| { |
| "best_metric": 0.3685910701751709, |
| "best_model_checkpoint": "../../text-generation-webui/loras/mistral-instruct-better-formatting-v1/checkpoint-135", |
| "epoch": 0.5162523900573613, |
| "eval_steps": 27, |
| "global_step": 135, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0, |
| "learning_rate": 0.0001, |
| "loss": 0.9252, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0, |
| "eval_loss": 0.9944313168525696, |
| "eval_runtime": 8.9255, |
| "eval_samples_per_second": 39.213, |
| "eval_steps_per_second": 9.859, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 0.0002, |
| "loss": 0.9232, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 0.0003, |
| "loss": 0.8082, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 0.0004, |
| "loss": 0.6783, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 0.0005, |
| "loss": 0.5423, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 0.0006, |
| "loss": 0.6041, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 0.0007, |
| "loss": 0.4542, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 0.0008, |
| "loss": 0.5088, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 0.0009000000000000001, |
| "loss": 0.5163, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 0.001, |
| "loss": 0.4498, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 0.0009999608360361113, |
| "loss": 0.4613, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.0009998433502797096, |
| "loss": 0.4891, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.0009996475611356265, |
| "loss": 0.4316, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.0009993734992753778, |
| "loss": 0.4464, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 0.0009990212076323587, |
| "loss": 0.4346, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 0.000998590741395118, |
| "loss": 0.3953, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.0009980821679987123, |
| "loss": 0.414, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.0009974955671141423, |
| "loss": 0.415, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.0009968310306358713, |
| "loss": 0.3885, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 0.00099608866266743, |
| "loss": 0.4143, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 0.0009952685795051076, |
| "loss": 0.4069, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 0.0009943709096197333, |
| "loss": 0.4054, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.0009933957936365514, |
| "loss": 0.3943, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.0009923433843131901, |
| "loss": 0.4342, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.0009912138465157324, |
| "loss": 0.4137, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.0009900073571928885, |
| "loss": 0.374, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.0009887241053482755, |
| "loss": 0.3953, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.1, |
| "eval_loss": 0.3981475234031677, |
| "eval_runtime": 9.1109, |
| "eval_samples_per_second": 38.415, |
| "eval_steps_per_second": 9.659, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.000987364292010809, |
| "loss": 0.4272, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.0009859281302032107, |
| "loss": 0.4212, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.0009844158449086372, |
| "loss": 0.3869, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.0009828276730354352, |
| "loss": 0.3549, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.0009811638633800287, |
| "loss": 0.39, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.000979424676587942, |
| "loss": 0.3672, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.0009776103851129704, |
| "loss": 0.3763, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.0009757212731744974, |
| "loss": 0.4669, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.0009737576367129695, |
| "loss": 0.4118, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.0009717197833435367, |
| "loss": 0.3796, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.0009696080323078621, |
| "loss": 0.403, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.000967422714424111, |
| "loss": 0.3771, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.0009651641720351261, |
| "loss": 0.4236, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.0009628327589547976, |
| "loss": 0.3739, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.0009604288404126362, |
| "loss": 0.3789, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.0009579527929965582, |
| "loss": 0.3923, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.0009554050045938894, |
| "loss": 0.4141, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.0009527858743306019, |
| "loss": 0.3981, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.0009500958125087882, |
| "loss": 0.3737, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.0009473352405423844, |
| "loss": 0.3878, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.0009445045908911536, |
| "loss": 0.3734, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.0009416043069929387, |
| "loss": 0.3647, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.0009386348431941953, |
| "loss": 0.3761, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.0009355966646788152, |
| "loss": 0.3846, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.0009324902473952528, |
| "loss": 0.3762, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.0009293160779819658, |
| "loss": 0.3907, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.000926074653691179, |
| "loss": 0.3662, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.21, |
| "eval_loss": 0.3824438154697418, |
| "eval_runtime": 9.1153, |
| "eval_samples_per_second": 38.397, |
| "eval_steps_per_second": 9.654, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.0009227664823109882, |
| "loss": 0.3862, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.0009193920820858111, |
| "loss": 0.409, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.000915951981635202, |
| "loss": 0.374, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00091244671987104, |
| "loss": 0.3829, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.000908876845913106, |
| "loss": 0.3919, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.0009052429190030589, |
| "loss": 0.3739, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.0009015455084168279, |
| "loss": 0.3918, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.0008977851933754317, |
| "loss": 0.3809, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.0008939625629542402, |
| "loss": 0.3554, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.0008900782159906927, |
| "loss": 0.4147, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.0008861327609904858, |
| "loss": 0.4175, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.0008821268160322482, |
| "loss": 0.36, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.0008780610086707148, |
| "loss": 0.3417, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.0008739359758384161, |
| "loss": 0.3486, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.0008697523637458997, |
| "loss": 0.4344, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.0008655108277804975, |
| "loss": 0.4002, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.0008612120324036547, |
| "loss": 0.4107, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.0008568566510468391, |
| "loss": 0.3752, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.0008524453660060433, |
| "loss": 0.3873, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.0008479788683348994, |
| "loss": 0.3487, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.0008434578577364219, |
| "loss": 0.3557, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.0008388830424533935, |
| "loss": 0.3841, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.0008342551391574165, |
| "loss": 0.3842, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.0008295748728366412, |
| "loss": 0.3597, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.0008248429766821926, |
| "loss": 0.3659, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.0008200601919733106, |
| "loss": 0.3921, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.0008152272679612261, |
| "loss": 0.3383, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.31, |
| "eval_loss": 0.37780898809432983, |
| "eval_runtime": 9.1104, |
| "eval_samples_per_second": 38.418, |
| "eval_steps_per_second": 9.659, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.000810344961751785, |
| "loss": 0.3658, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.0008054140381868435, |
| "loss": 0.4424, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.0008004352697244516, |
| "loss": 0.4, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.0007954094363178422, |
| "loss": 0.4207, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.0007903373252932473, |
| "loss": 0.4457, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.0007852197312265592, |
| "loss": 0.3963, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.0007800574558188547, |
| "loss": 0.3642, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.0007748513077708044, |
| "loss": 0.4025, |
| "step": 89 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.0007696021026559849, |
| "loss": 0.3789, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.0007643106627931147, |
| "loss": 0.4409, |
| "step": 91 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.0007589778171172321, |
| "loss": 0.3818, |
| "step": 92 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.0007536044010498396, |
| "loss": 0.3816, |
| "step": 93 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.000748191256368028, |
| "loss": 0.4157, |
| "step": 94 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.0007427392310726088, |
| "loss": 0.3725, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.0007372491792552693, |
| "loss": 0.4034, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.000731721960964774, |
| "loss": 0.3456, |
| "step": 97 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.0007261584420722328, |
| "loss": 0.3798, |
| "step": 98 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.000720559494135458, |
| "loss": 0.3309, |
| "step": 99 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.0007149259942624286, |
| "loss": 0.4046, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.0007092588249738871, |
| "loss": 0.3833, |
| "step": 101 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.0007035588740650869, |
| "loss": 0.3554, |
| "step": 102 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.0006978270344667142, |
| "loss": 0.389, |
| "step": 103 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.0006920642041050055, |
| "loss": 0.4031, |
| "step": 104 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.0006862712857610813, |
| "loss": 0.3599, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.0006804491869295207, |
| "loss": 0.359, |
| "step": 106 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.0006745988196761976, |
| "loss": 0.4034, |
| "step": 107 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.0006687211004953992, |
| "loss": 0.3484, |
| "step": 108 |
| }, |
| { |
| "epoch": 0.41, |
| "eval_loss": 0.3730239272117615, |
| "eval_runtime": 9.1206, |
| "eval_samples_per_second": 38.375, |
| "eval_steps_per_second": 9.648, |
| "step": 108 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.0006628169501662526, |
| "loss": 0.3735, |
| "step": 109 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.0006568872936084789, |
| "loss": 0.3637, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.0006509330597374993, |
| "loss": 0.3888, |
| "step": 111 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.000644955181318915, |
| "loss": 0.3852, |
| "step": 112 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.000638954594822384, |
| "loss": 0.3277, |
| "step": 113 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.000632932240274918, |
| "loss": 0.341, |
| "step": 114 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.000626889061113621, |
| "loss": 0.3207, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.0006208260040378946, |
| "loss": 0.3958, |
| "step": 116 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.0006147440188611324, |
| "loss": 0.4147, |
| "step": 117 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.0006086440583619257, |
| "loss": 0.4008, |
| "step": 118 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.0006025270781348054, |
| "loss": 0.3868, |
| "step": 119 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.0005963940364405425, |
| "loss": 0.4198, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.0005902458940560304, |
| "loss": 0.3412, |
| "step": 121 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.0005840836141237747, |
| "loss": 0.3843, |
| "step": 122 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.0005779081620010104, |
| "loss": 0.4006, |
| "step": 123 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.000571720505108473, |
| "loss": 0.3502, |
| "step": 124 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.0005655216127788471, |
| "loss": 0.3803, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.0005593124561049141, |
| "loss": 0.3338, |
| "step": 126 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.0005530940077874249, |
| "loss": 0.3904, |
| "step": 127 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.0005468672419827208, |
| "loss": 0.4288, |
| "step": 128 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.0005406331341501263, |
| "loss": 0.4279, |
| "step": 129 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.000534392660899138, |
| "loss": 0.4216, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.0005281467998364314, |
| "loss": 0.3592, |
| "step": 131 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.0005218965294127155, |
| "loss": 0.3659, |
| "step": 132 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.0005156428287694508, |
| "loss": 0.3812, |
| "step": 133 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.0005093866775854617, |
| "loss": 0.3631, |
| "step": 134 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.0005031290559234649, |
| "loss": 0.4098, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.52, |
| "eval_loss": 0.3685910701751709, |
| "eval_runtime": 9.1112, |
| "eval_samples_per_second": 38.414, |
| "eval_steps_per_second": 9.658, |
| "step": 135 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 261, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 27, |
| "total_flos": 3.8191644033417216e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
