| { |
| "best_metric": 0.05018164962530136, |
| "best_model_checkpoint": "saves/psy-course-doc-info/Ministral-8B-Instruct-2410/train/fold8/checkpoint-110", |
| "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": 0.6986701488494873, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.3512, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 0.7088757753372192, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.3588, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 0.8064380884170532, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.3718, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 0.7222112417221069, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.3595, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 0.6226270794868469, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.3219, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 0.6451139450073242, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.3117, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 0.4552927315235138, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.2792, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 0.4108279347419739, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.2616, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 0.49120235443115234, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.2405, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 0.634235680103302, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.2346, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 0.22451305389404297, |
| "eval_runtime": 29.4003, |
| "eval_samples_per_second": 1.531, |
| "eval_steps_per_second": 1.531, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 0.6467899680137634, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.2449, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 0.5100688338279724, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.213, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 0.48423299193382263, |
| "learning_rate": 0.0001, |
| "loss": 0.1846, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 0.4744335114955902, |
| "learning_rate": 9.998033131915266e-05, |
| "loss": 0.1631, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.4236028492450714, |
| "learning_rate": 9.992134075089084e-05, |
| "loss": 0.1391, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 0.46361225843429565, |
| "learning_rate": 9.982307470588098e-05, |
| "loss": 0.137, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 0.6843778491020203, |
| "learning_rate": 9.968561049466214e-05, |
| "loss": 0.1323, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.3910984396934509, |
| "learning_rate": 9.950905626682228e-05, |
| "loss": 0.1141, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 0.464354008436203, |
| "learning_rate": 9.92935509259118e-05, |
| "loss": 0.1178, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.45064210891723633, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.1064, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.10692152380943298, |
| "eval_runtime": 29.2333, |
| "eval_samples_per_second": 1.539, |
| "eval_steps_per_second": 1.539, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 0.5124718546867371, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 0.1217, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 0.4468311667442322, |
| "learning_rate": 9.841517610611309e-05, |
| "loss": 0.097, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 0.3930855095386505, |
| "learning_rate": 9.804586609725499e-05, |
| "loss": 0.0871, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 0.44672492146492004, |
| "learning_rate": 9.763875613614482e-05, |
| "loss": 0.1053, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.3032624125480652, |
| "learning_rate": 9.719416651541839e-05, |
| "loss": 0.0961, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0271604938271606, |
| "grad_norm": 0.3262697756290436, |
| "learning_rate": 9.671244701472999e-05, |
| "loss": 0.0775, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.30042222142219543, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.0706, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.106172839506173, |
| "grad_norm": 0.26015129685401917, |
| "learning_rate": 9.563916325306594e-05, |
| "loss": 0.0815, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.145679012345679, |
| "grad_norm": 0.38614243268966675, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.0786, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "grad_norm": 0.2820267081260681, |
| "learning_rate": 9.442228179894362e-05, |
| "loss": 0.0661, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "eval_loss": 0.0779971331357956, |
| "eval_runtime": 29.2289, |
| "eval_samples_per_second": 1.54, |
| "eval_steps_per_second": 1.54, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2246913580246914, |
| "grad_norm": 0.31274303793907166, |
| "learning_rate": 9.376117109543769e-05, |
| "loss": 0.0675, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2641975308641975, |
| "grad_norm": 0.31122153997421265, |
| "learning_rate": 9.306563141162046e-05, |
| "loss": 0.0717, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.3037037037037038, |
| "grad_norm": 0.4171571433544159, |
| "learning_rate": 9.233620996141421e-05, |
| "loss": 0.0705, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.34320987654321, |
| "grad_norm": 0.39130330085754395, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.0643, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.382716049382716, |
| "grad_norm": 0.26237934827804565, |
| "learning_rate": 9.077804344796302e-05, |
| "loss": 0.0685, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.3337700366973877, |
| "learning_rate": 8.995052426791247e-05, |
| "loss": 0.0599, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.4617283950617284, |
| "grad_norm": 0.34181517362594604, |
| "learning_rate": 8.90915741234015e-05, |
| "loss": 0.0605, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.5012345679012347, |
| "grad_norm": 0.4122283160686493, |
| "learning_rate": 8.820186879108038e-05, |
| "loss": 0.0659, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.5407407407407407, |
| "grad_norm": 0.392880380153656, |
| "learning_rate": 8.728210824415827e-05, |
| "loss": 0.0681, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "grad_norm": 0.3869952857494354, |
| "learning_rate": 8.633301610170135e-05, |
| "loss": 0.0574, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "eval_loss": 0.06701873987913132, |
| "eval_runtime": 29.226, |
| "eval_samples_per_second": 1.54, |
| "eval_steps_per_second": 1.54, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6197530864197531, |
| "grad_norm": 0.3228525221347809, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.0736, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6592592592592592, |
| "grad_norm": 0.380230188369751, |
| "learning_rate": 8.434984630174509e-05, |
| "loss": 0.0485, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.6987654320987655, |
| "grad_norm": 0.23963190615177155, |
| "learning_rate": 8.33173288976002e-05, |
| "loss": 0.0603, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.7382716049382716, |
| "grad_norm": 0.2060232162475586, |
| "learning_rate": 8.225859917710439e-05, |
| "loss": 0.0528, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.32117360830307007, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.0547, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.817283950617284, |
| "grad_norm": 0.2599658668041229, |
| "learning_rate": 8.006585456492029e-05, |
| "loss": 0.0527, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.8567901234567903, |
| "grad_norm": 0.2622724771499634, |
| "learning_rate": 7.89335648089903e-05, |
| "loss": 0.0671, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.8962962962962964, |
| "grad_norm": 0.23480120301246643, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.0539, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.9358024691358025, |
| "grad_norm": 0.2417857050895691, |
| "learning_rate": 7.660160382576683e-05, |
| "loss": 0.0603, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "grad_norm": 0.2173357754945755, |
| "learning_rate": 7.540376726232648e-05, |
| "loss": 0.0454, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "eval_loss": 0.05982673540711403, |
| "eval_runtime": 29.235, |
| "eval_samples_per_second": 1.539, |
| "eval_steps_per_second": 1.539, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0148148148148146, |
| "grad_norm": 0.22790434956550598, |
| "learning_rate": 7.4185944355262e-05, |
| "loss": 0.0492, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.054320987654321, |
| "grad_norm": 0.24523094296455383, |
| "learning_rate": 7.294909322337689e-05, |
| "loss": 0.0436, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.093827160493827, |
| "grad_norm": 0.172611802816391, |
| "learning_rate": 7.169418695587791e-05, |
| "loss": 0.0382, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.19519709050655365, |
| "learning_rate": 7.042221284679982e-05, |
| "loss": 0.0482, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.1728395061728394, |
| "grad_norm": 0.29516759514808655, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.0428, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.212345679012346, |
| "grad_norm": 0.3404478132724762, |
| "learning_rate": 6.783107663311565e-05, |
| "loss": 0.0378, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.251851851851852, |
| "grad_norm": 0.20548518002033234, |
| "learning_rate": 6.651395309775837e-05, |
| "loss": 0.0421, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.291358024691358, |
| "grad_norm": 0.27528247237205505, |
| "learning_rate": 6.518383725548074e-05, |
| "loss": 0.0414, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.330864197530864, |
| "grad_norm": 0.23328714072704315, |
| "learning_rate": 6.384177557124247e-05, |
| "loss": 0.0482, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "grad_norm": 0.20340496301651, |
| "learning_rate": 6.248882390836135e-05, |
| "loss": 0.0416, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "eval_loss": 0.05630980432033539, |
| "eval_runtime": 29.2424, |
| "eval_samples_per_second": 1.539, |
| "eval_steps_per_second": 1.539, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.4098765432098768, |
| "grad_norm": 0.23710526525974274, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.0396, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.449382716049383, |
| "grad_norm": 0.21828940510749817, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.04, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 0.24057340621948242, |
| "learning_rate": 5.837531116523682e-05, |
| "loss": 0.0486, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.528395061728395, |
| "grad_norm": 0.24865029752254486, |
| "learning_rate": 5.698951697677498e-05, |
| "loss": 0.0442, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.567901234567901, |
| "grad_norm": 0.2211083471775055, |
| "learning_rate": 5.559822380516539e-05, |
| "loss": 0.0483, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.6074074074074076, |
| "grad_norm": 0.21438068151474, |
| "learning_rate": 5.420252624646238e-05, |
| "loss": 0.0517, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.6469135802469137, |
| "grad_norm": 0.2499130219221115, |
| "learning_rate": 5.2803522361859594e-05, |
| "loss": 0.0482, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.68641975308642, |
| "grad_norm": 0.1926133632659912, |
| "learning_rate": 5.140231281379345e-05, |
| "loss": 0.0348, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.725925925925926, |
| "grad_norm": 0.18554463982582092, |
| "learning_rate": 5e-05, |
| "loss": 0.0384, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "grad_norm": 0.22229990363121033, |
| "learning_rate": 4.859768718620656e-05, |
| "loss": 0.0462, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "eval_loss": 0.05303001031279564, |
| "eval_runtime": 29.236, |
| "eval_samples_per_second": 1.539, |
| "eval_steps_per_second": 1.539, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8049382716049385, |
| "grad_norm": 0.302468866109848, |
| "learning_rate": 4.7196477638140404e-05, |
| "loss": 0.0434, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 0.2213534712791443, |
| "learning_rate": 4.579747375353763e-05, |
| "loss": 0.0394, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.8839506172839506, |
| "grad_norm": 0.21534393727779388, |
| "learning_rate": 4.4401776194834613e-05, |
| "loss": 0.0414, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.9234567901234567, |
| "grad_norm": 0.26027560234069824, |
| "learning_rate": 4.3010483023225045e-05, |
| "loss": 0.0428, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.962962962962963, |
| "grad_norm": 0.2458033412694931, |
| "learning_rate": 4.162468883476319e-05, |
| "loss": 0.0383, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0024691358024693, |
| "grad_norm": 0.17401082813739777, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.0394, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.0419753086419754, |
| "grad_norm": 0.15630896389484406, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.0317, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.0814814814814815, |
| "grad_norm": 0.16098880767822266, |
| "learning_rate": 3.7511176091638653e-05, |
| "loss": 0.0267, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.1209876543209876, |
| "grad_norm": 0.21407581865787506, |
| "learning_rate": 3.6158224428757535e-05, |
| "loss": 0.0345, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "grad_norm": 0.18872970342636108, |
| "learning_rate": 3.4816162744519263e-05, |
| "loss": 0.0333, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "eval_loss": 0.05208759754896164, |
| "eval_runtime": 29.23, |
| "eval_samples_per_second": 1.54, |
| "eval_steps_per_second": 1.54, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.18860113620758057, |
| "learning_rate": 3.3486046902241664e-05, |
| "loss": 0.0355, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2395061728395063, |
| "grad_norm": 0.19854336977005005, |
| "learning_rate": 3.216892336688435e-05, |
| "loss": 0.0355, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.2790123456790123, |
| "grad_norm": 0.19552765786647797, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.0319, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.3185185185185184, |
| "grad_norm": 0.17172157764434814, |
| "learning_rate": 2.9577787153200197e-05, |
| "loss": 0.0312, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.3580246913580245, |
| "grad_norm": 0.16564936935901642, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.032, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.397530864197531, |
| "grad_norm": 0.19835302233695984, |
| "learning_rate": 2.705090677662311e-05, |
| "loss": 0.0392, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.437037037037037, |
| "grad_norm": 0.24695785343647003, |
| "learning_rate": 2.581405564473801e-05, |
| "loss": 0.0372, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.476543209876543, |
| "grad_norm": 0.1902298927307129, |
| "learning_rate": 2.459623273767354e-05, |
| "loss": 0.0335, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.5160493827160493, |
| "grad_norm": 0.23312592506408691, |
| "learning_rate": 2.3398396174233178e-05, |
| "loss": 0.0359, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.2210913747549057, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.0389, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_loss": 0.05143319070339203, |
| "eval_runtime": 29.2368, |
| "eval_samples_per_second": 1.539, |
| "eval_steps_per_second": 1.539, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.595061728395062, |
| "grad_norm": 0.21577894687652588, |
| "learning_rate": 2.1066435191009715e-05, |
| "loss": 0.0362, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.634567901234568, |
| "grad_norm": 0.19230662286281586, |
| "learning_rate": 1.9934145435079702e-05, |
| "loss": 0.0318, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.674074074074074, |
| "grad_norm": 0.20312044024467468, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.0302, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.71358024691358, |
| "grad_norm": 0.2292894870042801, |
| "learning_rate": 1.774140082289563e-05, |
| "loss": 0.0397, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.753086419753086, |
| "grad_norm": 0.3409978151321411, |
| "learning_rate": 1.6682671102399805e-05, |
| "loss": 0.0318, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.7925925925925927, |
| "grad_norm": 0.1991758942604065, |
| "learning_rate": 1.5650153698254916e-05, |
| "loss": 0.0255, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.832098765432099, |
| "grad_norm": 0.1859804391860962, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.0338, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.871604938271605, |
| "grad_norm": 0.3077707290649414, |
| "learning_rate": 1.3666983898298657e-05, |
| "loss": 0.0348, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 0.174801304936409, |
| "learning_rate": 1.2717891755841722e-05, |
| "loss": 0.028, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "grad_norm": 0.196518212556839, |
| "learning_rate": 1.1798131208919627e-05, |
| "loss": 0.0338, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "eval_loss": 0.0505523718893528, |
| "eval_runtime": 29.2378, |
| "eval_samples_per_second": 1.539, |
| "eval_steps_per_second": 1.539, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.9901234567901236, |
| "grad_norm": 0.20451030135154724, |
| "learning_rate": 1.090842587659851e-05, |
| "loss": 0.0377, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.029629629629629, |
| "grad_norm": 0.17839042842388153, |
| "learning_rate": 1.004947573208756e-05, |
| "loss": 0.0314, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.069135802469136, |
| "grad_norm": 0.21361440420150757, |
| "learning_rate": 9.221956552036992e-06, |
| "loss": 0.0339, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.108641975308642, |
| "grad_norm": 0.19031283259391785, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.0288, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.148148148148148, |
| "grad_norm": 0.1789381355047226, |
| "learning_rate": 7.663790038585793e-06, |
| "loss": 0.0323, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.187654320987654, |
| "grad_norm": 0.18017913401126862, |
| "learning_rate": 6.934368588379553e-06, |
| "loss": 0.035, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.22716049382716, |
| "grad_norm": 0.18314358592033386, |
| "learning_rate": 6.238828904562316e-06, |
| "loss": 0.0263, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.20920193195343018, |
| "learning_rate": 5.577718201056392e-06, |
| "loss": 0.0337, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.306172839506173, |
| "grad_norm": 0.17229609191417694, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.0303, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "grad_norm": 0.1544303596019745, |
| "learning_rate": 4.360836746934055e-06, |
| "loss": 0.0269, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "eval_loss": 0.05018164962530136, |
| "eval_runtime": 29.2504, |
| "eval_samples_per_second": 1.538, |
| "eval_steps_per_second": 1.538, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.385185185185185, |
| "grad_norm": 0.18308553099632263, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.03, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.424691358024692, |
| "grad_norm": 0.19447027146816254, |
| "learning_rate": 3.2875529852700147e-06, |
| "loss": 0.0294, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.4641975308641975, |
| "grad_norm": 0.15953049063682556, |
| "learning_rate": 2.8058334845816213e-06, |
| "loss": 0.0249, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.503703703703704, |
| "grad_norm": 0.18681061267852783, |
| "learning_rate": 2.361243863855184e-06, |
| "loss": 0.0278, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.54320987654321, |
| "grad_norm": 0.16752764582633972, |
| "learning_rate": 1.9541339027450256e-06, |
| "loss": 0.0262, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.582716049382716, |
| "grad_norm": 0.18282541632652283, |
| "learning_rate": 1.584823893886933e-06, |
| "loss": 0.0349, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.1863105297088623, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 0.0295, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.661728395061728, |
| "grad_norm": 0.17035965621471405, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.0305, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.701234567901235, |
| "grad_norm": 0.17452426254749298, |
| "learning_rate": 7.064490740882057e-07, |
| "loss": 0.0319, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "grad_norm": 0.17947931587696075, |
| "learning_rate": 4.909437331777179e-07, |
| "loss": 0.0289, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "eval_loss": 0.050184786319732666, |
| "eval_runtime": 29.264, |
| "eval_samples_per_second": 1.538, |
| "eval_steps_per_second": 1.538, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.780246913580247, |
| "grad_norm": 0.19741973280906677, |
| "learning_rate": 3.143895053378698e-07, |
| "loss": 0.0266, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.8197530864197535, |
| "grad_norm": 0.17615406215190887, |
| "learning_rate": 1.7692529411904578e-07, |
| "loss": 0.0299, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.859259259259259, |
| "grad_norm": 0.15755115449428558, |
| "learning_rate": 7.865924910916977e-08, |
| "loss": 0.0284, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.898765432098766, |
| "grad_norm": 0.1805194765329361, |
| "learning_rate": 1.9668680847356735e-08, |
| "loss": 0.0279, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "grad_norm": 0.1919160634279251, |
| "learning_rate": 0.0, |
| "loss": 0.0373, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "step": 125, |
| "total_flos": 1.743556468483031e+17, |
| "train_loss": 0.07543200919032098, |
| "train_runtime": 5142.0517, |
| "train_samples_per_second": 0.394, |
| "train_steps_per_second": 0.024 |
| } |
| ], |
| "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": 1.743556468483031e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
