| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.5675837397575378, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.6417, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.5383580923080444, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 0.6334, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.523246705532074, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 0.6413, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.4905203580856323, | |
| "learning_rate": 0.00011428571428571428, | |
| "loss": 0.665, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.5177513957023621, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 0.6041, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.482448011636734, | |
| "learning_rate": 0.00017142857142857143, | |
| "loss": 0.6078, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.49536892771720886, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6412, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.5152004361152649, | |
| "learning_rate": 0.00019996456111234527, | |
| "loss": 0.607, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.496277391910553, | |
| "learning_rate": 0.0001998582695676762, | |
| "loss": 0.6227, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.5162248611450195, | |
| "learning_rate": 0.000199681200703075, | |
| "loss": 0.6012, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.5029735565185547, | |
| "learning_rate": 0.00019943348002101371, | |
| "loss": 0.5842, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.5039064884185791, | |
| "learning_rate": 0.00019911528310040074, | |
| "loss": 0.5833, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.486408531665802, | |
| "learning_rate": 0.00019872683547213446, | |
| "loss": 0.57, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.48064252734184265, | |
| "learning_rate": 0.00019826841245925212, | |
| "loss": 0.5857, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.4762842655181885, | |
| "learning_rate": 0.00019774033898178667, | |
| "loss": 0.5434, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.4918793737888336, | |
| "learning_rate": 0.00019714298932647098, | |
| "loss": 0.5295, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.4949023425579071, | |
| "learning_rate": 0.0001964767868814516, | |
| "loss": 0.5382, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.4618944227695465, | |
| "learning_rate": 0.00019574220383620055, | |
| "loss": 0.517, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.4404259920120239, | |
| "learning_rate": 0.00019493976084683813, | |
| "loss": 0.5089, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.47014883160591125, | |
| "learning_rate": 0.00019407002666710336, | |
| "loss": 0.5412, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.49193090200424194, | |
| "learning_rate": 0.00019313361774523385, | |
| "loss": 0.5533, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.47287049889564514, | |
| "learning_rate": 0.00019213119778704128, | |
| "loss": 0.486, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.4395417273044586, | |
| "learning_rate": 0.00019106347728549135, | |
| "loss": 0.4964, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.4677005708217621, | |
| "learning_rate": 0.00018993121301712193, | |
| "loss": 0.5101, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.4530835449695587, | |
| "learning_rate": 0.00018873520750565718, | |
| "loss": 0.4903, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.41354307532310486, | |
| "learning_rate": 0.00018747630845319612, | |
| "loss": 0.3837, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.4053184986114502, | |
| "learning_rate": 0.0001861554081393806, | |
| "loss": 0.3586, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.39625370502471924, | |
| "learning_rate": 0.0001847734427889671, | |
| "loss": 0.3408, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.3945152759552002, | |
| "learning_rate": 0.0001833313919082515, | |
| "loss": 0.3329, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.45374399423599243, | |
| "learning_rate": 0.0001818302775908169, | |
| "loss": 0.3273, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.44107717275619507, | |
| "learning_rate": 0.00018027116379309638, | |
| "loss": 0.3397, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.46182313561439514, | |
| "learning_rate": 0.00017865515558026428, | |
| "loss": 0.3439, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.4914720356464386, | |
| "learning_rate": 0.00017698339834299061, | |
| "loss": 0.3415, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.3599999999999999, | |
| "grad_norm": 0.46283280849456787, | |
| "learning_rate": 0.00017525707698561385, | |
| "loss": 0.3309, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.47037574648857117, | |
| "learning_rate": 0.00017347741508630672, | |
| "loss": 0.3311, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.4362049102783203, | |
| "learning_rate": 0.00017164567402983152, | |
| "loss": 0.3185, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.4418430030345917, | |
| "learning_rate": 0.0001697631521134985, | |
| "loss": 0.3189, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.4334975779056549, | |
| "learning_rate": 0.00016783118362696163, | |
| "loss": 0.3152, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.42978766560554504, | |
| "learning_rate": 0.00016585113790650388, | |
| "loss": 0.3302, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.4448607563972473, | |
| "learning_rate": 0.00016382441836448202, | |
| "loss": 0.3311, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6400000000000001, | |
| "grad_norm": 0.40594780445098877, | |
| "learning_rate": 0.0001617524614946192, | |
| "loss": 0.326, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 0.4091069996356964, | |
| "learning_rate": 0.00015963673585385016, | |
| "loss": 0.3374, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.42589232325553894, | |
| "learning_rate": 0.0001574787410214407, | |
| "loss": 0.3228, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.413335919380188, | |
| "learning_rate": 0.00015528000653611935, | |
| "loss": 0.3234, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.44703832268714905, | |
| "learning_rate": 0.00015304209081197425, | |
| "loss": 0.3352, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.8399999999999999, | |
| "grad_norm": 0.42445358633995056, | |
| "learning_rate": 0.000150766580033884, | |
| "loss": 0.3429, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.39593955874443054, | |
| "learning_rate": 0.00014845508703326504, | |
| "loss": 0.3247, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.40969106554985046, | |
| "learning_rate": 0.0001461092501449326, | |
| "loss": 0.3126, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.4226933717727661, | |
| "learning_rate": 0.00014373073204588556, | |
| "loss": 0.3184, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.4182460308074951, | |
| "learning_rate": 0.00014132121857683783, | |
| "loss": 0.3263, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "grad_norm": 0.3583109676837921, | |
| "learning_rate": 0.00013888241754733208, | |
| "loss": 0.2484, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 0.3850906491279602, | |
| "learning_rate": 0.00013641605752528224, | |
| "loss": 0.24, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": 0.3770233392715454, | |
| "learning_rate": 0.00013392388661180303, | |
| "loss": 0.2334, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 0.374737024307251, | |
| "learning_rate": 0.0001314076712021949, | |
| "loss": 0.244, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 0.37868672609329224, | |
| "learning_rate": 0.0001288691947339621, | |
| "loss": 0.2134, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 0.41098785400390625, | |
| "learning_rate": 0.00012631025642275212, | |
| "loss": 0.2373, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.2800000000000002, | |
| "grad_norm": 0.3870932161808014, | |
| "learning_rate": 0.0001237326699871115, | |
| "loss": 0.2238, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "grad_norm": 0.4083153307437897, | |
| "learning_rate": 0.00012113826236296244, | |
| "loss": 0.2141, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "grad_norm": 0.412580668926239, | |
| "learning_rate": 0.00011852887240871145, | |
| "loss": 0.2201, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 0.4499835968017578, | |
| "learning_rate": 0.00011590634960190721, | |
| "loss": 0.2215, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "grad_norm": 0.48053982853889465, | |
| "learning_rate": 0.00011327255272837221, | |
| "loss": 0.217, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "grad_norm": 0.44269296526908875, | |
| "learning_rate": 0.00011062934856473655, | |
| "loss": 0.2212, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "grad_norm": 0.4232514202594757, | |
| "learning_rate": 0.00010797861055530831, | |
| "loss": 0.2289, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 0.41652482748031616, | |
| "learning_rate": 0.00010532221748421787, | |
| "loss": 0.2098, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "grad_norm": 0.39650851488113403, | |
| "learning_rate": 0.00010266205214377748, | |
| "loss": 0.195, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 0.39610394835472107, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1996, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "grad_norm": 0.3933280110359192, | |
| "learning_rate": 9.733794785622253e-05, | |
| "loss": 0.2243, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.7199999999999998, | |
| "grad_norm": 0.3946898579597473, | |
| "learning_rate": 9.467778251578217e-05, | |
| "loss": 0.2216, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "grad_norm": 0.4111415147781372, | |
| "learning_rate": 9.202138944469168e-05, | |
| "loss": 0.2261, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 0.4122645854949951, | |
| "learning_rate": 8.937065143526347e-05, | |
| "loss": 0.226, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "grad_norm": 0.4040912091732025, | |
| "learning_rate": 8.672744727162781e-05, | |
| "loss": 0.2397, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 0.4039236605167389, | |
| "learning_rate": 8.409365039809281e-05, | |
| "loss": 0.214, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "grad_norm": 0.39346644282341003, | |
| "learning_rate": 8.147112759128859e-05, | |
| "loss": 0.2211, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": 0.4206030070781708, | |
| "learning_rate": 7.886173763703757e-05, | |
| "loss": 0.2193, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.3998810648918152, | |
| "learning_rate": 7.626733001288851e-05, | |
| "loss": 0.2129, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "grad_norm": 0.3447999060153961, | |
| "learning_rate": 7.368974357724789e-05, | |
| "loss": 0.1809, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "grad_norm": 0.3176288306713104, | |
| "learning_rate": 7.113080526603792e-05, | |
| "loss": 0.1648, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "grad_norm": 0.32004985213279724, | |
| "learning_rate": 6.859232879780515e-05, | |
| "loss": 0.1582, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "grad_norm": 0.31019288301467896, | |
| "learning_rate": 6.607611338819697e-05, | |
| "loss": 0.1502, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.31684502959251404, | |
| "learning_rate": 6.358394247471778e-05, | |
| "loss": 0.1514, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "grad_norm": 0.3580498695373535, | |
| "learning_rate": 6.111758245266794e-05, | |
| "loss": 0.1533, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2800000000000002, | |
| "grad_norm": 0.3377327024936676, | |
| "learning_rate": 5.867878142316221e-05, | |
| "loss": 0.1522, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "grad_norm": 0.36469805240631104, | |
| "learning_rate": 5.626926795411447e-05, | |
| "loss": 0.1625, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "grad_norm": 0.3576640486717224, | |
| "learning_rate": 5.38907498550674e-05, | |
| "loss": 0.1491, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "grad_norm": 0.36043015122413635, | |
| "learning_rate": 5.1544912966734994e-05, | |
| "loss": 0.1561, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "grad_norm": 0.3925049602985382, | |
| "learning_rate": 4.9233419966116036e-05, | |
| "loss": 0.1526, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "grad_norm": 0.3896467685699463, | |
| "learning_rate": 4.695790918802576e-05, | |
| "loss": 0.1626, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "grad_norm": 0.38003793358802795, | |
| "learning_rate": 4.47199934638807e-05, | |
| "loss": 0.1483, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "grad_norm": 0.3852701187133789, | |
| "learning_rate": 4.252125897855932e-05, | |
| "loss": 0.1494, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "grad_norm": 0.38289740681648254, | |
| "learning_rate": 4.036326414614985e-05, | |
| "loss": 0.1694, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "grad_norm": 0.3584575057029724, | |
| "learning_rate": 3.824753850538082e-05, | |
| "loss": 0.1581, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "grad_norm": 0.36479833722114563, | |
| "learning_rate": 3.617558163551802e-05, | |
| "loss": 0.1567, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.7199999999999998, | |
| "grad_norm": 0.3648757338523865, | |
| "learning_rate": 3.414886209349615e-05, | |
| "loss": 0.1539, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "grad_norm": 0.3735385835170746, | |
| "learning_rate": 3.216881637303839e-05, | |
| "loss": 0.1455, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "grad_norm": 0.3788692355155945, | |
| "learning_rate": 3.0236847886501542e-05, | |
| "loss": 0.1512, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "grad_norm": 0.36534735560417175, | |
| "learning_rate": 2.8354325970168484e-05, | |
| "loss": 0.1539, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "grad_norm": 0.3561382591724396, | |
| "learning_rate": 2.6522584913693294e-05, | |
| "loss": 0.1613, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "grad_norm": 0.36043405532836914, | |
| "learning_rate": 2.4742923014386156e-05, | |
| "loss": 0.1399, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "grad_norm": 0.3461771011352539, | |
| "learning_rate": 2.301660165700936e-05, | |
| "loss": 0.1446, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.3610660135746002, | |
| "learning_rate": 2.1344844419735755e-05, | |
| "loss": 0.1669, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "grad_norm": 0.3192867636680603, | |
| "learning_rate": 1.9728836206903656e-05, | |
| "loss": 0.138, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "grad_norm": 0.2961142957210541, | |
| "learning_rate": 1.8169722409183097e-05, | |
| "loss": 0.1251, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "grad_norm": 0.33224716782569885, | |
| "learning_rate": 1.6668608091748495e-05, | |
| "loss": 0.1307, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "grad_norm": 0.30373403429985046, | |
| "learning_rate": 1.522655721103291e-05, | |
| "loss": 0.1259, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "grad_norm": 0.31472688913345337, | |
| "learning_rate": 1.3844591860619383e-05, | |
| "loss": 0.1267, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "grad_norm": 0.3078845739364624, | |
| "learning_rate": 1.2523691546803873e-05, | |
| "loss": 0.123, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "grad_norm": 0.31925857067108154, | |
| "learning_rate": 1.1264792494342857e-05, | |
| "loss": 0.1326, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "grad_norm": 0.29572564363479614, | |
| "learning_rate": 1.0068786982878087e-05, | |
| "loss": 0.1162, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "grad_norm": 0.29332664608955383, | |
| "learning_rate": 8.936522714508678e-06, | |
| "loss": 0.1153, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "grad_norm": 0.29813987016677856, | |
| "learning_rate": 7.868802212958703e-06, | |
| "loss": 0.1166, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "grad_norm": 0.2909725308418274, | |
| "learning_rate": 6.866382254766157e-06, | |
| "loss": 0.108, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "grad_norm": 0.31103241443634033, | |
| "learning_rate": 5.929973332896677e-06, | |
| "loss": 0.1228, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "grad_norm": 0.29073992371559143, | |
| "learning_rate": 5.060239153161872e-06, | |
| "loss": 0.118, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.5600000000000005, | |
| "grad_norm": 0.288641095161438, | |
| "learning_rate": 4.257796163799455e-06, | |
| "loss": 0.1184, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "grad_norm": 0.3088034689426422, | |
| "learning_rate": 3.5232131185484076e-06, | |
| "loss": 0.1285, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "grad_norm": 0.30730554461479187, | |
| "learning_rate": 2.857010673529015e-06, | |
| "loss": 0.1263, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "grad_norm": 0.291875422000885, | |
| "learning_rate": 2.259661018213333e-06, | |
| "loss": 0.108, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "grad_norm": 0.31049686670303345, | |
| "learning_rate": 1.7315875407479032e-06, | |
| "loss": 0.1225, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "grad_norm": 0.32437863945961, | |
| "learning_rate": 1.2731645278655445e-06, | |
| "loss": 0.1431, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "grad_norm": 0.3190011978149414, | |
| "learning_rate": 8.847168995992916e-07, | |
| "loss": 0.1298, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "grad_norm": 0.3092647194862366, | |
| "learning_rate": 5.665199789862907e-07, | |
| "loss": 0.1333, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "grad_norm": 0.3259420096874237, | |
| "learning_rate": 3.1879929692498757e-07, | |
| "loss": 0.1312, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "grad_norm": 0.31257393956184387, | |
| "learning_rate": 1.4173043232380557e-07, | |
| "loss": 0.1255, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "grad_norm": 0.310062438249588, | |
| "learning_rate": 3.5438887654737355e-08, | |
| "loss": 0.1155, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.3081853687763214, | |
| "learning_rate": 0.0, | |
| "loss": 0.1245, | |
| "step": 125 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 125, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.8813347440214016e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |