| { |
| "best_metric": 0.05914134532213211, |
| "best_model_checkpoint": "saves/psy-course-doc-info/Llama-3.1-8B-Instruct/train/fold8/checkpoint-120", |
| "epoch": 4.938271604938271, |
| "eval_steps": 10, |
| "global_step": 125, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03950617283950617, |
| "grad_norm": 0.4311501383781433, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.3733, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 0.4168970286846161, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.3702, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 0.4759407341480255, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.3825, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 0.3973632752895355, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.349, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 0.3906443417072296, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.326, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 0.47783976793289185, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.3572, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 0.44277405738830566, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.3243, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 0.4378047585487366, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.304, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 0.35153862833976746, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.2805, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 0.44192877411842346, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.2773, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 0.27391907572746277, |
| "eval_runtime": 28.551, |
| "eval_samples_per_second": 1.576, |
| "eval_steps_per_second": 1.576, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 0.5524961948394775, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.2835, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 0.574954628944397, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.2666, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 0.46546486020088196, |
| "learning_rate": 0.0001, |
| "loss": 0.2236, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 0.35821306705474854, |
| "learning_rate": 9.998033131915266e-05, |
| "loss": 0.2079, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.30893611907958984, |
| "learning_rate": 9.992134075089084e-05, |
| "loss": 0.195, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 0.31012162566185, |
| "learning_rate": 9.982307470588098e-05, |
| "loss": 0.1917, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 0.3026062250137329, |
| "learning_rate": 9.968561049466214e-05, |
| "loss": 0.1928, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.30849477648735046, |
| "learning_rate": 9.950905626682228e-05, |
| "loss": 0.1678, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 0.2820775508880615, |
| "learning_rate": 9.92935509259118e-05, |
| "loss": 0.1758, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.2553909420967102, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.1445, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.14966602623462677, |
| "eval_runtime": 28.3381, |
| "eval_samples_per_second": 1.588, |
| "eval_steps_per_second": 1.588, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 0.3081815540790558, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 0.1588, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 0.37473446130752563, |
| "learning_rate": 9.841517610611309e-05, |
| "loss": 0.1397, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 0.30875682830810547, |
| "learning_rate": 9.804586609725499e-05, |
| "loss": 0.1342, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 0.3308342695236206, |
| "learning_rate": 9.763875613614482e-05, |
| "loss": 0.1437, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.2710496485233307, |
| "learning_rate": 9.719416651541839e-05, |
| "loss": 0.1308, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0271604938271606, |
| "grad_norm": 0.703623354434967, |
| "learning_rate": 9.671244701472999e-05, |
| "loss": 0.2146, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.3301350474357605, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.1084, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.106172839506173, |
| "grad_norm": 0.42952051758766174, |
| "learning_rate": 9.563916325306594e-05, |
| "loss": 0.1348, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.145679012345679, |
| "grad_norm": 0.2704355716705322, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.1234, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "grad_norm": 0.35829588770866394, |
| "learning_rate": 9.442228179894362e-05, |
| "loss": 0.1055, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "eval_loss": 0.11220573633909225, |
| "eval_runtime": 28.3419, |
| "eval_samples_per_second": 1.588, |
| "eval_steps_per_second": 1.588, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2246913580246914, |
| "grad_norm": 0.2162196785211563, |
| "learning_rate": 9.376117109543769e-05, |
| "loss": 0.0727, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2641975308641975, |
| "grad_norm": 0.33504047989845276, |
| "learning_rate": 9.306563141162046e-05, |
| "loss": 0.1157, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.3037037037037038, |
| "grad_norm": 0.24898596107959747, |
| "learning_rate": 9.233620996141421e-05, |
| "loss": 0.0912, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.34320987654321, |
| "grad_norm": 0.2832293212413788, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.0974, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.382716049382716, |
| "grad_norm": 0.28242823481559753, |
| "learning_rate": 9.077804344796302e-05, |
| "loss": 0.0919, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.2866489887237549, |
| "learning_rate": 8.995052426791247e-05, |
| "loss": 0.0888, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.4617283950617284, |
| "grad_norm": 0.27560609579086304, |
| "learning_rate": 8.90915741234015e-05, |
| "loss": 0.083, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.5012345679012347, |
| "grad_norm": 0.28571322560310364, |
| "learning_rate": 8.820186879108038e-05, |
| "loss": 0.0932, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.5407407407407407, |
| "grad_norm": 0.2709600627422333, |
| "learning_rate": 8.728210824415827e-05, |
| "loss": 0.0847, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "grad_norm": 0.21476197242736816, |
| "learning_rate": 8.633301610170135e-05, |
| "loss": 0.0708, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "eval_loss": 0.08975765109062195, |
| "eval_runtime": 28.3482, |
| "eval_samples_per_second": 1.587, |
| "eval_steps_per_second": 1.587, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6197530864197531, |
| "grad_norm": 0.300514817237854, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.1042, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6592592592592592, |
| "grad_norm": 0.24534659087657928, |
| "learning_rate": 8.434984630174509e-05, |
| "loss": 0.0669, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.6987654320987655, |
| "grad_norm": 0.2643331289291382, |
| "learning_rate": 8.33173288976002e-05, |
| "loss": 0.0889, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.7382716049382716, |
| "grad_norm": 0.28658440709114075, |
| "learning_rate": 8.225859917710439e-05, |
| "loss": 0.0883, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.21738804876804352, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.0603, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.817283950617284, |
| "grad_norm": 0.21699436008930206, |
| "learning_rate": 8.006585456492029e-05, |
| "loss": 0.0662, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.8567901234567903, |
| "grad_norm": 0.3024793267250061, |
| "learning_rate": 7.89335648089903e-05, |
| "loss": 0.106, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.8962962962962964, |
| "grad_norm": 0.2880363464355469, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.0655, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.9358024691358025, |
| "grad_norm": 0.2906877100467682, |
| "learning_rate": 7.660160382576683e-05, |
| "loss": 0.0707, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "grad_norm": 0.22044140100479126, |
| "learning_rate": 7.540376726232648e-05, |
| "loss": 0.0684, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "eval_loss": 0.07698836177587509, |
| "eval_runtime": 28.3291, |
| "eval_samples_per_second": 1.588, |
| "eval_steps_per_second": 1.588, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0148148148148146, |
| "grad_norm": 0.3665280342102051, |
| "learning_rate": 7.4185944355262e-05, |
| "loss": 0.1001, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.054320987654321, |
| "grad_norm": 0.31293874979019165, |
| "learning_rate": 7.294909322337689e-05, |
| "loss": 0.0614, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.093827160493827, |
| "grad_norm": 0.3628917634487152, |
| "learning_rate": 7.169418695587791e-05, |
| "loss": 0.0572, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.2650579512119293, |
| "learning_rate": 7.042221284679982e-05, |
| "loss": 0.0693, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.1728395061728394, |
| "grad_norm": 0.21211613714694977, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.057, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.212345679012346, |
| "grad_norm": 0.3100660741329193, |
| "learning_rate": 6.783107663311565e-05, |
| "loss": 0.0576, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.251851851851852, |
| "grad_norm": 0.25580716133117676, |
| "learning_rate": 6.651395309775837e-05, |
| "loss": 0.0552, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.291358024691358, |
| "grad_norm": 0.2666609585285187, |
| "learning_rate": 6.518383725548074e-05, |
| "loss": 0.0637, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.330864197530864, |
| "grad_norm": 0.25851911306381226, |
| "learning_rate": 6.384177557124247e-05, |
| "loss": 0.062, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "grad_norm": 0.1969081163406372, |
| "learning_rate": 6.248882390836135e-05, |
| "loss": 0.0595, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "eval_loss": 0.06951971352100372, |
| "eval_runtime": 28.3397, |
| "eval_samples_per_second": 1.588, |
| "eval_steps_per_second": 1.588, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.4098765432098768, |
| "grad_norm": 0.22541911900043488, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.057, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.449382716049383, |
| "grad_norm": 0.2766355276107788, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.0576, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 0.26666122674942017, |
| "learning_rate": 5.837531116523682e-05, |
| "loss": 0.0664, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.528395061728395, |
| "grad_norm": 0.22401662170886993, |
| "learning_rate": 5.698951697677498e-05, |
| "loss": 0.0622, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.567901234567901, |
| "grad_norm": 0.22098611295223236, |
| "learning_rate": 5.559822380516539e-05, |
| "loss": 0.074, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.6074074074074076, |
| "grad_norm": 0.23813539743423462, |
| "learning_rate": 5.420252624646238e-05, |
| "loss": 0.0635, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.6469135802469137, |
| "grad_norm": 0.18617506325244904, |
| "learning_rate": 5.2803522361859594e-05, |
| "loss": 0.0621, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.68641975308642, |
| "grad_norm": 0.21707528829574585, |
| "learning_rate": 5.140231281379345e-05, |
| "loss": 0.0504, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.725925925925926, |
| "grad_norm": 0.2116302102804184, |
| "learning_rate": 5e-05, |
| "loss": 0.0583, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "grad_norm": 0.1969866156578064, |
| "learning_rate": 4.859768718620656e-05, |
| "loss": 0.054, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "eval_loss": 0.06469142436981201, |
| "eval_runtime": 28.3092, |
| "eval_samples_per_second": 1.59, |
| "eval_steps_per_second": 1.59, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8049382716049385, |
| "grad_norm": 0.16579212248325348, |
| "learning_rate": 4.7196477638140404e-05, |
| "loss": 0.0556, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 0.18136507272720337, |
| "learning_rate": 4.579747375353763e-05, |
| "loss": 0.0584, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.8839506172839506, |
| "grad_norm": 0.2566329836845398, |
| "learning_rate": 4.4401776194834613e-05, |
| "loss": 0.0526, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.9234567901234567, |
| "grad_norm": 0.24844352900981903, |
| "learning_rate": 4.3010483023225045e-05, |
| "loss": 0.0627, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.962962962962963, |
| "grad_norm": 0.1949816793203354, |
| "learning_rate": 4.162468883476319e-05, |
| "loss": 0.0495, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0024691358024693, |
| "grad_norm": 0.3685036897659302, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.0916, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.0419753086419754, |
| "grad_norm": 0.1892664134502411, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.0481, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.0814814814814815, |
| "grad_norm": 0.17612430453300476, |
| "learning_rate": 3.7511176091638653e-05, |
| "loss": 0.0383, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.1209876543209876, |
| "grad_norm": 0.2572883665561676, |
| "learning_rate": 3.6158224428757535e-05, |
| "loss": 0.0482, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "grad_norm": 0.20305465161800385, |
| "learning_rate": 3.4816162744519263e-05, |
| "loss": 0.05, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "eval_loss": 0.06237329542636871, |
| "eval_runtime": 28.2541, |
| "eval_samples_per_second": 1.593, |
| "eval_steps_per_second": 1.593, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.17858922481536865, |
| "learning_rate": 3.3486046902241664e-05, |
| "loss": 0.0465, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2395061728395063, |
| "grad_norm": 0.222541943192482, |
| "learning_rate": 3.216892336688435e-05, |
| "loss": 0.0493, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.2790123456790123, |
| "grad_norm": 0.17371205985546112, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.0441, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.3185185185185184, |
| "grad_norm": 0.1984930783510208, |
| "learning_rate": 2.9577787153200197e-05, |
| "loss": 0.0423, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.3580246913580245, |
| "grad_norm": 0.17953994870185852, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.0477, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.397530864197531, |
| "grad_norm": 0.229425311088562, |
| "learning_rate": 2.705090677662311e-05, |
| "loss": 0.0568, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.437037037037037, |
| "grad_norm": 0.19390399754047394, |
| "learning_rate": 2.581405564473801e-05, |
| "loss": 0.053, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.476543209876543, |
| "grad_norm": 0.2115180641412735, |
| "learning_rate": 2.459623273767354e-05, |
| "loss": 0.0518, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.5160493827160493, |
| "grad_norm": 0.2087424099445343, |
| "learning_rate": 2.3398396174233178e-05, |
| "loss": 0.0486, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.2142495959997177, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.0569, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_loss": 0.06091349944472313, |
| "eval_runtime": 28.2654, |
| "eval_samples_per_second": 1.592, |
| "eval_steps_per_second": 1.592, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.595061728395062, |
| "grad_norm": 0.27506786584854126, |
| "learning_rate": 2.1066435191009715e-05, |
| "loss": 0.0534, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.634567901234568, |
| "grad_norm": 0.20141656696796417, |
| "learning_rate": 1.9934145435079702e-05, |
| "loss": 0.0426, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.674074074074074, |
| "grad_norm": 0.187766894698143, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.0433, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.71358024691358, |
| "grad_norm": 0.2187131941318512, |
| "learning_rate": 1.774140082289563e-05, |
| "loss": 0.0528, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.753086419753086, |
| "grad_norm": 0.27640262246131897, |
| "learning_rate": 1.6682671102399805e-05, |
| "loss": 0.0567, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.7925925925925927, |
| "grad_norm": 0.25254082679748535, |
| "learning_rate": 1.5650153698254916e-05, |
| "loss": 0.0399, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.832098765432099, |
| "grad_norm": 0.16558228433132172, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.0438, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.871604938271605, |
| "grad_norm": 0.20659472048282623, |
| "learning_rate": 1.3666983898298657e-05, |
| "loss": 0.0505, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 0.20600548386573792, |
| "learning_rate": 1.2717891755841722e-05, |
| "loss": 0.0471, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "grad_norm": 0.17909127473831177, |
| "learning_rate": 1.1798131208919627e-05, |
| "loss": 0.0492, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "eval_loss": 0.05985533818602562, |
| "eval_runtime": 28.3173, |
| "eval_samples_per_second": 1.589, |
| "eval_steps_per_second": 1.589, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.9901234567901236, |
| "grad_norm": 0.18871206045150757, |
| "learning_rate": 1.090842587659851e-05, |
| "loss": 0.0545, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.029629629629629, |
| "grad_norm": 0.30704087018966675, |
| "learning_rate": 1.004947573208756e-05, |
| "loss": 0.0778, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.069135802469136, |
| "grad_norm": 0.14208008348941803, |
| "learning_rate": 9.221956552036992e-06, |
| "loss": 0.0466, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.108641975308642, |
| "grad_norm": 0.1746240109205246, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.0378, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.148148148148148, |
| "grad_norm": 0.1741980016231537, |
| "learning_rate": 7.663790038585793e-06, |
| "loss": 0.0503, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.187654320987654, |
| "grad_norm": 0.20491904020309448, |
| "learning_rate": 6.934368588379553e-06, |
| "loss": 0.0519, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.22716049382716, |
| "grad_norm": 0.2031223475933075, |
| "learning_rate": 6.238828904562316e-06, |
| "loss": 0.0407, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.20566163957118988, |
| "learning_rate": 5.577718201056392e-06, |
| "loss": 0.0496, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.306172839506173, |
| "grad_norm": 0.16476655006408691, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.0449, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "grad_norm": 0.16324129700660706, |
| "learning_rate": 4.360836746934055e-06, |
| "loss": 0.0362, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "eval_loss": 0.05922485515475273, |
| "eval_runtime": 28.3158, |
| "eval_samples_per_second": 1.589, |
| "eval_steps_per_second": 1.589, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.385185185185185, |
| "grad_norm": 0.17888972163200378, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.0461, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.424691358024692, |
| "grad_norm": 0.14221294224262238, |
| "learning_rate": 3.2875529852700147e-06, |
| "loss": 0.0374, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.4641975308641975, |
| "grad_norm": 0.1701335906982422, |
| "learning_rate": 2.8058334845816213e-06, |
| "loss": 0.0414, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.503703703703704, |
| "grad_norm": 0.21760079264640808, |
| "learning_rate": 2.361243863855184e-06, |
| "loss": 0.0554, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.54320987654321, |
| "grad_norm": 0.1680031418800354, |
| "learning_rate": 1.9541339027450256e-06, |
| "loss": 0.0351, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.582716049382716, |
| "grad_norm": 0.18210847675800323, |
| "learning_rate": 1.584823893886933e-06, |
| "loss": 0.0495, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.1485206037759781, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 0.039, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.661728395061728, |
| "grad_norm": 0.1765493005514145, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.0526, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.701234567901235, |
| "grad_norm": 0.20030546188354492, |
| "learning_rate": 7.064490740882057e-07, |
| "loss": 0.0479, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "grad_norm": 0.2075965404510498, |
| "learning_rate": 4.909437331777179e-07, |
| "loss": 0.0464, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "eval_loss": 0.05914134532213211, |
| "eval_runtime": 28.3122, |
| "eval_samples_per_second": 1.589, |
| "eval_steps_per_second": 1.589, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.780246913580247, |
| "grad_norm": 0.1739559769630432, |
| "learning_rate": 3.143895053378698e-07, |
| "loss": 0.0401, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.8197530864197535, |
| "grad_norm": 0.18577301502227783, |
| "learning_rate": 1.7692529411904578e-07, |
| "loss": 0.0395, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.859259259259259, |
| "grad_norm": 0.1738099902868271, |
| "learning_rate": 7.865924910916977e-08, |
| "loss": 0.0438, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.898765432098766, |
| "grad_norm": 0.17269267141819, |
| "learning_rate": 1.9668680847356735e-08, |
| "loss": 0.0414, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "grad_norm": 0.18021945655345917, |
| "learning_rate": 0.0, |
| "loss": 0.0475, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "step": 125, |
| "total_flos": 1.668671807275008e+17, |
| "train_loss": 0.09916372174024582, |
| "train_runtime": 4791.8412, |
| "train_samples_per_second": 0.423, |
| "train_steps_per_second": 0.026 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 125, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.668671807275008e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
