| { | |
| "best_metric": 0.09263816475868225, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.0085577972229948, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.557797222994801e-05, | |
| "grad_norm": 11.9537353515625, | |
| "learning_rate": 1e-05, | |
| "loss": 3.3148, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.557797222994801e-05, | |
| "eval_loss": 3.4356112480163574, | |
| "eval_runtime": 1496.8372, | |
| "eval_samples_per_second": 13.148, | |
| "eval_steps_per_second": 3.288, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017115594445989602, | |
| "grad_norm": 12.756943702697754, | |
| "learning_rate": 2e-05, | |
| "loss": 3.4725, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000256733916689844, | |
| "grad_norm": 11.090555191040039, | |
| "learning_rate": 3e-05, | |
| "loss": 3.2797, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00034231188891979203, | |
| "grad_norm": 8.203390121459961, | |
| "learning_rate": 4e-05, | |
| "loss": 2.6269, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00042788986114974004, | |
| "grad_norm": 7.875814914703369, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0335, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000513467833379688, | |
| "grad_norm": 6.270211696624756, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4926, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005990458056096361, | |
| "grad_norm": 7.452057361602783, | |
| "learning_rate": 7e-05, | |
| "loss": 0.7715, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006846237778395841, | |
| "grad_norm": 4.604471683502197, | |
| "learning_rate": 8e-05, | |
| "loss": 0.3611, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007702017500695321, | |
| "grad_norm": 9.149091720581055, | |
| "learning_rate": 9e-05, | |
| "loss": 0.266, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008557797222994801, | |
| "grad_norm": 8.267728805541992, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2832, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009413576945294281, | |
| "grad_norm": 5.3810224533081055, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 0.2749, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001026935666759376, | |
| "grad_norm": 4.651538372039795, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 0.1623, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0011125136389893242, | |
| "grad_norm": 4.34693717956543, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 0.1978, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0011980916112192721, | |
| "grad_norm": 1.7665005922317505, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 0.0916, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0012836695834492202, | |
| "grad_norm": 3.6700124740600586, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.1451, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013692475556791681, | |
| "grad_norm": 2.432461977005005, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 0.0877, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0014548255279091162, | |
| "grad_norm": 3.331000804901123, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 0.1919, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0015404035001390641, | |
| "grad_norm": 2.1896657943725586, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.1212, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0016259814723690123, | |
| "grad_norm": 2.280017375946045, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 0.122, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0017115594445989602, | |
| "grad_norm": 2.8614282608032227, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.1135, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0017971374168289083, | |
| "grad_norm": 1.6623473167419434, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 0.0904, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0018827153890588562, | |
| "grad_norm": 1.221984624862671, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 0.0837, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0019682933612888043, | |
| "grad_norm": 0.9691879749298096, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 0.0735, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.002053871333518752, | |
| "grad_norm": 0.5991889834403992, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.0591, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0021394493057487, | |
| "grad_norm": 0.8098444938659668, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.0728, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0022250272779786484, | |
| "grad_norm": 1.0000460147857666, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 0.0575, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0023106052502085963, | |
| "grad_norm": 0.7823395729064941, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.0454, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0023961832224385442, | |
| "grad_norm": 1.5458400249481201, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.0744, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.002481761194668492, | |
| "grad_norm": 1.1707133054733276, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0969, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0025673391668984405, | |
| "grad_norm": 1.4632576704025269, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.0593, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0026529171391283884, | |
| "grad_norm": 0.5689661502838135, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 0.0494, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0027384951113583363, | |
| "grad_norm": 1.107108235359192, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.0683, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.002824073083588284, | |
| "grad_norm": 0.7869353890419006, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 0.0623, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0029096510558182325, | |
| "grad_norm": 0.7320476770401001, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 0.063, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0029952290280481804, | |
| "grad_norm": 1.0443247556686401, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.0734, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0030808070002781283, | |
| "grad_norm": 0.7589712738990784, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.0735, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0031663849725080766, | |
| "grad_norm": 1.519474744796753, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 0.0605, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0032519629447380245, | |
| "grad_norm": 0.4899841547012329, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 0.0408, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0033375409169679724, | |
| "grad_norm": 1.4099607467651367, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.067, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0034231188891979203, | |
| "grad_norm": 1.2132967710494995, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.0696, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0035086968614278687, | |
| "grad_norm": 0.7433332800865173, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.0524, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0035942748336578166, | |
| "grad_norm": 1.189876914024353, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.0713, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0036798528058877645, | |
| "grad_norm": 0.9605991244316101, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.0619, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0037654307781177124, | |
| "grad_norm": 0.9537285566329956, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.0635, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0038510087503476607, | |
| "grad_norm": 0.8157845735549927, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.06, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003936586722577609, | |
| "grad_norm": 0.5266832113265991, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.0398, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.004022164694807557, | |
| "grad_norm": 0.5681657195091248, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.0329, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.004107742667037504, | |
| "grad_norm": 0.7972701191902161, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0543, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.004193320639267453, | |
| "grad_norm": 1.5113557577133179, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.0397, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0042788986114974, | |
| "grad_norm": 1.7996363639831543, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.0342, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0042788986114974, | |
| "eval_loss": 0.29323455691337585, | |
| "eval_runtime": 1501.7672, | |
| "eval_samples_per_second": 13.105, | |
| "eval_steps_per_second": 3.277, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0043644765837273485, | |
| "grad_norm": 2.4326767921447754, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 0.4022, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.004450054555957297, | |
| "grad_norm": 1.9868508577346802, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 0.2928, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.004535632528187244, | |
| "grad_norm": 1.331284999847412, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 0.1449, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.004621210500417193, | |
| "grad_norm": 0.5776102542877197, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 0.0617, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.004706788472647141, | |
| "grad_norm": 2.261007070541382, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 0.225, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0047923664448770885, | |
| "grad_norm": 1.6656039953231812, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 0.1828, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.004877944417107037, | |
| "grad_norm": 1.5622031688690186, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 0.1436, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.004963522389336984, | |
| "grad_norm": 0.4732876718044281, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 0.0701, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.005049100361566933, | |
| "grad_norm": 0.6526130437850952, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 0.0704, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.005134678333796881, | |
| "grad_norm": 0.9172316193580627, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.081, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.005220256306026828, | |
| "grad_norm": 0.7165319323539734, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 0.0599, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.005305834278256777, | |
| "grad_norm": 1.2434439659118652, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 0.0907, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.005391412250486725, | |
| "grad_norm": 1.8290995359420776, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 0.1152, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0054769902227166725, | |
| "grad_norm": 0.6257376074790955, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 0.0532, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.005562568194946621, | |
| "grad_norm": 1.2729533910751343, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 0.0639, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.005648146167176568, | |
| "grad_norm": 0.9542877674102783, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 0.0606, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.005733724139406517, | |
| "grad_norm": 0.8180510997772217, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0785, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.005819302111636465, | |
| "grad_norm": 0.5551479458808899, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 0.0288, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0059048800838664125, | |
| "grad_norm": 0.6363096833229065, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 0.0407, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.005990458056096361, | |
| "grad_norm": 0.773931086063385, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.0659, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.006076036028326309, | |
| "grad_norm": 1.042119026184082, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 0.0502, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.006161614000556257, | |
| "grad_norm": 0.7260262966156006, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.0437, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.006247191972786205, | |
| "grad_norm": 0.5678524374961853, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 0.0399, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.006332769945016153, | |
| "grad_norm": 0.7263334393501282, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 0.0523, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.006418347917246101, | |
| "grad_norm": 0.3313182294368744, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.0393, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.006503925889476049, | |
| "grad_norm": 0.3484734892845154, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 0.0418, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.0065895038617059965, | |
| "grad_norm": 0.47232550382614136, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 0.0432, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.006675081833935945, | |
| "grad_norm": 0.8112048506736755, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 0.0743, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.006760659806165893, | |
| "grad_norm": 0.51592618227005, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 0.0641, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.006846237778395841, | |
| "grad_norm": 0.3841154873371124, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.0498, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.006931815750625789, | |
| "grad_norm": 1.377824068069458, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 0.0608, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.007017393722855737, | |
| "grad_norm": 0.7310321927070618, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 0.0606, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.007102971695085685, | |
| "grad_norm": 0.6445568203926086, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 0.0613, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.007188549667315633, | |
| "grad_norm": 0.586155116558075, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 0.0583, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.007274127639545581, | |
| "grad_norm": 0.48145791888237, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.0457, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.007359705611775529, | |
| "grad_norm": 0.5043821930885315, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0531, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.007445283584005477, | |
| "grad_norm": 0.42169609665870667, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 0.0581, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.007530861556235425, | |
| "grad_norm": 0.760418713092804, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 0.0568, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.007616439528465373, | |
| "grad_norm": 0.6648797988891602, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 0.0403, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.007702017500695321, | |
| "grad_norm": 0.46584442257881165, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.0446, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.007787595472925269, | |
| "grad_norm": 0.5709188580513, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 0.0643, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.007873173445155217, | |
| "grad_norm": 0.7237929105758667, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 0.0586, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.007958751417385165, | |
| "grad_norm": 0.4494575560092926, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 0.0617, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.008044329389615114, | |
| "grad_norm": 2.223395347595215, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 0.0576, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.008129907361845061, | |
| "grad_norm": 0.8537086844444275, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 0.0348, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.008215485334075009, | |
| "grad_norm": 0.556140124797821, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.0418, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.008301063306304956, | |
| "grad_norm": 0.4685639441013336, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 0.0378, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.008386641278534905, | |
| "grad_norm": 0.5281150937080383, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 0.0541, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.008472219250764853, | |
| "grad_norm": 0.3150881230831146, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 0.0548, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.0085577972229948, | |
| "grad_norm": 0.96101313829422, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.0488, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0085577972229948, | |
| "eval_loss": 0.09263816475868225, | |
| "eval_runtime": 1501.1983, | |
| "eval_samples_per_second": 13.11, | |
| "eval_steps_per_second": 3.278, | |
| "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": 1.508513578745856e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |