| { | |
| "best_metric": 0.7277113199234009, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.3436426116838488, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003436426116838488, | |
| "grad_norm": 6.875288009643555, | |
| "learning_rate": 1e-05, | |
| "loss": 4.5691, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003436426116838488, | |
| "eval_loss": 1.1649625301361084, | |
| "eval_runtime": 56.8704, | |
| "eval_samples_per_second": 8.616, | |
| "eval_steps_per_second": 2.163, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006872852233676976, | |
| "grad_norm": 10.01762580871582, | |
| "learning_rate": 2e-05, | |
| "loss": 4.7735, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010309278350515464, | |
| "grad_norm": 8.196460723876953, | |
| "learning_rate": 3e-05, | |
| "loss": 5.4559, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013745704467353952, | |
| "grad_norm": 7.672198295593262, | |
| "learning_rate": 4e-05, | |
| "loss": 4.582, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01718213058419244, | |
| "grad_norm": 4.969404220581055, | |
| "learning_rate": 5e-05, | |
| "loss": 3.4696, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.020618556701030927, | |
| "grad_norm": 4.3889851570129395, | |
| "learning_rate": 6e-05, | |
| "loss": 3.3103, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.024054982817869417, | |
| "grad_norm": 4.012556076049805, | |
| "learning_rate": 7e-05, | |
| "loss": 3.2335, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.027491408934707903, | |
| "grad_norm": 3.344139814376831, | |
| "learning_rate": 8e-05, | |
| "loss": 3.0476, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.030927835051546393, | |
| "grad_norm": 3.173506021499634, | |
| "learning_rate": 9e-05, | |
| "loss": 3.1844, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03436426116838488, | |
| "grad_norm": 2.4493091106414795, | |
| "learning_rate": 0.0001, | |
| "loss": 2.782, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.037800687285223365, | |
| "grad_norm": 3.146341323852539, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 3.0659, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.041237113402061855, | |
| "grad_norm": 2.8679311275482178, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 2.7422, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.044673539518900345, | |
| "grad_norm": 2.7918779850006104, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 2.931, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.048109965635738834, | |
| "grad_norm": 2.896129846572876, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 2.8184, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05154639175257732, | |
| "grad_norm": 2.6621735095977783, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 2.6664, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.054982817869415807, | |
| "grad_norm": 2.8896968364715576, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 2.7089, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.058419243986254296, | |
| "grad_norm": 3.0421786308288574, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 2.7472, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.061855670103092786, | |
| "grad_norm": 2.725599765777588, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 2.6994, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06529209621993128, | |
| "grad_norm": 2.331462860107422, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 2.6058, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06872852233676977, | |
| "grad_norm": 2.9271135330200195, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 2.6624, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07216494845360824, | |
| "grad_norm": 2.924933433532715, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 2.5572, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07560137457044673, | |
| "grad_norm": 2.7112512588500977, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 2.6309, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07903780068728522, | |
| "grad_norm": 2.8630990982055664, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 2.5248, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08247422680412371, | |
| "grad_norm": 2.5011701583862305, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 2.6045, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0859106529209622, | |
| "grad_norm": 3.070207118988037, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 2.869, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08934707903780069, | |
| "grad_norm": 2.714486837387085, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 2.8448, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09278350515463918, | |
| "grad_norm": 3.2341771125793457, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 2.6683, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09621993127147767, | |
| "grad_norm": 2.5088119506835938, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 2.6063, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09965635738831616, | |
| "grad_norm": 2.819406270980835, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.6812, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10309278350515463, | |
| "grad_norm": 2.6176741123199463, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 2.8282, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10652920962199312, | |
| "grad_norm": 2.890087604522705, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 2.9375, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10996563573883161, | |
| "grad_norm": 3.169712781906128, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 3.0984, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1134020618556701, | |
| "grad_norm": 3.0394792556762695, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 2.6701, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11683848797250859, | |
| "grad_norm": 3.2077884674072266, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 2.9322, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.12027491408934708, | |
| "grad_norm": 2.8351423740386963, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 2.9144, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.12371134020618557, | |
| "grad_norm": 3.7410457134246826, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 3.1276, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12714776632302405, | |
| "grad_norm": 3.0850861072540283, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 3.2167, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.13058419243986255, | |
| "grad_norm": 3.5275065898895264, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 2.67, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.13402061855670103, | |
| "grad_norm": 3.8704416751861572, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 2.9465, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.13745704467353953, | |
| "grad_norm": 4.236602306365967, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 3.1699, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.140893470790378, | |
| "grad_norm": 3.579802989959717, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 3.5988, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.14432989690721648, | |
| "grad_norm": 3.929170608520508, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 3.7835, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.14776632302405499, | |
| "grad_norm": 4.23232889175415, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 3.249, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.15120274914089346, | |
| "grad_norm": 4.3421454429626465, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 3.0539, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.15463917525773196, | |
| "grad_norm": 5.814420223236084, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 3.1705, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.15807560137457044, | |
| "grad_norm": 4.802507400512695, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 3.4311, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.16151202749140894, | |
| "grad_norm": 5.132009029388428, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 3.1524, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.16494845360824742, | |
| "grad_norm": 6.066173553466797, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 3.9363, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.16838487972508592, | |
| "grad_norm": 8.14843463897705, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 3.9255, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1718213058419244, | |
| "grad_norm": 11.949299812316895, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 4.9737, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1718213058419244, | |
| "eval_loss": 0.7489818334579468, | |
| "eval_runtime": 58.1061, | |
| "eval_samples_per_second": 8.433, | |
| "eval_steps_per_second": 2.117, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17525773195876287, | |
| "grad_norm": 3.229118824005127, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 3.9858, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.17869415807560138, | |
| "grad_norm": 3.4312267303466797, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 4.7884, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.18213058419243985, | |
| "grad_norm": 2.815904140472412, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 4.1316, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.18556701030927836, | |
| "grad_norm": 2.907052755355835, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 3.8479, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.18900343642611683, | |
| "grad_norm": 2.1939303874969482, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 2.9194, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.19243986254295534, | |
| "grad_norm": 2.066952705383301, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 2.71, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1958762886597938, | |
| "grad_norm": 2.301304817199707, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 2.3676, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.19931271477663232, | |
| "grad_norm": 3.6853837966918945, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 2.4181, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.2027491408934708, | |
| "grad_norm": 2.3933732509613037, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 2.6629, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.20618556701030927, | |
| "grad_norm": 2.310511350631714, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 2.5932, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.20962199312714777, | |
| "grad_norm": 2.1882212162017822, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 2.5533, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.21305841924398625, | |
| "grad_norm": 2.224141836166382, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 2.6595, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.21649484536082475, | |
| "grad_norm": 2.0371408462524414, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 2.4645, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.21993127147766323, | |
| "grad_norm": 1.9904556274414062, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 2.815, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.22336769759450173, | |
| "grad_norm": 1.9936702251434326, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 2.6361, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2268041237113402, | |
| "grad_norm": 2.063617467880249, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 2.8328, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.23024054982817868, | |
| "grad_norm": 1.778960108757019, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 2.5526, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.23367697594501718, | |
| "grad_norm": 1.8721736669540405, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 2.2001, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.23711340206185566, | |
| "grad_norm": 2.1718900203704834, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 2.6618, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.24054982817869416, | |
| "grad_norm": 1.905144453048706, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 2.4549, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.24398625429553264, | |
| "grad_norm": 2.322458028793335, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 2.6667, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.24742268041237114, | |
| "grad_norm": 2.112133741378784, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 2.4297, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.2508591065292096, | |
| "grad_norm": 2.050910472869873, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 2.512, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.2542955326460481, | |
| "grad_norm": 2.034681558609009, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 2.4437, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.25773195876288657, | |
| "grad_norm": 1.984123945236206, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 2.5732, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2611683848797251, | |
| "grad_norm": 2.2462446689605713, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 2.6211, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.2646048109965636, | |
| "grad_norm": 2.473987102508545, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 2.7826, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.26804123711340205, | |
| "grad_norm": 2.3901572227478027, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 2.5584, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.27147766323024053, | |
| "grad_norm": 2.2320001125335693, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 2.4833, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.27491408934707906, | |
| "grad_norm": 2.112913131713867, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 2.4669, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.27835051546391754, | |
| "grad_norm": 2.4999232292175293, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 2.633, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.281786941580756, | |
| "grad_norm": 2.5236027240753174, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 2.6726, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.2852233676975945, | |
| "grad_norm": 2.610469341278076, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 2.6783, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.28865979381443296, | |
| "grad_norm": 2.888082504272461, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 3.0809, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.2920962199312715, | |
| "grad_norm": 3.045673370361328, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 3.2255, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.29553264604810997, | |
| "grad_norm": 3.2517120838165283, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 3.0398, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.29896907216494845, | |
| "grad_norm": 2.757512331008911, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 2.72, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.3024054982817869, | |
| "grad_norm": 2.845644235610962, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 3.4635, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.30584192439862545, | |
| "grad_norm": 2.752856492996216, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 3.3043, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.30927835051546393, | |
| "grad_norm": 3.0697596073150635, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 3.2902, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3127147766323024, | |
| "grad_norm": 3.290828227996826, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 3.6147, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.3161512027491409, | |
| "grad_norm": 3.5331523418426514, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 3.3361, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.31958762886597936, | |
| "grad_norm": 3.4285762310028076, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 3.216, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.3230240549828179, | |
| "grad_norm": 3.717268466949463, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 3.1196, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.32646048109965636, | |
| "grad_norm": 3.960413932800293, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 3.3172, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.32989690721649484, | |
| "grad_norm": 4.5019850730896, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 3.2663, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 6.533929347991943, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 3.5329, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.33676975945017185, | |
| "grad_norm": 5.7289719581604, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 3.3525, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.3402061855670103, | |
| "grad_norm": 5.30385684967041, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 3.2372, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.3436426116838488, | |
| "grad_norm": 7.11011266708374, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 4.2534, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3436426116838488, | |
| "eval_loss": 0.7277113199234009, | |
| "eval_runtime": 58.1102, | |
| "eval_samples_per_second": 8.432, | |
| "eval_steps_per_second": 2.117, | |
| "step": 100 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.5413965215432704e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |