| { |
| "best_metric": 0.13604725897312164, |
| "best_model_checkpoint": "saves/psy-course-info/Llama-3.1-8B-Instruct/train/fold8/checkpoint-80", |
| "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": 2.3129239082336426, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.979, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 2.1840054988861084, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 1.1572, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 2.2480788230895996, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 1.0986, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 2.4084527492523193, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 1.0493, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 2.3237855434417725, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 1.0138, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 2.7604610919952393, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 1.0267, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 2.486992120742798, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.8574, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 2.3500819206237793, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.6849, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 2.4173693656921387, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.5599, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 1.7449085712432861, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.5793, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 0.4396974742412567, |
| "eval_runtime": 21.23, |
| "eval_samples_per_second": 2.12, |
| "eval_steps_per_second": 2.12, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 1.0092576742172241, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.3847, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 1.13295316696167, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.5426, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 1.1906849145889282, |
| "learning_rate": 0.0001, |
| "loss": 0.3527, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 1.1590957641601562, |
| "learning_rate": 9.998033131915266e-05, |
| "loss": 0.3105, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 1.1589328050613403, |
| "learning_rate": 9.992134075089084e-05, |
| "loss": 0.3833, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 0.8769106268882751, |
| "learning_rate": 9.982307470588098e-05, |
| "loss": 0.2899, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 0.6918982267379761, |
| "learning_rate": 9.968561049466214e-05, |
| "loss": 0.3528, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.6679126024246216, |
| "learning_rate": 9.950905626682228e-05, |
| "loss": 0.2644, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 0.8453378677368164, |
| "learning_rate": 9.92935509259118e-05, |
| "loss": 0.2715, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.7257595658302307, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.3189, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.2390153855085373, |
| "eval_runtime": 21.046, |
| "eval_samples_per_second": 2.138, |
| "eval_steps_per_second": 2.138, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 0.6925722360610962, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 0.3506, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 0.8197972178459167, |
| "learning_rate": 9.841517610611309e-05, |
| "loss": 0.2298, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 0.6052566766738892, |
| "learning_rate": 9.804586609725499e-05, |
| "loss": 0.2231, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 0.6209917068481445, |
| "learning_rate": 9.763875613614482e-05, |
| "loss": 0.3174, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.8214046955108643, |
| "learning_rate": 9.719416651541839e-05, |
| "loss": 0.3354, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0271604938271606, |
| "grad_norm": 1.3651379346847534, |
| "learning_rate": 9.671244701472999e-05, |
| "loss": 0.5323, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.48607707023620605, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.1663, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.106172839506173, |
| "grad_norm": 0.5762261152267456, |
| "learning_rate": 9.563916325306594e-05, |
| "loss": 0.2065, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.145679012345679, |
| "grad_norm": 0.6236944794654846, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.1983, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "grad_norm": 0.6843675374984741, |
| "learning_rate": 9.442228179894362e-05, |
| "loss": 0.2334, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "eval_loss": 0.17819355428218842, |
| "eval_runtime": 21.0554, |
| "eval_samples_per_second": 2.137, |
| "eval_steps_per_second": 2.137, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2246913580246914, |
| "grad_norm": 0.5448902249336243, |
| "learning_rate": 9.376117109543769e-05, |
| "loss": 0.1896, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2641975308641975, |
| "grad_norm": 0.7466155886650085, |
| "learning_rate": 9.306563141162046e-05, |
| "loss": 0.2553, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.3037037037037038, |
| "grad_norm": 0.7103949785232544, |
| "learning_rate": 9.233620996141421e-05, |
| "loss": 0.2239, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.34320987654321, |
| "grad_norm": 0.5833294987678528, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.2126, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.382716049382716, |
| "grad_norm": 0.7536190748214722, |
| "learning_rate": 9.077804344796302e-05, |
| "loss": 0.1658, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.6158977746963501, |
| "learning_rate": 8.995052426791247e-05, |
| "loss": 0.1474, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.4617283950617284, |
| "grad_norm": 0.4840237498283386, |
| "learning_rate": 8.90915741234015e-05, |
| "loss": 0.1457, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.5012345679012347, |
| "grad_norm": 0.6149028539657593, |
| "learning_rate": 8.820186879108038e-05, |
| "loss": 0.1614, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.5407407407407407, |
| "grad_norm": 0.7064690589904785, |
| "learning_rate": 8.728210824415827e-05, |
| "loss": 0.2171, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "grad_norm": 0.5807669758796692, |
| "learning_rate": 8.633301610170135e-05, |
| "loss": 0.1602, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "eval_loss": 0.14948707818984985, |
| "eval_runtime": 21.038, |
| "eval_samples_per_second": 2.139, |
| "eval_steps_per_second": 2.139, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6197530864197531, |
| "grad_norm": 0.5889521837234497, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.1946, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6592592592592592, |
| "grad_norm": 0.48432469367980957, |
| "learning_rate": 8.434984630174509e-05, |
| "loss": 0.1063, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.6987654320987655, |
| "grad_norm": 0.5573430061340332, |
| "learning_rate": 8.33173288976002e-05, |
| "loss": 0.18, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.7382716049382716, |
| "grad_norm": 0.5946013927459717, |
| "learning_rate": 8.225859917710439e-05, |
| "loss": 0.1245, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.48479312658309937, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.1284, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.817283950617284, |
| "grad_norm": 0.5809167623519897, |
| "learning_rate": 8.006585456492029e-05, |
| "loss": 0.161, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.8567901234567903, |
| "grad_norm": 0.6000732183456421, |
| "learning_rate": 7.89335648089903e-05, |
| "loss": 0.1632, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.8962962962962964, |
| "grad_norm": 0.6094791293144226, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.1697, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.9358024691358025, |
| "grad_norm": 0.5543623566627502, |
| "learning_rate": 7.660160382576683e-05, |
| "loss": 0.1466, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "grad_norm": 0.5216181874275208, |
| "learning_rate": 7.540376726232648e-05, |
| "loss": 0.1259, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "eval_loss": 0.13782641291618347, |
| "eval_runtime": 21.0488, |
| "eval_samples_per_second": 2.138, |
| "eval_steps_per_second": 2.138, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0148148148148146, |
| "grad_norm": 1.0420159101486206, |
| "learning_rate": 7.4185944355262e-05, |
| "loss": 0.1748, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.054320987654321, |
| "grad_norm": 0.4040446877479553, |
| "learning_rate": 7.294909322337689e-05, |
| "loss": 0.0961, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.093827160493827, |
| "grad_norm": 0.445033997297287, |
| "learning_rate": 7.169418695587791e-05, |
| "loss": 0.1283, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.6002264022827148, |
| "learning_rate": 7.042221284679982e-05, |
| "loss": 0.1474, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.1728395061728394, |
| "grad_norm": 0.5108594298362732, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.1213, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.212345679012346, |
| "grad_norm": 0.5323643088340759, |
| "learning_rate": 6.783107663311565e-05, |
| "loss": 0.0995, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.251851851851852, |
| "grad_norm": 0.48319751024246216, |
| "learning_rate": 6.651395309775837e-05, |
| "loss": 0.0964, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.291358024691358, |
| "grad_norm": 0.6517108082771301, |
| "learning_rate": 6.518383725548074e-05, |
| "loss": 0.1564, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.330864197530864, |
| "grad_norm": 0.5919092893600464, |
| "learning_rate": 6.384177557124247e-05, |
| "loss": 0.1256, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "grad_norm": 0.5027915835380554, |
| "learning_rate": 6.248882390836135e-05, |
| "loss": 0.122, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "eval_loss": 0.13772016763687134, |
| "eval_runtime": 21.0499, |
| "eval_samples_per_second": 2.138, |
| "eval_steps_per_second": 2.138, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.4098765432098768, |
| "grad_norm": 0.5357543230056763, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.1193, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.449382716049383, |
| "grad_norm": 0.5479106307029724, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.128, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 0.5546219348907471, |
| "learning_rate": 5.837531116523682e-05, |
| "loss": 0.1158, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.528395061728395, |
| "grad_norm": 0.6667020916938782, |
| "learning_rate": 5.698951697677498e-05, |
| "loss": 0.1468, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.567901234567901, |
| "grad_norm": 0.7351205945014954, |
| "learning_rate": 5.559822380516539e-05, |
| "loss": 0.1454, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.6074074074074076, |
| "grad_norm": 0.5360890626907349, |
| "learning_rate": 5.420252624646238e-05, |
| "loss": 0.0804, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.6469135802469137, |
| "grad_norm": 0.8633858561515808, |
| "learning_rate": 5.2803522361859594e-05, |
| "loss": 0.1177, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.68641975308642, |
| "grad_norm": 0.4301098883152008, |
| "learning_rate": 5.140231281379345e-05, |
| "loss": 0.0628, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.725925925925926, |
| "grad_norm": 0.6666284799575806, |
| "learning_rate": 5e-05, |
| "loss": 0.1402, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "grad_norm": 0.5822936296463013, |
| "learning_rate": 4.859768718620656e-05, |
| "loss": 0.1298, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "eval_loss": 0.13793574273586273, |
| "eval_runtime": 21.0618, |
| "eval_samples_per_second": 2.137, |
| "eval_steps_per_second": 2.137, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8049382716049385, |
| "grad_norm": 0.6189770698547363, |
| "learning_rate": 4.7196477638140404e-05, |
| "loss": 0.1167, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 0.5474162697792053, |
| "learning_rate": 4.579747375353763e-05, |
| "loss": 0.0818, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.8839506172839506, |
| "grad_norm": 0.6895817518234253, |
| "learning_rate": 4.4401776194834613e-05, |
| "loss": 0.1191, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.9234567901234567, |
| "grad_norm": 0.6634834408760071, |
| "learning_rate": 4.3010483023225045e-05, |
| "loss": 0.1212, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.962962962962963, |
| "grad_norm": 0.4516965448856354, |
| "learning_rate": 4.162468883476319e-05, |
| "loss": 0.101, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0024691358024693, |
| "grad_norm": 1.4281126260757446, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.1806, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.0419753086419754, |
| "grad_norm": 0.4838202893733978, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.0729, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.0814814814814815, |
| "grad_norm": 0.49613136053085327, |
| "learning_rate": 3.7511176091638653e-05, |
| "loss": 0.0657, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.1209876543209876, |
| "grad_norm": 0.5470857620239258, |
| "learning_rate": 3.6158224428757535e-05, |
| "loss": 0.0855, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "grad_norm": 0.6039894223213196, |
| "learning_rate": 3.4816162744519263e-05, |
| "loss": 0.069, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "eval_loss": 0.13604725897312164, |
| "eval_runtime": 21.0616, |
| "eval_samples_per_second": 2.137, |
| "eval_steps_per_second": 2.137, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.5436442494392395, |
| "learning_rate": 3.3486046902241664e-05, |
| "loss": 0.0753, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2395061728395063, |
| "grad_norm": 0.5677600502967834, |
| "learning_rate": 3.216892336688435e-05, |
| "loss": 0.089, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.2790123456790123, |
| "grad_norm": 0.5541965365409851, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.1057, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.3185185185185184, |
| "grad_norm": 0.6926407814025879, |
| "learning_rate": 2.9577787153200197e-05, |
| "loss": 0.0871, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.3580246913580245, |
| "grad_norm": 0.5953899025917053, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.1024, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.397530864197531, |
| "grad_norm": 0.5269374251365662, |
| "learning_rate": 2.705090677662311e-05, |
| "loss": 0.0794, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.437037037037037, |
| "grad_norm": 0.7235696911811829, |
| "learning_rate": 2.581405564473801e-05, |
| "loss": 0.1081, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.476543209876543, |
| "grad_norm": 0.638532817363739, |
| "learning_rate": 2.459623273767354e-05, |
| "loss": 0.0874, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.5160493827160493, |
| "grad_norm": 0.7972421646118164, |
| "learning_rate": 2.3398396174233178e-05, |
| "loss": 0.1097, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.6267678141593933, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.1119, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_loss": 0.13853015005588531, |
| "eval_runtime": 21.0695, |
| "eval_samples_per_second": 2.136, |
| "eval_steps_per_second": 2.136, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.595061728395062, |
| "grad_norm": 0.4760293960571289, |
| "learning_rate": 2.1066435191009715e-05, |
| "loss": 0.0814, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.634567901234568, |
| "grad_norm": 0.591591477394104, |
| "learning_rate": 1.9934145435079702e-05, |
| "loss": 0.0766, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.674074074074074, |
| "grad_norm": 0.5675305128097534, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.0569, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.71358024691358, |
| "grad_norm": 0.757902204990387, |
| "learning_rate": 1.774140082289563e-05, |
| "loss": 0.103, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.753086419753086, |
| "grad_norm": 0.737522304058075, |
| "learning_rate": 1.6682671102399805e-05, |
| "loss": 0.0979, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.7925925925925927, |
| "grad_norm": 0.512159526348114, |
| "learning_rate": 1.5650153698254916e-05, |
| "loss": 0.0487, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.832098765432099, |
| "grad_norm": 0.4241292178630829, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.0558, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.871604938271605, |
| "grad_norm": 0.7563615441322327, |
| "learning_rate": 1.3666983898298657e-05, |
| "loss": 0.0936, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 0.7162846326828003, |
| "learning_rate": 1.2717891755841722e-05, |
| "loss": 0.08, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "grad_norm": 0.7690584659576416, |
| "learning_rate": 1.1798131208919627e-05, |
| "loss": 0.1059, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "eval_loss": 0.14245392382144928, |
| "eval_runtime": 21.0746, |
| "eval_samples_per_second": 2.135, |
| "eval_steps_per_second": 2.135, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.9901234567901236, |
| "grad_norm": 0.9220129251480103, |
| "learning_rate": 1.090842587659851e-05, |
| "loss": 0.1405, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.029629629629629, |
| "grad_norm": 1.5278953313827515, |
| "learning_rate": 1.004947573208756e-05, |
| "loss": 0.1666, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.069135802469136, |
| "grad_norm": 0.5032985210418701, |
| "learning_rate": 9.221956552036992e-06, |
| "loss": 0.0488, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.108641975308642, |
| "grad_norm": 0.5397678017616272, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.0522, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.148148148148148, |
| "grad_norm": 0.5098193287849426, |
| "learning_rate": 7.663790038585793e-06, |
| "loss": 0.0589, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.187654320987654, |
| "grad_norm": 0.6907945871353149, |
| "learning_rate": 6.934368588379553e-06, |
| "loss": 0.0921, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.22716049382716, |
| "grad_norm": 0.5158552527427673, |
| "learning_rate": 6.238828904562316e-06, |
| "loss": 0.08, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.5230313539505005, |
| "learning_rate": 5.577718201056392e-06, |
| "loss": 0.0666, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.306172839506173, |
| "grad_norm": 0.6710767149925232, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.0795, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "grad_norm": 0.6325903534889221, |
| "learning_rate": 4.360836746934055e-06, |
| "loss": 0.0794, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "eval_loss": 0.14366517961025238, |
| "eval_runtime": 21.0782, |
| "eval_samples_per_second": 2.135, |
| "eval_steps_per_second": 2.135, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.385185185185185, |
| "grad_norm": 0.4515002965927124, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.0657, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.424691358024692, |
| "grad_norm": 0.6361060738563538, |
| "learning_rate": 3.2875529852700147e-06, |
| "loss": 0.0783, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.4641975308641975, |
| "grad_norm": 0.5367184281349182, |
| "learning_rate": 2.8058334845816213e-06, |
| "loss": 0.0603, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.503703703703704, |
| "grad_norm": 0.5024017691612244, |
| "learning_rate": 2.361243863855184e-06, |
| "loss": 0.0623, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.54320987654321, |
| "grad_norm": 0.6290796399116516, |
| "learning_rate": 1.9541339027450256e-06, |
| "loss": 0.061, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.582716049382716, |
| "grad_norm": 0.4280959367752075, |
| "learning_rate": 1.584823893886933e-06, |
| "loss": 0.0591, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.5220338702201843, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 0.0568, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.661728395061728, |
| "grad_norm": 0.7212453484535217, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.08, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.701234567901235, |
| "grad_norm": 0.523912787437439, |
| "learning_rate": 7.064490740882057e-07, |
| "loss": 0.0742, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "grad_norm": 0.5243128538131714, |
| "learning_rate": 4.909437331777179e-07, |
| "loss": 0.0595, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "eval_loss": 0.14257951080799103, |
| "eval_runtime": 21.0801, |
| "eval_samples_per_second": 2.135, |
| "eval_steps_per_second": 2.135, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.780246913580247, |
| "grad_norm": 0.5481652617454529, |
| "learning_rate": 3.143895053378698e-07, |
| "loss": 0.056, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.8197530864197535, |
| "grad_norm": 0.749200701713562, |
| "learning_rate": 1.7692529411904578e-07, |
| "loss": 0.0942, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.859259259259259, |
| "grad_norm": 0.7117516994476318, |
| "learning_rate": 7.865924910916977e-08, |
| "loss": 0.0815, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.898765432098766, |
| "grad_norm": 0.6400362253189087, |
| "learning_rate": 1.9668680847356735e-08, |
| "loss": 0.0782, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "grad_norm": 0.654387354850769, |
| "learning_rate": 0.0, |
| "loss": 0.0889, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "step": 125, |
| "total_flos": 1.2645167320439194e+17, |
| "train_loss": 0.2063523907959461, |
| "train_runtime": 3515.9057, |
| "train_samples_per_second": 0.576, |
| "train_steps_per_second": 0.036 |
| } |
| ], |
| "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": 1.2645167320439194e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
