| { | |
| "best_metric": 1.361222743988037, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.13035685188202706, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006517842594101353, | |
| "grad_norm": 0.559842050075531, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1631, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006517842594101353, | |
| "eval_loss": 2.1502420902252197, | |
| "eval_runtime": 201.5034, | |
| "eval_samples_per_second": 12.824, | |
| "eval_steps_per_second": 3.206, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013035685188202706, | |
| "grad_norm": 0.8112638592720032, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2317, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001955352778230406, | |
| "grad_norm": 0.6634911298751831, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2741, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002607137037640541, | |
| "grad_norm": 1.0499569177627563, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5231, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0032589212970506763, | |
| "grad_norm": 1.4701368808746338, | |
| "learning_rate": 5e-05, | |
| "loss": 1.455, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003910705556460812, | |
| "grad_norm": 0.8571744561195374, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6068, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004562489815870947, | |
| "grad_norm": 0.6071902513504028, | |
| "learning_rate": 7e-05, | |
| "loss": 1.4519, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005214274075281082, | |
| "grad_norm": 0.4109746813774109, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3739, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005866058334691217, | |
| "grad_norm": 0.6581244468688965, | |
| "learning_rate": 9e-05, | |
| "loss": 1.3667, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006517842594101353, | |
| "grad_norm": 0.5391998887062073, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4816, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007169626853511487, | |
| "grad_norm": 0.5498155355453491, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.4465, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007821411112921624, | |
| "grad_norm": 0.5792071223258972, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 1.3428, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008473195372331759, | |
| "grad_norm": 0.7036895751953125, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 1.6394, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009124979631741893, | |
| "grad_norm": 0.9383275508880615, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.5432, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009776763891152028, | |
| "grad_norm": 0.7889774441719055, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.6771, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010428548150562164, | |
| "grad_norm": 0.6964580416679382, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 1.5616, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0110803324099723, | |
| "grad_norm": 0.5818759799003601, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 1.3317, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011732116669382434, | |
| "grad_norm": 0.6486309170722961, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 1.4147, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01238390092879257, | |
| "grad_norm": 0.7740495800971985, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 1.6616, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.013035685188202705, | |
| "grad_norm": 0.747631311416626, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 1.7606, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01368746944761284, | |
| "grad_norm": 0.9149699211120605, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 1.8095, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.014339253707022975, | |
| "grad_norm": 0.9890636801719666, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 1.7603, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.014991037966433111, | |
| "grad_norm": 0.8543292880058289, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 1.686, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.015642822225843248, | |
| "grad_norm": 0.8413967490196228, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 1.5366, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.016294606485253382, | |
| "grad_norm": 0.8846473693847656, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 1.7333, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016946390744663517, | |
| "grad_norm": 0.7301384210586548, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 1.495, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.017598175004073652, | |
| "grad_norm": 0.7829327583312988, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 1.3632, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.018249959263483786, | |
| "grad_norm": 0.7952656149864197, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 1.5095, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01890174352289392, | |
| "grad_norm": 0.8105695247650146, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.4607, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.019553527782304056, | |
| "grad_norm": 0.9978770017623901, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.4877, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.020205312041714194, | |
| "grad_norm": 1.1400288343429565, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 1.3916, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.02085709630112433, | |
| "grad_norm": 1.2443031072616577, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 1.4607, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.021508880560534464, | |
| "grad_norm": 1.2221732139587402, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 1.495, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0221606648199446, | |
| "grad_norm": 1.1427334547042847, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 1.3543, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.022812449079354733, | |
| "grad_norm": 1.0424737930297852, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 1.4943, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.023464233338764868, | |
| "grad_norm": 1.3495514392852783, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 1.3856, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.024116017598175003, | |
| "grad_norm": 1.3965070247650146, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 1.4963, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02476780185758514, | |
| "grad_norm": 1.183819055557251, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 1.1338, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.025419586116995276, | |
| "grad_norm": 1.5519204139709473, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 1.4559, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02607137037640541, | |
| "grad_norm": 1.5406330823898315, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 1.1754, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.026723154635815545, | |
| "grad_norm": 1.5823599100112915, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 1.5913, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02737493889522568, | |
| "grad_norm": 1.2872836589813232, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 1.3551, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.028026723154635814, | |
| "grad_norm": 1.4425047636032104, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 1.2788, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02867850741404595, | |
| "grad_norm": 1.8383742570877075, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 1.5667, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.029330291673456087, | |
| "grad_norm": 1.540223479270935, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 1.5531, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.029982075932866222, | |
| "grad_norm": 1.7879434823989868, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 1.3786, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.030633860192276357, | |
| "grad_norm": 2.3967573642730713, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 1.3847, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.031285644451686495, | |
| "grad_norm": 2.373622417449951, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.2245, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03193742871109663, | |
| "grad_norm": 2.342925786972046, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 1.5844, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.032589212970506765, | |
| "grad_norm": 4.0998077392578125, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 2.3574, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.032589212970506765, | |
| "eval_loss": 1.5625872611999512, | |
| "eval_runtime": 203.3684, | |
| "eval_samples_per_second": 12.706, | |
| "eval_steps_per_second": 3.177, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0332409972299169, | |
| "grad_norm": 0.5773328542709351, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 1.1741, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.033892781489327034, | |
| "grad_norm": 0.569870114326477, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 1.1699, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.03454456574873717, | |
| "grad_norm": 0.5505066514015198, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 1.3949, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.035196350008147304, | |
| "grad_norm": 0.5093855261802673, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 1.2573, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.03584813426755744, | |
| "grad_norm": 0.6201264262199402, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 1.2551, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.03649991852696757, | |
| "grad_norm": 0.6050621867179871, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 1.3761, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.03715170278637771, | |
| "grad_norm": 0.4428724944591522, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 1.1776, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.03780348704578784, | |
| "grad_norm": 0.5018085837364197, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 1.2878, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.03845527130519798, | |
| "grad_norm": 0.4629620313644409, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 1.4328, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.03910705556460811, | |
| "grad_norm": 0.47736626863479614, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 1.4597, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03975883982401825, | |
| "grad_norm": 0.46020087599754333, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 1.496, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.04041062408342839, | |
| "grad_norm": 0.5311948657035828, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 1.5641, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.04106240834283852, | |
| "grad_norm": 0.5824150443077087, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 1.3796, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.04171419260224866, | |
| "grad_norm": 0.5060763955116272, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 1.5424, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.04236597686165879, | |
| "grad_norm": 0.5149311423301697, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 1.5314, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.04301776112106893, | |
| "grad_norm": 0.6181354522705078, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 1.666, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.04366954538047906, | |
| "grad_norm": 0.6071786880493164, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 1.6037, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0443213296398892, | |
| "grad_norm": 0.5892857313156128, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 1.5234, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.04497311389929933, | |
| "grad_norm": 0.6549196839332581, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 1.7427, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.045624898158709466, | |
| "grad_norm": 0.6623611450195312, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 1.6478, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0462766824181196, | |
| "grad_norm": 0.6412277817726135, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 1.654, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.046928466677529736, | |
| "grad_norm": 0.7149087190628052, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 1.5823, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.04758025093693987, | |
| "grad_norm": 0.6478785276412964, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 1.5092, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.048232035196350005, | |
| "grad_norm": 0.8339841365814209, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 1.7081, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.04888381945576014, | |
| "grad_norm": 0.6634137630462646, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 1.5685, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.04953560371517028, | |
| "grad_norm": 0.7319443821907043, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 1.3952, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.050187387974580416, | |
| "grad_norm": 0.7438411116600037, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 1.3501, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.05083917223399055, | |
| "grad_norm": 0.7561342120170593, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 1.5413, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.051490956493400686, | |
| "grad_norm": 0.6312757134437561, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 1.3898, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.05214274075281082, | |
| "grad_norm": 0.7573202252388, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 1.3744, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.052794525012220955, | |
| "grad_norm": 0.9921998381614685, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 1.5812, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.05344630927163109, | |
| "grad_norm": 0.9239053726196289, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 1.3269, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.054098093531041225, | |
| "grad_norm": 0.8641653060913086, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 1.4101, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.05474987779045136, | |
| "grad_norm": 0.9148449301719666, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 1.3028, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.055401662049861494, | |
| "grad_norm": 1.0409218072891235, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 1.3792, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.05605344630927163, | |
| "grad_norm": 0.978447437286377, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.3389, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.056705230568681764, | |
| "grad_norm": 1.385927677154541, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 1.4932, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.0573570148280919, | |
| "grad_norm": 0.9205519556999207, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 1.0915, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.05800879908750204, | |
| "grad_norm": 1.234601378440857, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 1.2098, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.058660583346912175, | |
| "grad_norm": 1.015903115272522, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 1.2165, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.05931236760632231, | |
| "grad_norm": 1.420213222503662, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 1.582, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.059964151865732444, | |
| "grad_norm": 1.2678552865982056, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 1.3321, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.06061593612514258, | |
| "grad_norm": 1.171578288078308, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 1.2771, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.061267720384552714, | |
| "grad_norm": 1.3661903142929077, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 1.4461, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.06191950464396285, | |
| "grad_norm": 1.2631621360778809, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 1.11, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.06257128890337299, | |
| "grad_norm": 1.7056459188461304, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 1.3257, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.06322307316278312, | |
| "grad_norm": 1.7923287153244019, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 1.3669, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.06387485742219326, | |
| "grad_norm": 1.509992003440857, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 1.3823, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.0645266416816034, | |
| "grad_norm": 2.4850306510925293, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 1.7633, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.06517842594101353, | |
| "grad_norm": 3.989614725112915, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 1.3741, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06517842594101353, | |
| "eval_loss": 1.439968466758728, | |
| "eval_runtime": 203.9683, | |
| "eval_samples_per_second": 12.669, | |
| "eval_steps_per_second": 3.167, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06583021020042366, | |
| "grad_norm": 0.31170693039894104, | |
| "learning_rate": 5.330452921628497e-05, | |
| "loss": 1.0834, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.0664819944598338, | |
| "grad_norm": 0.32115522027015686, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 1.1309, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.06713377871924393, | |
| "grad_norm": 0.3525278568267822, | |
| "learning_rate": 5.165316846586541e-05, | |
| "loss": 1.1598, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.06778556297865407, | |
| "grad_norm": 0.358556866645813, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 1.3622, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.0684373472380642, | |
| "grad_norm": 0.32107800245285034, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1696, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.06908913149747434, | |
| "grad_norm": 0.4025322496891022, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 1.2357, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.06974091575688447, | |
| "grad_norm": 0.36745789647102356, | |
| "learning_rate": 4.834683153413459e-05, | |
| "loss": 1.3919, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.07039270001629461, | |
| "grad_norm": 0.3489651083946228, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 1.106, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.07104448427570474, | |
| "grad_norm": 0.37726274132728577, | |
| "learning_rate": 4.669547078371504e-05, | |
| "loss": 1.2702, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.07169626853511488, | |
| "grad_norm": 0.3918270766735077, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 1.1876, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.07234805279452501, | |
| "grad_norm": 0.415508896112442, | |
| "learning_rate": 4.504772348747687e-05, | |
| "loss": 1.3956, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.07299983705393515, | |
| "grad_norm": 0.380808562040329, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 1.3316, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.07365162131334528, | |
| "grad_norm": 0.46469783782958984, | |
| "learning_rate": 4.3405391432896555e-05, | |
| "loss": 1.4574, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.07430340557275542, | |
| "grad_norm": 0.4693603217601776, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 1.3827, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.07495518983216555, | |
| "grad_norm": 0.5363829731941223, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 1.5779, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.07560697409157568, | |
| "grad_norm": 0.5474920868873596, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 1.4873, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.07625875835098582, | |
| "grad_norm": 0.5812809467315674, | |
| "learning_rate": 4.0144148627425993e-05, | |
| "loss": 1.5276, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.07691054261039595, | |
| "grad_norm": 0.6456193923950195, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 1.4315, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.07756232686980609, | |
| "grad_norm": 0.5870631337165833, | |
| "learning_rate": 3.852880399766243e-05, | |
| "loss": 1.6514, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.07821411112921622, | |
| "grad_norm": 0.6266175508499146, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 1.6129, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.07886589538862636, | |
| "grad_norm": 0.6647204160690308, | |
| "learning_rate": 3.6926002952309016e-05, | |
| "loss": 1.6369, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.0795176796480365, | |
| "grad_norm": 0.6961146593093872, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 1.6736, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.08016946390744664, | |
| "grad_norm": 0.7353977560997009, | |
| "learning_rate": 3.533749813077677e-05, | |
| "loss": 1.6961, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.08082124816685678, | |
| "grad_norm": 0.6045286059379578, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.4501, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.08147303242626691, | |
| "grad_norm": 0.6582840085029602, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 1.4565, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.08212481668567705, | |
| "grad_norm": 0.6543602347373962, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 1.399, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.08277660094508718, | |
| "grad_norm": 0.7159081697463989, | |
| "learning_rate": 3.221030765387417e-05, | |
| "loss": 1.4648, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.08342838520449732, | |
| "grad_norm": 0.7286494374275208, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 1.4932, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.08408016946390745, | |
| "grad_norm": 0.6608577370643616, | |
| "learning_rate": 3.0675041535377405e-05, | |
| "loss": 1.2703, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.08473195372331759, | |
| "grad_norm": 0.8380109667778015, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 1.2489, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.08538373798272772, | |
| "grad_norm": 0.7555432319641113, | |
| "learning_rate": 2.916090697523549e-05, | |
| "loss": 1.2819, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.08603552224213785, | |
| "grad_norm": 0.7918082475662231, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 1.2549, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.08668730650154799, | |
| "grad_norm": 0.9338359236717224, | |
| "learning_rate": 2.766955965735968e-05, | |
| "loss": 1.4434, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.08733909076095812, | |
| "grad_norm": 0.8965134024620056, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 1.5997, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.08799087502036826, | |
| "grad_norm": 0.864808976650238, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 1.1591, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.0886426592797784, | |
| "grad_norm": 0.8886546492576599, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 1.1788, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.08929444353918853, | |
| "grad_norm": 0.9865848422050476, | |
| "learning_rate": 2.476172311325783e-05, | |
| "loss": 1.1863, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.08994622779859866, | |
| "grad_norm": 1.2445539236068726, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 1.4217, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.0905980120580088, | |
| "grad_norm": 1.043266773223877, | |
| "learning_rate": 2.3348413563600325e-05, | |
| "loss": 1.1928, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.09124979631741893, | |
| "grad_norm": 1.2551209926605225, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 1.2908, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.09190158057682907, | |
| "grad_norm": 1.1211011409759521, | |
| "learning_rate": 2.196424713241637e-05, | |
| "loss": 1.0974, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.0925533648362392, | |
| "grad_norm": 1.3813427686691284, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 1.516, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.09320514909564934, | |
| "grad_norm": 1.0231101512908936, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 1.1618, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.09385693335505947, | |
| "grad_norm": 1.2551326751708984, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 1.3938, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.0945087176144696, | |
| "grad_norm": 1.2844427824020386, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 1.3299, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.09516050187387974, | |
| "grad_norm": 1.5775208473205566, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 1.4055, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.09581228613328988, | |
| "grad_norm": 1.5789850950241089, | |
| "learning_rate": 1.800157297483417e-05, | |
| "loss": 1.3381, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.09646407039270001, | |
| "grad_norm": 1.4319522380828857, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 1.1653, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.09711585465211015, | |
| "grad_norm": 1.9949793815612793, | |
| "learning_rate": 1.6748771394307585e-05, | |
| "loss": 1.2896, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.09776763891152028, | |
| "grad_norm": 2.9262423515319824, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 2.3794, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.09776763891152028, | |
| "eval_loss": 1.3852198123931885, | |
| "eval_runtime": 203.8229, | |
| "eval_samples_per_second": 12.678, | |
| "eval_steps_per_second": 3.169, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.09841942317093043, | |
| "grad_norm": 0.47645169496536255, | |
| "learning_rate": 1.553232954407171e-05, | |
| "loss": 1.0494, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.09907120743034056, | |
| "grad_norm": 0.5075923204421997, | |
| "learning_rate": 1.4938160786375572e-05, | |
| "loss": 1.0708, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.0997229916897507, | |
| "grad_norm": 0.4150218963623047, | |
| "learning_rate": 1.435357758543015e-05, | |
| "loss": 1.1979, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.10037477594916083, | |
| "grad_norm": 0.30560022592544556, | |
| "learning_rate": 1.3778739760445552e-05, | |
| "loss": 1.1073, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.10102656020857097, | |
| "grad_norm": 0.30022111535072327, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 1.2567, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.1016783444679811, | |
| "grad_norm": 0.3166671097278595, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 1.1401, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.10233012872739124, | |
| "grad_norm": 0.2917068600654602, | |
| "learning_rate": 1.2114256511983274e-05, | |
| "loss": 1.2677, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.10298191298680137, | |
| "grad_norm": 0.38655999302864075, | |
| "learning_rate": 1.157994445715706e-05, | |
| "loss": 1.246, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.1036336972462115, | |
| "grad_norm": 0.4095091223716736, | |
| "learning_rate": 1.1056136061894384e-05, | |
| "loss": 1.2043, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.10428548150562164, | |
| "grad_norm": 0.4321068823337555, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 1.4105, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.10493726576503178, | |
| "grad_norm": 0.39612093567848206, | |
| "learning_rate": 1.0040600155253765e-05, | |
| "loss": 1.3139, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.10558905002444191, | |
| "grad_norm": 0.3853474259376526, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.3323, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.10624083428385205, | |
| "grad_norm": 0.3935280442237854, | |
| "learning_rate": 9.068759265665384e-06, | |
| "loss": 1.2363, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.10689261854326218, | |
| "grad_norm": 0.5228778719902039, | |
| "learning_rate": 8.599558442598998e-06, | |
| "loss": 1.286, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.10754440280267231, | |
| "grad_norm": 0.6150017380714417, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 1.6245, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.10819618706208245, | |
| "grad_norm": 0.5249809622764587, | |
| "learning_rate": 7.695237378953223e-06, | |
| "loss": 1.554, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.10884797132149258, | |
| "grad_norm": 0.6609563827514648, | |
| "learning_rate": 7.260364370723044e-06, | |
| "loss": 1.4923, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.10949975558090272, | |
| "grad_norm": 0.6654233336448669, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 1.3852, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.11015153984031285, | |
| "grad_norm": 0.7500722408294678, | |
| "learning_rate": 6.425787818636131e-06, | |
| "loss": 1.609, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.11080332409972299, | |
| "grad_norm": 0.8355409502983093, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 1.5349, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.11145510835913312, | |
| "grad_norm": 0.7490067481994629, | |
| "learning_rate": 5.6388590278194096e-06, | |
| "loss": 1.4562, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.11210689261854326, | |
| "grad_norm": 0.7271214723587036, | |
| "learning_rate": 5.263533508961827e-06, | |
| "loss": 1.3688, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.11275867687795339, | |
| "grad_norm": 0.6731093525886536, | |
| "learning_rate": 4.900438493352055e-06, | |
| "loss": 1.3032, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.11341046113736353, | |
| "grad_norm": 0.8805928826332092, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 1.6322, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.11406224539677366, | |
| "grad_norm": 0.8619354963302612, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 1.3416, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.1147140296561838, | |
| "grad_norm": 1.0904561281204224, | |
| "learning_rate": 3.885512251130763e-06, | |
| "loss": 1.4407, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.11536581391559393, | |
| "grad_norm": 0.9875521659851074, | |
| "learning_rate": 3.5722980755146517e-06, | |
| "loss": 1.4815, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.11601759817500408, | |
| "grad_norm": 0.7343928813934326, | |
| "learning_rate": 3.271776770026963e-06, | |
| "loss": 1.1324, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.11666938243441421, | |
| "grad_norm": 0.8297130465507507, | |
| "learning_rate": 2.9840304941919415e-06, | |
| "loss": 1.2739, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.11732116669382435, | |
| "grad_norm": 0.8896876573562622, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 1.3703, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.11797295095323448, | |
| "grad_norm": 0.965018093585968, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 1.207, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.11862473521264462, | |
| "grad_norm": 0.8725919723510742, | |
| "learning_rate": 2.1982109232821178e-06, | |
| "loss": 1.4627, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.11927651947205475, | |
| "grad_norm": 0.9071240425109863, | |
| "learning_rate": 1.962316193157593e-06, | |
| "loss": 1.2579, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.11992830373146489, | |
| "grad_norm": 0.8951742053031921, | |
| "learning_rate": 1.7395544861325718e-06, | |
| "loss": 1.2658, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.12058008799087502, | |
| "grad_norm": 1.0315836668014526, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 1.241, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.12123187225028516, | |
| "grad_norm": 1.0490803718566895, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 1.2428, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.12188365650969529, | |
| "grad_norm": 1.0791021585464478, | |
| "learning_rate": 1.1506584608200367e-06, | |
| "loss": 1.3135, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.12253544076910543, | |
| "grad_norm": 1.1855067014694214, | |
| "learning_rate": 9.810017062595322e-07, | |
| "loss": 1.355, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.12318722502851556, | |
| "grad_norm": 1.252608299255371, | |
| "learning_rate": 8.247462563808817e-07, | |
| "loss": 1.2521, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.1238390092879257, | |
| "grad_norm": 1.0825389623641968, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 1.188, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.12449079354733583, | |
| "grad_norm": 1.040637493133545, | |
| "learning_rate": 5.526064699265753e-07, | |
| "loss": 1.4622, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.12514257780674598, | |
| "grad_norm": 1.2370599508285522, | |
| "learning_rate": 4.367965336512403e-07, | |
| "loss": 1.3151, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.1257943620661561, | |
| "grad_norm": 1.528090000152588, | |
| "learning_rate": 3.3453668231809286e-07, | |
| "loss": 1.3784, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.12644614632556625, | |
| "grad_norm": 1.2140353918075562, | |
| "learning_rate": 2.458548727494292e-07, | |
| "loss": 1.201, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.12709793058497637, | |
| "grad_norm": 1.264957070350647, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 1.2813, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.12774971484438652, | |
| "grad_norm": 1.1036807298660278, | |
| "learning_rate": 1.0931863906127327e-07, | |
| "loss": 1.0974, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.12840149910379664, | |
| "grad_norm": 1.3171941041946411, | |
| "learning_rate": 6.150154258476315e-08, | |
| "loss": 1.2015, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.1290532833632068, | |
| "grad_norm": 1.4972693920135498, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 1.4118, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.1297050676226169, | |
| "grad_norm": 1.881248950958252, | |
| "learning_rate": 6.834750376549792e-09, | |
| "loss": 1.1438, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.13035685188202706, | |
| "grad_norm": 2.239445447921753, | |
| "learning_rate": 0.0, | |
| "loss": 1.6636, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13035685188202706, | |
| "eval_loss": 1.361222743988037, | |
| "eval_runtime": 203.746, | |
| "eval_samples_per_second": 12.682, | |
| "eval_steps_per_second": 3.171, | |
| "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": 2.86984941600768e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |