| { | |
| "best_metric": 1.031202793121338, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.0184314809694959, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000184314809694959, | |
| "grad_norm": 5.6318583488464355, | |
| "learning_rate": 1e-05, | |
| "loss": 1.5347, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000184314809694959, | |
| "eval_loss": 1.8659999370574951, | |
| "eval_runtime": 690.4469, | |
| "eval_samples_per_second": 13.235, | |
| "eval_steps_per_second": 3.309, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000368629619389918, | |
| "grad_norm": 6.1715569496154785, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4167, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000552944429084877, | |
| "grad_norm": 8.9030179977417, | |
| "learning_rate": 3e-05, | |
| "loss": 1.4119, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000737259238779836, | |
| "grad_norm": 3.8838179111480713, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3732, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009215740484747949, | |
| "grad_norm": 2.0309371948242188, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3939, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001105888858169754, | |
| "grad_norm": 2.3626461029052734, | |
| "learning_rate": 6e-05, | |
| "loss": 1.3555, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001290203667864713, | |
| "grad_norm": 1.0350866317749023, | |
| "learning_rate": 7e-05, | |
| "loss": 1.3572, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001474518477559672, | |
| "grad_norm": 0.9269211292266846, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3471, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0016588332872546309, | |
| "grad_norm": 0.5549191236495972, | |
| "learning_rate": 9e-05, | |
| "loss": 1.1463, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0018431480969495898, | |
| "grad_norm": 0.6531222462654114, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1916, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0020274629066445488, | |
| "grad_norm": 0.6145579218864441, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.2206, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002211777716339508, | |
| "grad_norm": 0.5604798793792725, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 1.1826, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0023960925260344667, | |
| "grad_norm": 0.5696496367454529, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 1.0996, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002580407335729426, | |
| "grad_norm": 0.4159340262413025, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.1148, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002764722145424385, | |
| "grad_norm": 0.36338186264038086, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.2153, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002949036955119344, | |
| "grad_norm": 0.4037957191467285, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 1.1852, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.003133351764814303, | |
| "grad_norm": 0.3298725485801697, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 1.178, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0033176665745092617, | |
| "grad_norm": 0.3211928606033325, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 1.1417, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003501981384204221, | |
| "grad_norm": 0.3271002173423767, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 1.0869, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0036862961938991796, | |
| "grad_norm": 0.3212750256061554, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 1.225, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003870611003594139, | |
| "grad_norm": 0.30292510986328125, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 1.0461, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0040549258132890975, | |
| "grad_norm": 0.32509174942970276, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 1.051, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004239240622984057, | |
| "grad_norm": 0.34532973170280457, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 1.1228, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004423555432679016, | |
| "grad_norm": 0.42038172483444214, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 1.0871, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004607870242373975, | |
| "grad_norm": 0.37254562973976135, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 1.1268, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004792185052068933, | |
| "grad_norm": 0.3617491126060486, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 1.0728, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0049764998617638926, | |
| "grad_norm": 0.36921921372413635, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 1.098, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.005160814671458852, | |
| "grad_norm": 0.4023534953594208, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 1.1402, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.005345129481153811, | |
| "grad_norm": 0.34242668747901917, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.1111, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.00552944429084877, | |
| "grad_norm": 0.4034554064273834, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.1581, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005713759100543728, | |
| "grad_norm": 0.33662593364715576, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 1.0005, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.005898073910238688, | |
| "grad_norm": 0.3856150209903717, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 1.121, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.006082388719933647, | |
| "grad_norm": 0.37353983521461487, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 1.1154, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.006266703529628606, | |
| "grad_norm": 0.4448533058166504, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 1.1909, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.006451018339323564, | |
| "grad_norm": 0.4428851008415222, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 1.1107, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006635333149018523, | |
| "grad_norm": 0.4387335181236267, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 1.0992, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.006819647958713483, | |
| "grad_norm": 0.47019171714782715, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 1.1371, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.007003962768408442, | |
| "grad_norm": 0.4469152092933655, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 1.13, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.007188277578103401, | |
| "grad_norm": 0.45129719376564026, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 1.1404, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.007372592387798359, | |
| "grad_norm": 0.5520405769348145, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 1.2157, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0075569071974933184, | |
| "grad_norm": 0.5522369146347046, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 1.0666, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.007741222007188278, | |
| "grad_norm": 0.5612422823905945, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 1.215, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.007925536816883237, | |
| "grad_norm": 0.5706326365470886, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 1.1647, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.008109851626578195, | |
| "grad_norm": 0.6179230809211731, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 1.1573, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.008294166436273155, | |
| "grad_norm": 0.6024773716926575, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 1.1301, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008478481245968113, | |
| "grad_norm": 0.6232503056526184, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 1.0745, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.008662796055663072, | |
| "grad_norm": 0.6185201406478882, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 1.0483, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.008847110865358032, | |
| "grad_norm": 0.6560455560684204, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.0439, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.00903142567505299, | |
| "grad_norm": 0.7669586539268494, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 1.0518, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.00921574048474795, | |
| "grad_norm": 0.9614732265472412, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.8784, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00921574048474795, | |
| "eval_loss": 1.1081956624984741, | |
| "eval_runtime": 692.2817, | |
| "eval_samples_per_second": 13.2, | |
| "eval_steps_per_second": 3.301, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.009400055294442908, | |
| "grad_norm": 0.48868894577026367, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 0.8871, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.009584370104137867, | |
| "grad_norm": 0.4619584381580353, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 0.9272, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.009768684913832827, | |
| "grad_norm": 0.4740832448005676, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 1.017, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.009952999723527785, | |
| "grad_norm": 0.36349406838417053, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 1.0592, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.010137314533222745, | |
| "grad_norm": 0.3204439878463745, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 0.9724, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.010321629342917703, | |
| "grad_norm": 0.2830290198326111, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 0.9933, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.010505944152612662, | |
| "grad_norm": 0.2824137806892395, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 1.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.010690258962307622, | |
| "grad_norm": 0.2988187074661255, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 1.028, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.01087457377200258, | |
| "grad_norm": 0.25733092427253723, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 1.0645, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.01105888858169754, | |
| "grad_norm": 0.29357191920280457, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 1.0244, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.011243203391392498, | |
| "grad_norm": 0.28911539912223816, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 1.0476, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.011427518201087457, | |
| "grad_norm": 0.307320237159729, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 1.0962, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.011611833010782417, | |
| "grad_norm": 0.28484243154525757, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 1.0024, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.011796147820477375, | |
| "grad_norm": 0.2947733998298645, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 0.934, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.011980462630172335, | |
| "grad_norm": 0.28290286660194397, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 0.92, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.012164777439867294, | |
| "grad_norm": 0.29178595542907715, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 1.035, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.012349092249562252, | |
| "grad_norm": 0.2829218804836273, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 1.0749, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.012533407059257212, | |
| "grad_norm": 0.3027656376361847, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 1.0472, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.01271772186895217, | |
| "grad_norm": 0.3055793344974518, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 1.0366, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.012902036678647128, | |
| "grad_norm": 0.2900894582271576, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 1.063, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.013086351488342089, | |
| "grad_norm": 0.2908357083797455, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 1.0328, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.013270666298037047, | |
| "grad_norm": 0.2756956219673157, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.9437, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.013454981107732007, | |
| "grad_norm": 0.2930951416492462, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 1.0172, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.013639295917426965, | |
| "grad_norm": 0.29136356711387634, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 1.0952, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.013823610727121923, | |
| "grad_norm": 0.32149508595466614, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.9384, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.014007925536816884, | |
| "grad_norm": 0.3315494954586029, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 1.0781, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.014192240346511842, | |
| "grad_norm": 0.31092604994773865, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 1.0356, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.014376555156206802, | |
| "grad_norm": 0.3504660427570343, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 1.1046, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.01456086996590176, | |
| "grad_norm": 0.31477150321006775, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 1.0652, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.014745184775596719, | |
| "grad_norm": 0.3404114544391632, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 1.0259, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.014929499585291679, | |
| "grad_norm": 0.32545822858810425, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 1.0509, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.015113814394986637, | |
| "grad_norm": 0.3260136544704437, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 1.0279, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.015298129204681597, | |
| "grad_norm": 0.37822264432907104, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 0.9802, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.015482444014376555, | |
| "grad_norm": 0.37306562066078186, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 1.1249, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.015666758824071515, | |
| "grad_norm": 0.37852713465690613, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 1.1109, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.015851073633766474, | |
| "grad_norm": 0.3962250351905823, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.1005, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.016035388443461432, | |
| "grad_norm": 0.41836705803871155, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 1.0755, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.01621970325315639, | |
| "grad_norm": 0.4547691345214844, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 1.071, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.01640401806285135, | |
| "grad_norm": 0.4516165256500244, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 1.089, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.01658833287254631, | |
| "grad_norm": 0.46264412999153137, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 1.0303, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.01677264768224127, | |
| "grad_norm": 0.5163282752037048, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 1.0642, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.016956962491936227, | |
| "grad_norm": 0.49469366669654846, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 0.9772, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.017141277301631185, | |
| "grad_norm": 0.5242800712585449, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 1.0933, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.017325592111326144, | |
| "grad_norm": 0.5365490913391113, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 0.9827, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.017509906921021105, | |
| "grad_norm": 0.5569202899932861, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 1.1377, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.017694221730716064, | |
| "grad_norm": 0.6217386722564697, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 1.0177, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.017878536540411022, | |
| "grad_norm": 0.6114227175712585, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 0.9871, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.01806285135010598, | |
| "grad_norm": 0.6836398243904114, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 0.9991, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.01824716615980094, | |
| "grad_norm": 0.7496846914291382, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 1.0059, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.0184314809694959, | |
| "grad_norm": 0.8987806439399719, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.7866, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0184314809694959, | |
| "eval_loss": 1.031202793121338, | |
| "eval_runtime": 692.9955, | |
| "eval_samples_per_second": 13.186, | |
| "eval_steps_per_second": 3.297, | |
| "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": 1.4158528819023053e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |