| { | |
| "best_metric": 0.6248776316642761, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.13619339462036092, | |
| "eval_steps": 100, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001361933946203609, | |
| "grad_norm": 6.723554611206055, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8744, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001361933946203609, | |
| "eval_loss": 1.29380464553833, | |
| "eval_runtime": 151.1717, | |
| "eval_samples_per_second": 8.183, | |
| "eval_steps_per_second": 2.051, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002723867892407218, | |
| "grad_norm": 4.329668045043945, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1685, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0040858018386108275, | |
| "grad_norm": 3.8606443405151367, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.9956, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005447735784814436, | |
| "grad_norm": 2.3737833499908447, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8493, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0068096697310180455, | |
| "grad_norm": 2.2130537033081055, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.0386, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008171603677221655, | |
| "grad_norm": 1.7720967531204224, | |
| "learning_rate": 3e-05, | |
| "loss": 0.9583, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009533537623425264, | |
| "grad_norm": 2.0626909732818604, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.9117, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010895471569628872, | |
| "grad_norm": 1.2568459510803223, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7207, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012257405515832482, | |
| "grad_norm": 1.2235935926437378, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.7072, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013619339462036091, | |
| "grad_norm": 1.4364486932754517, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7842, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0149812734082397, | |
| "grad_norm": 1.6137148141860962, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.7727, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01634320735444331, | |
| "grad_norm": 1.0391216278076172, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6199, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017705141300646918, | |
| "grad_norm": 1.2817028760910034, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.8018, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01906707524685053, | |
| "grad_norm": 1.4122101068496704, | |
| "learning_rate": 7e-05, | |
| "loss": 0.7091, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020429009193054137, | |
| "grad_norm": 1.2346439361572266, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6746, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021790943139257744, | |
| "grad_norm": 1.101813554763794, | |
| "learning_rate": 8e-05, | |
| "loss": 0.7234, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.023152877085461356, | |
| "grad_norm": 1.3349500894546509, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.7135, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.024514811031664963, | |
| "grad_norm": 1.274173617362976, | |
| "learning_rate": 9e-05, | |
| "loss": 0.6312, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.025876744977868574, | |
| "grad_norm": 1.210764765739441, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.6636, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.027238678924072182, | |
| "grad_norm": 1.1875956058502197, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6469, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028600612870275793, | |
| "grad_norm": 1.3556970357894897, | |
| "learning_rate": 9.999892908320647e-05, | |
| "loss": 0.6853, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0299625468164794, | |
| "grad_norm": 1.341584324836731, | |
| "learning_rate": 9.999571637870036e-05, | |
| "loss": 0.6772, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03132448076268301, | |
| "grad_norm": 1.3170078992843628, | |
| "learning_rate": 9.999036202410325e-05, | |
| "loss": 0.6173, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03268641470888662, | |
| "grad_norm": 1.4024509191513062, | |
| "learning_rate": 9.998286624877786e-05, | |
| "loss": 0.679, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03404834865509023, | |
| "grad_norm": 1.5314940214157104, | |
| "learning_rate": 9.997322937381829e-05, | |
| "loss": 0.6211, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.035410282601293835, | |
| "grad_norm": 1.3796993494033813, | |
| "learning_rate": 9.996145181203615e-05, | |
| "loss": 0.663, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03677221654749745, | |
| "grad_norm": 1.162498116493225, | |
| "learning_rate": 9.994753406794301e-05, | |
| "loss": 0.5981, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03813415049370106, | |
| "grad_norm": 1.214526653289795, | |
| "learning_rate": 9.99314767377287e-05, | |
| "loss": 0.7738, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03949608443990466, | |
| "grad_norm": 1.251236915588379, | |
| "learning_rate": 9.991328050923581e-05, | |
| "loss": 0.6466, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04085801838610827, | |
| "grad_norm": 1.2019500732421875, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.6285, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.042219952332311884, | |
| "grad_norm": 1.506635308265686, | |
| "learning_rate": 9.98704745668676e-05, | |
| "loss": 0.7005, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04358188627851549, | |
| "grad_norm": 1.2021490335464478, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 0.6355, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0449438202247191, | |
| "grad_norm": 1.1416049003601074, | |
| "learning_rate": 9.981912357541627e-05, | |
| "loss": 0.6532, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04630575417092271, | |
| "grad_norm": 1.165168285369873, | |
| "learning_rate": 9.97902463787331e-05, | |
| "loss": 0.6076, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04766768811712632, | |
| "grad_norm": 1.1205216646194458, | |
| "learning_rate": 9.975923633360985e-05, | |
| "loss": 0.5811, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.049029622063329927, | |
| "grad_norm": 1.0092084407806396, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.6334, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05039155600953354, | |
| "grad_norm": 1.0040332078933716, | |
| "learning_rate": 9.969082310281891e-05, | |
| "loss": 0.5839, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05175348995573715, | |
| "grad_norm": 1.1557093858718872, | |
| "learning_rate": 9.965342284774632e-05, | |
| "loss": 0.7276, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05311542390194075, | |
| "grad_norm": 1.0903106927871704, | |
| "learning_rate": 9.961389560529836e-05, | |
| "loss": 0.6504, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.054477357848144364, | |
| "grad_norm": 1.1416411399841309, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.5472, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.055839291794347976, | |
| "grad_norm": 0.9939647912979126, | |
| "learning_rate": 9.952846702217886e-05, | |
| "loss": 0.6051, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05720122574055159, | |
| "grad_norm": 1.759358286857605, | |
| "learning_rate": 9.948256934098352e-05, | |
| "loss": 0.6047, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05856315968675519, | |
| "grad_norm": 1.137244701385498, | |
| "learning_rate": 9.943455199120837e-05, | |
| "loss": 0.6423, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0599250936329588, | |
| "grad_norm": 1.1570804119110107, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.6577, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.06128702757916241, | |
| "grad_norm": 1.2725093364715576, | |
| "learning_rate": 9.933216660424395e-05, | |
| "loss": 0.7253, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06264896152536602, | |
| "grad_norm": 1.4316565990447998, | |
| "learning_rate": 9.927780295290389e-05, | |
| "loss": 0.7288, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06401089547156963, | |
| "grad_norm": 1.6259329319000244, | |
| "learning_rate": 9.922132840449459e-05, | |
| "loss": 0.8127, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06537282941777324, | |
| "grad_norm": 1.5872222185134888, | |
| "learning_rate": 9.916274537819775e-05, | |
| "loss": 0.744, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06673476336397685, | |
| "grad_norm": 2.1103341579437256, | |
| "learning_rate": 9.91020563835152e-05, | |
| "loss": 0.7684, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06809669731018046, | |
| "grad_norm": 2.860896587371826, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.8936, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06945863125638406, | |
| "grad_norm": 0.8009760975837708, | |
| "learning_rate": 9.897437097795257e-05, | |
| "loss": 0.6914, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.07082056520258767, | |
| "grad_norm": 0.8302339911460876, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.7927, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.07218249914879128, | |
| "grad_norm": 0.8460277318954468, | |
| "learning_rate": 9.883829406604363e-05, | |
| "loss": 0.6558, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0735444330949949, | |
| "grad_norm": 0.6343598961830139, | |
| "learning_rate": 9.876711602542563e-05, | |
| "loss": 0.6166, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0749063670411985, | |
| "grad_norm": 0.6294136643409729, | |
| "learning_rate": 9.869384896386668e-05, | |
| "loss": 0.7247, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.07626830098740212, | |
| "grad_norm": 0.6533523201942444, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 0.6108, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.07763023493360573, | |
| "grad_norm": 0.7479948997497559, | |
| "learning_rate": 9.854106042134641e-05, | |
| "loss": 0.6284, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.07899216887980932, | |
| "grad_norm": 0.6209579110145569, | |
| "learning_rate": 9.846154548533773e-05, | |
| "loss": 0.5844, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.08035410282601294, | |
| "grad_norm": 0.6447109580039978, | |
| "learning_rate": 9.837995461801299e-05, | |
| "loss": 0.5638, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.08171603677221655, | |
| "grad_norm": 0.6410228610038757, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.6504, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.08307797071842016, | |
| "grad_norm": 0.6668742895126343, | |
| "learning_rate": 9.821055915851647e-05, | |
| "loss": 0.6025, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.08443990466462377, | |
| "grad_norm": 1.3477871417999268, | |
| "learning_rate": 9.812276182268236e-05, | |
| "loss": 0.5365, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.08580183861082738, | |
| "grad_norm": 0.6480602622032166, | |
| "learning_rate": 9.803290306789676e-05, | |
| "loss": 0.5192, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.08716377255703098, | |
| "grad_norm": 0.6879251003265381, | |
| "learning_rate": 9.794098674340965e-05, | |
| "loss": 0.5351, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.08852570650323459, | |
| "grad_norm": 0.7362158894538879, | |
| "learning_rate": 9.784701678661045e-05, | |
| "loss": 0.5237, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0898876404494382, | |
| "grad_norm": 0.7937474250793457, | |
| "learning_rate": 9.775099722285935e-05, | |
| "loss": 0.6137, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.09124957439564181, | |
| "grad_norm": 0.8558733463287354, | |
| "learning_rate": 9.765293216531486e-05, | |
| "loss": 0.6135, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.09261150834184542, | |
| "grad_norm": 0.9930456876754761, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.5677, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.09397344228804903, | |
| "grad_norm": 0.816164493560791, | |
| "learning_rate": 9.74506824594107e-05, | |
| "loss": 0.5234, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.09533537623425264, | |
| "grad_norm": 0.8402704000473022, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.4945, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.09669731018045624, | |
| "grad_norm": 0.7770735025405884, | |
| "learning_rate": 9.724030232334391e-05, | |
| "loss": 0.5315, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.09805924412665985, | |
| "grad_norm": 0.998912513256073, | |
| "learning_rate": 9.713207455460894e-05, | |
| "loss": 0.5267, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.09942117807286346, | |
| "grad_norm": 0.8477897644042969, | |
| "learning_rate": 9.702182780466775e-05, | |
| "loss": 0.551, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.10078311201906708, | |
| "grad_norm": 0.8563628792762756, | |
| "learning_rate": 9.690956679612421e-05, | |
| "loss": 0.6059, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.10214504596527069, | |
| "grad_norm": 0.79013592004776, | |
| "learning_rate": 9.67952963378663e-05, | |
| "loss": 0.562, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1035069799114743, | |
| "grad_norm": 0.7895680069923401, | |
| "learning_rate": 9.667902132486009e-05, | |
| "loss": 0.5271, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.10486891385767791, | |
| "grad_norm": 0.9388853311538696, | |
| "learning_rate": 9.656074673794018e-05, | |
| "loss": 0.6054, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.1062308478038815, | |
| "grad_norm": 0.9046183228492737, | |
| "learning_rate": 9.644047764359622e-05, | |
| "loss": 0.5627, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.10759278175008512, | |
| "grad_norm": 0.9057890772819519, | |
| "learning_rate": 9.631821919375591e-05, | |
| "loss": 0.602, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.10895471569628873, | |
| "grad_norm": 0.9569646716117859, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.539, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.11031664964249234, | |
| "grad_norm": 0.9439347386360168, | |
| "learning_rate": 9.606775526115963e-05, | |
| "loss": 0.5636, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.11167858358869595, | |
| "grad_norm": 0.8295052647590637, | |
| "learning_rate": 9.593956050744492e-05, | |
| "loss": 0.544, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.11304051753489956, | |
| "grad_norm": 0.9805134534835815, | |
| "learning_rate": 9.580939785585681e-05, | |
| "loss": 0.589, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.11440245148110317, | |
| "grad_norm": 0.8532008528709412, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.5225, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.11576438542730677, | |
| "grad_norm": 1.0181292295455933, | |
| "learning_rate": 9.554319124605879e-05, | |
| "loss": 0.6054, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.11712631937351038, | |
| "grad_norm": 0.882378339767456, | |
| "learning_rate": 9.540715869125407e-05, | |
| "loss": 0.5787, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.118488253319714, | |
| "grad_norm": 0.8436698913574219, | |
| "learning_rate": 9.526918104489777e-05, | |
| "loss": 0.5484, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.1198501872659176, | |
| "grad_norm": 1.0983854532241821, | |
| "learning_rate": 9.512926421749304e-05, | |
| "loss": 0.6058, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 0.9240631461143494, | |
| "learning_rate": 9.498741420261108e-05, | |
| "loss": 0.608, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.12257405515832483, | |
| "grad_norm": 0.8889957070350647, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.5661, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.12393598910452842, | |
| "grad_norm": 0.883852481842041, | |
| "learning_rate": 9.469793899849661e-05, | |
| "loss": 0.5305, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.12529792305073204, | |
| "grad_norm": 0.9092103838920593, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 0.5246, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.12665985699693566, | |
| "grad_norm": 0.990210771560669, | |
| "learning_rate": 9.440080503264037e-05, | |
| "loss": 0.5956, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.12802179094313926, | |
| "grad_norm": 0.981751024723053, | |
| "learning_rate": 9.42493818731521e-05, | |
| "loss": 0.5482, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.12938372488934285, | |
| "grad_norm": 1.1555558443069458, | |
| "learning_rate": 9.409606321741775e-05, | |
| "loss": 0.7, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.13074565883554648, | |
| "grad_norm": 1.1215264797210693, | |
| "learning_rate": 9.394085563309827e-05, | |
| "loss": 0.5967, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.13210759278175008, | |
| "grad_norm": 1.1388212442398071, | |
| "learning_rate": 9.378376576876999e-05, | |
| "loss": 0.5699, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.1334695267279537, | |
| "grad_norm": 1.3690537214279175, | |
| "learning_rate": 9.362480035363986e-05, | |
| "loss": 0.6795, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.1348314606741573, | |
| "grad_norm": 1.632396936416626, | |
| "learning_rate": 9.34639661972572e-05, | |
| "loss": 0.7396, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.13619339462036092, | |
| "grad_norm": 2.967085838317871, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.9022, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13619339462036092, | |
| "eval_loss": 0.6248776316642761, | |
| "eval_runtime": 153.1736, | |
| "eval_samples_per_second": 8.076, | |
| "eval_steps_per_second": 2.024, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.4323173481919283e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |