010142383460113126, | |
| "grad_norm": 2.8650152683258057, | |
| "learning_rate": 9.727592877996585e-05, | |
| "loss": 6.1383, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.010402444574475, | |
| "grad_norm": 2.1736435890197754, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 5.8534, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010662505688836877, | |
| "grad_norm": 2.3826494216918945, | |
| "learning_rate": 9.667902132486009e-05, | |
| "loss": 5.8372, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.010922566803198752, | |
| "grad_norm": 2.3414485454559326, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 5.9025, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011182627917560627, | |
| "grad_norm": 3.2391109466552734, | |
| "learning_rate": 9.602524267262203e-05, | |
| "loss": 6.2408, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.011442689031922502, | |
| "grad_norm": 2.560239791870117, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 5.844, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.011702750146284377, | |
| "grad_norm": 4.429433345794678, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 5.9313, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.011962811260646251, | |
| "grad_norm": 5.025948524475098, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 6.1156, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.012222872375008126, | |
| "grad_norm": 4.9493727684021, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 6.1575, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.012482933489370003, | |
| "grad_norm": 2.9699819087982178, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 5.8556, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.012742994603731878, | |
| "grad_norm": 2.35396409034729, | |
| "learning_rate": 9.373098535696979e-05, | |
| "loss": 5.7382, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.013003055718093752, | |
| "grad_norm": 1.974317193031311, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 6.0416, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013003055718093752, | |
| "eval_loss": 5.998004913330078, | |
| "eval_runtime": 48.629, | |
| "eval_samples_per_second": 133.192, | |
| "eval_steps_per_second": 66.606, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013263116832455627, | |
| "grad_norm": 4.363042831420898, | |
| "learning_rate": 9.285836503510562e-05, | |
| "loss": 5.9608, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.013523177946817502, | |
| "grad_norm": 4.278781414031982, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 6.3781, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.013783239061179377, | |
| "grad_norm": 3.778721332550049, | |
| "learning_rate": 9.193352839727121e-05, | |
| "loss": 6.2402, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.014043300175541252, | |
| "grad_norm": 3.498566150665283, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 5.8672, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.014303361289903128, | |
| "grad_norm": 2.5575318336486816, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 6.2251, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.014563422404265003, | |
| "grad_norm": 2.7712318897247314, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 5.8533, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.014823483518626878, | |
| "grad_norm": 2.6722428798675537, | |
| "learning_rate": 8.993177550236464e-05, | |
| "loss": 6.2118, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.015083544632988753, | |
| "grad_norm": 2.6320745944976807, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 5.9229, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.015343605747350627, | |
| "grad_norm": 3.009500503540039, | |
| "learning_rate": 8.885729807284856e-05, | |
| "loss": 6.1045, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.015603666861712502, | |
| "grad_norm": 2.7028679847717285, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 5.9121, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01586372797607438, | |
| "grad_norm": 2.4579215049743652, | |
| "learning_rate": 8.773547901113862e-05, | |
| "loss": 5.6692, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.01612378909043625, | |
| "grad_norm": 2.4235904216766357, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 6.0567, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.016383850204798128, | |
| "grad_norm": 2.282179594039917, | |
| "learning_rate": 8.656768508095853e-05, | |
| "loss": 5.9487, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.01664391131916, | |
| "grad_norm": 2.4681618213653564, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 5.8193, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.016903972433521878, | |
| "grad_norm": 2.345444440841675, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.7292, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.017164033547883754, | |
| "grad_norm": 2.1743881702423096, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 5.7868, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.017424094662245627, | |
| "grad_norm": 2.0475363731384277, | |
| "learning_rate": 8.409991800312493e-05, | |
| "loss": 5.8631, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.017684155776607504, | |
| "grad_norm": 2.0247652530670166, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 5.9889, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.017944216890969377, | |
| "grad_norm": 2.2418599128723145, | |
| "learning_rate": 8.280295144952536e-05, | |
| "loss": 6.0085, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.018204278005331254, | |
| "grad_norm": 2.2492949962615967, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 5.8585, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.018464339119693127, | |
| "grad_norm": 2.267843008041382, | |
| "learning_rate": 8.146601955249188e-05, | |
| "loss": 5.6249, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.018724400234055003, | |
| "grad_norm": 2.3722450733184814, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 5.8605, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.018984461348416876, | |
| "grad_norm": 2.5645058155059814, | |
| "learning_rate": 8.009075115760243e-05, | |
| "loss": 5.6836, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.019244522462778753, | |
| "grad_norm": 1.8278781175613403, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 5.7605, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.01950458357714063, | |
| "grad_norm": 1.9225795269012451, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 6.0398, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.019764644691502502, | |
| "grad_norm": 2.0590267181396484, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 5.787, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.02002470580586438, | |
| "grad_norm": 2.1128058433532715, | |
| "learning_rate": 7.723195175075136e-05, | |
| "loss": 5.5382, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.020284766920226252, | |
| "grad_norm": 1.947939157485962, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 5.8782, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.02054482803458813, | |
| "grad_norm": 2.0571346282958984, | |
| "learning_rate": 7.575190374550272e-05, | |
| "loss": 6.0179, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.02080488914895, | |
| "grad_norm": 2.2099356651306152, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 5.6631, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.021064950263311878, | |
| "grad_norm": 2.370307207107544, | |
| "learning_rate": 7.424048101231686e-05, | |
| "loss": 5.5898, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.021325011377673755, | |
| "grad_norm": 2.1935746669769287, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 5.9512, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.021585072492035628, | |
| "grad_norm": 2.0591251850128174, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 5.8631, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.021845133606397504, | |
| "grad_norm": 2.2366886138916016, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 5.7982, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.022105194720759377, | |
| "grad_norm": 2.359128475189209, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 5.8195, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.022365255835121254, | |
| "grad_norm": 2.3458919525146484, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 5.8264, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.022625316949483127, | |
| "grad_norm": 2.4972236156463623, | |
| "learning_rate": 6.953655642446368e-05, | |
| "loss": 5.7646, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.022885378063845004, | |
| "grad_norm": 2.109933853149414, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 5.9329, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.02314543917820688, | |
| "grad_norm": 2.2802915573120117, | |
| "learning_rate": 6.7918397477265e-05, | |
| "loss": 5.6465, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.023405500292568753, | |
| "grad_norm": 2.1097252368927, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 5.9014, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02366556140693063, | |
| "grad_norm": 2.1285314559936523, | |
| "learning_rate": 6.627840772285784e-05, | |
| "loss": 5.8136, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.023925622521292503, | |
| "grad_norm": 2.2824885845184326, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 5.786, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.02418568363565438, | |
| "grad_norm": 2.440842866897583, | |
| "learning_rate": 6.461858523613684e-05, | |
| "loss": 5.747, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.024445744750016252, | |
| "grad_norm": 2.4772531986236572, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 5.7615, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.02470580586437813, | |
| "grad_norm": 1.9417319297790527, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 5.6267, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.024965866978740005, | |
| "grad_norm": 2.200648784637451, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 5.4595, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.02522592809310188, | |
| "grad_norm": 1.9711750745773315, | |
| "learning_rate": 6.124755271719325e-05, | |
| "loss": 5.8309, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.025485989207463755, | |
| "grad_norm": 2.5392403602600098, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 5.8212, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.025746050321825628, | |
| "grad_norm": 1.87886643409729, | |
| "learning_rate": 5.9540449768827246e-05, | |
| "loss": 5.7186, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.026006111436187505, | |
| "grad_norm": 2.1092851161956787, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 5.8411, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.026006111436187505, | |
| "eval_loss": 5.840994834899902, | |
| "eval_runtime": 48.6683, | |
| "eval_samples_per_second": 133.085, | |
| "eval_steps_per_second": 66.553, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.026266172550549378, | |
| "grad_norm": 2.57004714012146, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 5.9867, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.026526233664911254, | |
| "grad_norm": 2.1859915256500244, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 6.0568, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.02678629477927313, | |
| "grad_norm": 2.2751128673553467, | |
| "learning_rate": 5.6093467170257374e-05, | |
| "loss": 5.8706, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.027046355893635004, | |
| "grad_norm": 2.1009652614593506, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 5.9817, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.02730641700799688, | |
| "grad_norm": 2.266655445098877, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 5.6929, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.027566478122358753, | |
| "grad_norm": 1.9885139465332031, | |
| "learning_rate": 5.348782368720626e-05, | |
| "loss": 5.978, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.02782653923672063, | |
| "grad_norm": 2.028961420059204, | |
| "learning_rate": 5.26167978121472e-05, | |
| "loss": 5.8351, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.028086600351082503, | |
| "grad_norm": 1.9886070489883423, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 5.8824, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.02834666146544438, | |
| "grad_norm": 2.343224048614502, | |
| "learning_rate": 5.0872620321864185e-05, | |
| "loss": 5.9582, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.028606722579806256, | |
| "grad_norm": 2.5639307498931885, | |
| "learning_rate": 5e-05, | |
| "loss": 5.8952, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02886678369416813, | |
| "grad_norm": 2.0477116107940674, | |
| "learning_rate": 4.912737967813583e-05, | |
| "loss": 5.9346, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.029126844808530006, | |
| "grad_norm": 1.8866691589355469, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 6.0466, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.02938690592289188, | |
| "grad_norm": 1.9691741466522217, | |
| "learning_rate": 4.738320218785281e-05, | |
| "loss": 5.5029, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.029646967037253755, | |
| "grad_norm": 1.8502812385559082, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 5.7583, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.02990702815161563, | |
| "grad_norm": 2.5639379024505615, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 5.3675, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.030167089265977505, | |
| "grad_norm": 1.9151495695114136, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 5.7421, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.030427150380339378, | |
| "grad_norm": 1.8344489336013794, | |
| "learning_rate": 4.390653282974264e-05, | |
| "loss": 5.871, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.030687211494701255, | |
| "grad_norm": 1.7897135019302368, | |
| "learning_rate": 4.3041344951996746e-05, | |
| "loss": 5.7288, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.03094727260906313, | |
| "grad_norm": 2.029815196990967, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 5.9199, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.031207333723425004, | |
| "grad_norm": 1.9268794059753418, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 5.8271, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.03146739483778688, | |
| "grad_norm": 1.8820242881774902, | |
| "learning_rate": 4.045955023117276e-05, | |
| "loss": 5.7487, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.03172745595214876, | |
| "grad_norm": 1.9745794534683228, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 5.6484, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.03198751706651063, | |
| "grad_norm": 1.8738607168197632, | |
| "learning_rate": 3.875244728280676e-05, | |
| "loss": 5.9072, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.0322475781808725, | |
| "grad_norm": 2.0338311195373535, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 5.5293, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.03250763929523438, | |
| "grad_norm": 2.4185123443603516, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 5.8123, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.032767700409596257, | |
| "grad_norm": 2.2349812984466553, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 5.9097, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.03302776152395813, | |
| "grad_norm": 2.378011703491211, | |
| "learning_rate": 3.5381414763863166e-05, | |
| "loss": 5.8261, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.03328782263832, | |
| "grad_norm": 2.0955443382263184, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 5.8907, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.03354788375268188, | |
| "grad_norm": 2.049766778945923, | |
| "learning_rate": 3.372159227714218e-05, | |
| "loss": 5.6951, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.033807944867043756, | |
| "grad_norm": 2.211913585662842, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 5.6701, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.03406800598140563, | |
| "grad_norm": 2.1762237548828125, | |
| "learning_rate": 3.2081602522734986e-05, | |
| "loss": 5.8482, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.03432806709576751, | |
| "grad_norm": 1.9880789518356323, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 5.8196, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.03458812821012938, | |
| "grad_norm": 2.4828646183013916, | |
| "learning_rate": 3.046344357553632e-05, | |
| "loss": 5.5032, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.034848189324491255, | |
| "grad_norm": 2.043897867202759, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 5.712, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.03510825043885313, | |
| "grad_norm": 2.0667715072631836, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 5.7623, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.03536831155321501, | |
| "grad_norm": 1.8965405225753784, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 6.0675, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.03562837266757688, | |
| "grad_norm": 2.2518186569213867, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 5.9103, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.035888433781938754, | |
| "grad_norm": 2.1538784503936768, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 6.0621, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.03614849489630063, | |
| "grad_norm": 2.6064345836639404, | |
| "learning_rate": 2.575951898768315e-05, | |
| "loss": 5.2939, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.03640855601066251, | |
| "grad_norm": 2.093737840652466, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 5.6876, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.03666861712502438, | |
| "grad_norm": 1.951988697052002, | |
| "learning_rate": 2.4248096254497288e-05, | |
| "loss": 5.6047, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.03692867823938625, | |
| "grad_norm": 2.254817247390747, | |
| "learning_rate": 2.350403678833976e-05, | |
| "loss": 5.9507, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.03718873935374813, | |
| "grad_norm": 2.305563449859619, | |
| "learning_rate": 2.2768048249248648e-05, | |
| "loss": 6.1418, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.037448800468110006, | |
| "grad_norm": 2.025839328765869, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 5.6341, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.03770886158247188, | |
| "grad_norm": 2.292506456375122, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 5.681, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.03796892269683375, | |
| "grad_norm": 2.450554132461548, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 6.2452, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.03822898381119563, | |
| "grad_norm": 1.7618736028671265, | |
| "learning_rate": 1.9909248842397584e-05, | |
| "loss": 5.5073, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.038489044925557506, | |
| "grad_norm": 1.966064453125, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 5.7759, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.03874910603991938, | |
| "grad_norm": 2.008685350418091, | |
| "learning_rate": 1.8533980447508137e-05, | |
| "loss": 5.9435, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.03900916715428126, | |
| "grad_norm": 2.194380521774292, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 6.1454, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03900916715428126, | |
| "eval_loss": 5.7715630531311035, | |
| "eval_runtime": 48.9592, | |
| "eval_samples_per_second": 132.294, | |
| "eval_steps_per_second": 66.157, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03926922826864313, | |
| "grad_norm": 2.1486167907714844, | |
| "learning_rate": 1.7197048550474643e-05, | |
| "loss": 5.9314, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.039529289383005005, | |
| "grad_norm": 2.113476276397705, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 5.6945, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.03978935049736688, | |
| "grad_norm": 2.3845126628875732, | |
| "learning_rate": 1.5900081996875083e-05, | |
| "loss": 6.0969, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.04004941161172876, | |
| "grad_norm": 2.2422235012054443, | |
| "learning_rate": 1.526708147705013e-05, | |
| "loss": 5.7678, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.04030947272609063, | |
| "grad_norm": 2.3688573837280273, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 5.7291, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.040569533840452504, | |
| "grad_norm": 2.266603469848633, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 6.0137, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.040829594954814384, | |
| "grad_norm": 2.143157482147217, | |
| "learning_rate": 1.3432314919041478e-05, | |
| "loss": 5.6486, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.04108965606917626, | |
| "grad_norm": 2.3287534713745117, | |
| "learning_rate": 1.2842758726130283e-05, | |
| "loss": 5.6967, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.04134971718353813, | |
| "grad_norm": 2.0474727153778076, | |
| "learning_rate": 1.22645209888614e-05, | |
| "loss": 5.9549, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.0416097782979, | |
| "grad_norm": 2.322507619857788, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 5.6328, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.04186983941226188, | |
| "grad_norm": 2.4897751808166504, | |
| "learning_rate": 1.1142701927151456e-05, | |
| "loss": 5.7139, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.042129900526623756, | |
| "grad_norm": 1.8576676845550537, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 6.0336, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.04238996164098563, | |
| "grad_norm": 2.2130608558654785, | |
| "learning_rate": 1.006822449763537e-05, | |
| "loss": 5.5478, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.04265002275534751, | |
| "grad_norm": 2.381807327270508, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 5.6933, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.04291008386970938, | |
| "grad_norm": 2.003005027770996, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 5.9695, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.043170144984071256, | |
| "grad_norm": 1.9043495655059814, | |
| "learning_rate": 8.548121372247918e-06, | |
| "loss": 5.8895, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.04343020609843313, | |
| "grad_norm": 1.9111559391021729, | |
| "learning_rate": 8.066471602728803e-06, | |
| "loss": 5.8929, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.04369026721279501, | |
| "grad_norm": 1.8936721086502075, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 5.9478, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.04395032832715688, | |
| "grad_norm": 2.007209300994873, | |
| "learning_rate": 7.1416349648943894e-06, | |
| "loss": 5.9119, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.044210389441518755, | |
| "grad_norm": 2.0411062240600586, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 5.9512, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.044470450555880635, | |
| "grad_norm": 1.808025598526001, | |
| "learning_rate": 6.269014643030213e-06, | |
| "loss": 5.82, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.04473051167024251, | |
| "grad_norm": 1.875134825706482, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 5.835, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.04499057278460438, | |
| "grad_norm": 1.7879668474197388, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 5.6259, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.045250633898966254, | |
| "grad_norm": 2.106720209121704, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 5.7261, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.045510695013328134, | |
| "grad_norm": 1.7821826934814453, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 5.6791, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.04577075612769001, | |
| "grad_norm": 1.8573359251022339, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 5.9206, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.04603081724205188, | |
| "grad_norm": 1.8888030052185059, | |
| "learning_rate": 3.974757327377981e-06, | |
| "loss": 5.6468, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.04629087835641376, | |
| "grad_norm": 1.8285032510757446, | |
| "learning_rate": 3.6408072716606346e-06, | |
| "loss": 5.5881, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.04655093947077563, | |
| "grad_norm": 1.9863262176513672, | |
| "learning_rate": 3.3209786751399187e-06, | |
| "loss": 5.722, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.046811000585137506, | |
| "grad_norm": 2.2431719303131104, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 5.6575, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.04707106169949938, | |
| "grad_norm": 2.047182321548462, | |
| "learning_rate": 2.724071220034158e-06, | |
| "loss": 5.4315, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.04733112281386126, | |
| "grad_norm": 1.8060697317123413, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 5.8507, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.04759118392822313, | |
| "grad_norm": 1.9971647262573242, | |
| "learning_rate": 2.1847622018482283e-06, | |
| "loss": 5.7017, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.047851245042585006, | |
| "grad_norm": 2.5897560119628906, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 5.5973, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.048111306156946886, | |
| "grad_norm": 2.2017526626586914, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 5.8183, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.04837136727130876, | |
| "grad_norm": 2.3036229610443115, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 5.7241, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.04863142838567063, | |
| "grad_norm": 2.3444440364837646, | |
| "learning_rate": 1.2814967607382432e-06, | |
| "loss": 5.7225, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.048891489500032505, | |
| "grad_norm": 2.1423869132995605, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 5.7248, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.049151550614394385, | |
| "grad_norm": 2.1155991554260254, | |
| "learning_rate": 9.186408276168013e-07, | |
| "loss": 5.5723, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.04941161172875626, | |
| "grad_norm": 2.301825761795044, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 5.7194, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.04967167284311813, | |
| "grad_norm": 2.186354160308838, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 5.5791, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.04993173395748001, | |
| "grad_norm": 2.2333290576934814, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 5.763, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.050191795071841884, | |
| "grad_norm": 2.092721700668335, | |
| "learning_rate": 3.7269241793390085e-07, | |
| "loss": 5.76, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.05045185618620376, | |
| "grad_norm": 2.0245654582977295, | |
| "learning_rate": 2.7390523158633554e-07, | |
| "loss": 5.5846, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.05071191730056563, | |
| "grad_norm": 2.045283079147339, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 5.6608, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.05097197841492751, | |
| "grad_norm": 2.104609727859497, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 6.1454, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.05123203952928938, | |
| "grad_norm": 2.0057427883148193, | |
| "learning_rate": 6.852326227130834e-08, | |
| "loss": 5.6056, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.051492100643651256, | |
| "grad_norm": 1.982209324836731, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 5.5759, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.051752161758013136, | |
| "grad_norm": 2.1231882572174072, | |
| "learning_rate": 7.615242180436522e-09, | |
| "loss": 5.8412, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.05201222287237501, | |
| "grad_norm": 2.233738660812378, | |
| "learning_rate": 0.0, | |
| "loss": 6.0729, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05201222287237501, | |
| "eval_loss": 5.759253978729248, | |
| "eval_runtime": 49.0339, | |
| "eval_samples_per_second": 132.092, | |
| "eval_steps_per_second": 66.056, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 140636376268800.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |