|
{ |
|
"best_metric": 0.05646544694900513, |
|
"best_model_checkpoint": "saves/psy-course-doc/Qwen2.5-7B-Instruct/train/fold3/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": 0.17131534218788147, |
|
"learning_rate": 7.692307692307694e-06, |
|
"loss": 0.2688, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.07901234567901234, |
|
"grad_norm": 0.20588842034339905, |
|
"learning_rate": 1.5384615384615387e-05, |
|
"loss": 0.2168, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.11851851851851852, |
|
"grad_norm": 0.2186741828918457, |
|
"learning_rate": 2.307692307692308e-05, |
|
"loss": 0.222, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.1580246913580247, |
|
"grad_norm": 0.19203895330429077, |
|
"learning_rate": 3.0769230769230774e-05, |
|
"loss": 0.251, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.19753086419753085, |
|
"grad_norm": 0.16441994905471802, |
|
"learning_rate": 3.846153846153846e-05, |
|
"loss": 0.369, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.23703703703703705, |
|
"grad_norm": 0.1986899971961975, |
|
"learning_rate": 4.615384615384616e-05, |
|
"loss": 0.2294, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.2765432098765432, |
|
"grad_norm": 0.17869219183921814, |
|
"learning_rate": 5.384615384615385e-05, |
|
"loss": 0.2963, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.3160493827160494, |
|
"grad_norm": 0.17493276298046112, |
|
"learning_rate": 6.153846153846155e-05, |
|
"loss": 0.2559, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.35555555555555557, |
|
"grad_norm": 0.19952566921710968, |
|
"learning_rate": 6.923076923076924e-05, |
|
"loss": 0.2287, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.3950617283950617, |
|
"grad_norm": 0.15901486575603485, |
|
"learning_rate": 7.692307692307693e-05, |
|
"loss": 0.1738, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.3950617283950617, |
|
"eval_loss": 0.17395542562007904, |
|
"eval_runtime": 21.8373, |
|
"eval_samples_per_second": 2.061, |
|
"eval_steps_per_second": 2.061, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.4345679012345679, |
|
"grad_norm": 0.1476554125547409, |
|
"learning_rate": 8.461538461538461e-05, |
|
"loss": 0.1822, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.4740740740740741, |
|
"grad_norm": 0.14130815863609314, |
|
"learning_rate": 9.230769230769232e-05, |
|
"loss": 0.1687, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.5135802469135803, |
|
"grad_norm": 0.09482128173112869, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1301, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.5530864197530864, |
|
"grad_norm": 0.09204382449388504, |
|
"learning_rate": 9.998033131915266e-05, |
|
"loss": 0.2117, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.5925925925925926, |
|
"grad_norm": 0.09261525422334671, |
|
"learning_rate": 9.992134075089084e-05, |
|
"loss": 0.1463, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.6320987654320988, |
|
"grad_norm": 0.1050386056303978, |
|
"learning_rate": 9.982307470588098e-05, |
|
"loss": 0.1436, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.671604938271605, |
|
"grad_norm": 0.10071782767772675, |
|
"learning_rate": 9.968561049466214e-05, |
|
"loss": 0.1664, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.7111111111111111, |
|
"grad_norm": 0.10573982447385788, |
|
"learning_rate": 9.950905626682228e-05, |
|
"loss": 0.1846, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.7506172839506173, |
|
"grad_norm": 0.08506191521883011, |
|
"learning_rate": 9.92935509259118e-05, |
|
"loss": 0.1549, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.7901234567901234, |
|
"grad_norm": 0.09038273990154266, |
|
"learning_rate": 9.903926402016153e-05, |
|
"loss": 0.1035, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.7901234567901234, |
|
"eval_loss": 0.10419965535402298, |
|
"eval_runtime": 21.8485, |
|
"eval_samples_per_second": 2.06, |
|
"eval_steps_per_second": 2.06, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.8296296296296296, |
|
"grad_norm": 0.11464792490005493, |
|
"learning_rate": 9.874639560909117e-05, |
|
"loss": 0.1232, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.8691358024691358, |
|
"grad_norm": 0.11794886738061905, |
|
"learning_rate": 9.841517610611309e-05, |
|
"loss": 0.1191, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.908641975308642, |
|
"grad_norm": 0.10086370259523392, |
|
"learning_rate": 9.804586609725499e-05, |
|
"loss": 0.1859, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.9481481481481482, |
|
"grad_norm": 0.09910855442285538, |
|
"learning_rate": 9.763875613614482e-05, |
|
"loss": 0.1734, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.9876543209876543, |
|
"grad_norm": 0.09258950501680374, |
|
"learning_rate": 9.719416651541839e-05, |
|
"loss": 0.1085, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 1.0271604938271606, |
|
"grad_norm": 0.14311587810516357, |
|
"learning_rate": 9.671244701472999e-05, |
|
"loss": 0.1716, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 1.0666666666666667, |
|
"grad_norm": 0.07099040597677231, |
|
"learning_rate": 9.619397662556435e-05, |
|
"loss": 0.1346, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 1.106172839506173, |
|
"grad_norm": 0.07571985572576523, |
|
"learning_rate": 9.563916325306594e-05, |
|
"loss": 0.1693, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 1.145679012345679, |
|
"grad_norm": 0.07121696323156357, |
|
"learning_rate": 9.504844339512095e-05, |
|
"loss": 0.1156, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 1.1851851851851851, |
|
"grad_norm": 0.07326597720384598, |
|
"learning_rate": 9.442228179894362e-05, |
|
"loss": 0.1098, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 1.1851851851851851, |
|
"eval_loss": 0.07620410621166229, |
|
"eval_runtime": 21.8415, |
|
"eval_samples_per_second": 2.06, |
|
"eval_steps_per_second": 2.06, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 1.2246913580246914, |
|
"grad_norm": 0.07799484580755234, |
|
"learning_rate": 9.376117109543769e-05, |
|
"loss": 0.1156, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 1.2641975308641975, |
|
"grad_norm": 0.06944699585437775, |
|
"learning_rate": 9.306563141162046e-05, |
|
"loss": 0.1133, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 1.3037037037037038, |
|
"grad_norm": 0.06568016856908798, |
|
"learning_rate": 9.233620996141421e-05, |
|
"loss": 0.0784, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 1.34320987654321, |
|
"grad_norm": 0.08781968057155609, |
|
"learning_rate": 9.157348061512727e-05, |
|
"loss": 0.1612, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 1.382716049382716, |
|
"grad_norm": 0.06498590856790543, |
|
"learning_rate": 9.077804344796302e-05, |
|
"loss": 0.0521, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 1.4222222222222223, |
|
"grad_norm": 0.09262922406196594, |
|
"learning_rate": 8.995052426791247e-05, |
|
"loss": 0.082, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 1.4617283950617284, |
|
"grad_norm": 0.08837880194187164, |
|
"learning_rate": 8.90915741234015e-05, |
|
"loss": 0.1643, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 1.5012345679012347, |
|
"grad_norm": 0.07971847057342529, |
|
"learning_rate": 8.820186879108038e-05, |
|
"loss": 0.0627, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 1.5407407407407407, |
|
"grad_norm": 0.08186373859643936, |
|
"learning_rate": 8.728210824415827e-05, |
|
"loss": 0.0965, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 1.5802469135802468, |
|
"grad_norm": 0.08488698303699493, |
|
"learning_rate": 8.633301610170135e-05, |
|
"loss": 0.129, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 1.5802469135802468, |
|
"eval_loss": 0.06689994782209396, |
|
"eval_runtime": 21.8352, |
|
"eval_samples_per_second": 2.061, |
|
"eval_steps_per_second": 2.061, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 1.6197530864197531, |
|
"grad_norm": 0.06791165471076965, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 0.0437, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 1.6592592592592592, |
|
"grad_norm": 0.07856765389442444, |
|
"learning_rate": 8.434984630174509e-05, |
|
"loss": 0.1499, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 1.6987654320987655, |
|
"grad_norm": 0.08699782192707062, |
|
"learning_rate": 8.33173288976002e-05, |
|
"loss": 0.1006, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 1.7382716049382716, |
|
"grad_norm": 0.07783804833889008, |
|
"learning_rate": 8.225859917710439e-05, |
|
"loss": 0.151, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 1.7777777777777777, |
|
"grad_norm": 0.0708998367190361, |
|
"learning_rate": 8.117449009293668e-05, |
|
"loss": 0.0571, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 1.817283950617284, |
|
"grad_norm": 0.05117553845047951, |
|
"learning_rate": 8.006585456492029e-05, |
|
"loss": 0.0491, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 1.8567901234567903, |
|
"grad_norm": 0.07001707702875137, |
|
"learning_rate": 7.89335648089903e-05, |
|
"loss": 0.1067, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 1.8962962962962964, |
|
"grad_norm": 0.07765704393386841, |
|
"learning_rate": 7.777851165098012e-05, |
|
"loss": 0.1132, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 1.9358024691358025, |
|
"grad_norm": 0.06105352193117142, |
|
"learning_rate": 7.660160382576683e-05, |
|
"loss": 0.0836, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 1.9753086419753085, |
|
"grad_norm": 0.06479307264089584, |
|
"learning_rate": 7.540376726232648e-05, |
|
"loss": 0.089, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 1.9753086419753085, |
|
"eval_loss": 0.06264698505401611, |
|
"eval_runtime": 21.8236, |
|
"eval_samples_per_second": 2.062, |
|
"eval_steps_per_second": 2.062, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 2.0148148148148146, |
|
"grad_norm": 0.15705189108848572, |
|
"learning_rate": 7.4185944355262e-05, |
|
"loss": 0.1434, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 2.054320987654321, |
|
"grad_norm": 0.06653366982936859, |
|
"learning_rate": 7.294909322337689e-05, |
|
"loss": 0.1148, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 2.093827160493827, |
|
"grad_norm": 0.06903208792209625, |
|
"learning_rate": 7.169418695587791e-05, |
|
"loss": 0.0738, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 2.1333333333333333, |
|
"grad_norm": 0.058074112981557846, |
|
"learning_rate": 7.042221284679982e-05, |
|
"loss": 0.0746, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 2.1728395061728394, |
|
"grad_norm": 0.059003956615924835, |
|
"learning_rate": 6.91341716182545e-05, |
|
"loss": 0.0512, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 2.212345679012346, |
|
"grad_norm": 0.07441215962171555, |
|
"learning_rate": 6.783107663311565e-05, |
|
"loss": 0.1786, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 2.251851851851852, |
|
"grad_norm": 0.07707154750823975, |
|
"learning_rate": 6.651395309775837e-05, |
|
"loss": 0.1418, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 2.291358024691358, |
|
"grad_norm": 0.06668653339147568, |
|
"learning_rate": 6.518383725548074e-05, |
|
"loss": 0.0716, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 2.330864197530864, |
|
"grad_norm": 0.06787598878145218, |
|
"learning_rate": 6.384177557124247e-05, |
|
"loss": 0.0962, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 2.3703703703703702, |
|
"grad_norm": 0.07978978753089905, |
|
"learning_rate": 6.248882390836135e-05, |
|
"loss": 0.045, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 2.3703703703703702, |
|
"eval_loss": 0.06034701690077782, |
|
"eval_runtime": 21.8151, |
|
"eval_samples_per_second": 2.063, |
|
"eval_steps_per_second": 2.063, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 2.4098765432098768, |
|
"grad_norm": 0.07540140300989151, |
|
"learning_rate": 6.112604669781572e-05, |
|
"loss": 0.0907, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 2.449382716049383, |
|
"grad_norm": 0.062165502458810806, |
|
"learning_rate": 5.9754516100806423e-05, |
|
"loss": 0.092, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 2.488888888888889, |
|
"grad_norm": 0.07297363877296448, |
|
"learning_rate": 5.837531116523682e-05, |
|
"loss": 0.0937, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 2.528395061728395, |
|
"grad_norm": 0.06504316627979279, |
|
"learning_rate": 5.698951697677498e-05, |
|
"loss": 0.0845, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 2.567901234567901, |
|
"grad_norm": 0.05565926805138588, |
|
"learning_rate": 5.559822380516539e-05, |
|
"loss": 0.0486, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 2.6074074074074076, |
|
"grad_norm": 0.08517668396234512, |
|
"learning_rate": 5.420252624646238e-05, |
|
"loss": 0.0809, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 2.6469135802469137, |
|
"grad_norm": 0.06398051977157593, |
|
"learning_rate": 5.2803522361859594e-05, |
|
"loss": 0.0758, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 2.68641975308642, |
|
"grad_norm": 0.0701739564538002, |
|
"learning_rate": 5.140231281379345e-05, |
|
"loss": 0.113, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 2.725925925925926, |
|
"grad_norm": 0.09116528928279877, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0837, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 2.765432098765432, |
|
"grad_norm": 0.0724126547574997, |
|
"learning_rate": 4.859768718620656e-05, |
|
"loss": 0.073, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 2.765432098765432, |
|
"eval_loss": 0.0586002916097641, |
|
"eval_runtime": 21.819, |
|
"eval_samples_per_second": 2.062, |
|
"eval_steps_per_second": 2.062, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 2.8049382716049385, |
|
"grad_norm": 0.0718497633934021, |
|
"learning_rate": 4.7196477638140404e-05, |
|
"loss": 0.0979, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 2.8444444444444446, |
|
"grad_norm": 0.06620865315198898, |
|
"learning_rate": 4.579747375353763e-05, |
|
"loss": 0.1085, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 2.8839506172839506, |
|
"grad_norm": 0.05052490904927254, |
|
"learning_rate": 4.4401776194834613e-05, |
|
"loss": 0.0298, |
|
"step": 73 |
|
}, |
|
{ |
|
"epoch": 2.9234567901234567, |
|
"grad_norm": 0.089655801653862, |
|
"learning_rate": 4.3010483023225045e-05, |
|
"loss": 0.1575, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 2.962962962962963, |
|
"grad_norm": 0.07064040750265121, |
|
"learning_rate": 4.162468883476319e-05, |
|
"loss": 0.0545, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 3.0024691358024693, |
|
"grad_norm": 0.1359511762857437, |
|
"learning_rate": 4.0245483899193595e-05, |
|
"loss": 0.1837, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 3.0419753086419754, |
|
"grad_norm": 0.07111749053001404, |
|
"learning_rate": 3.887395330218429e-05, |
|
"loss": 0.0886, |
|
"step": 77 |
|
}, |
|
{ |
|
"epoch": 3.0814814814814815, |
|
"grad_norm": 0.07351371645927429, |
|
"learning_rate": 3.7511176091638653e-05, |
|
"loss": 0.136, |
|
"step": 78 |
|
}, |
|
{ |
|
"epoch": 3.1209876543209876, |
|
"grad_norm": 0.08288402855396271, |
|
"learning_rate": 3.6158224428757535e-05, |
|
"loss": 0.1156, |
|
"step": 79 |
|
}, |
|
{ |
|
"epoch": 3.1604938271604937, |
|
"grad_norm": 0.091995969414711, |
|
"learning_rate": 3.4816162744519263e-05, |
|
"loss": 0.1419, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 3.1604938271604937, |
|
"eval_loss": 0.05760585516691208, |
|
"eval_runtime": 21.8022, |
|
"eval_samples_per_second": 2.064, |
|
"eval_steps_per_second": 2.064, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"grad_norm": 0.07099512219429016, |
|
"learning_rate": 3.3486046902241664e-05, |
|
"loss": 0.0927, |
|
"step": 81 |
|
}, |
|
{ |
|
"epoch": 3.2395061728395063, |
|
"grad_norm": 0.05904627963900566, |
|
"learning_rate": 3.216892336688435e-05, |
|
"loss": 0.0747, |
|
"step": 82 |
|
}, |
|
{ |
|
"epoch": 3.2790123456790123, |
|
"grad_norm": 0.0664386972784996, |
|
"learning_rate": 3.086582838174551e-05, |
|
"loss": 0.0474, |
|
"step": 83 |
|
}, |
|
{ |
|
"epoch": 3.3185185185185184, |
|
"grad_norm": 0.0734579861164093, |
|
"learning_rate": 2.9577787153200197e-05, |
|
"loss": 0.0891, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 3.3580246913580245, |
|
"grad_norm": 0.06800848245620728, |
|
"learning_rate": 2.8305813044122097e-05, |
|
"loss": 0.0476, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 3.397530864197531, |
|
"grad_norm": 0.07006184756755829, |
|
"learning_rate": 2.705090677662311e-05, |
|
"loss": 0.097, |
|
"step": 86 |
|
}, |
|
{ |
|
"epoch": 3.437037037037037, |
|
"grad_norm": 0.07209555804729462, |
|
"learning_rate": 2.581405564473801e-05, |
|
"loss": 0.063, |
|
"step": 87 |
|
}, |
|
{ |
|
"epoch": 3.476543209876543, |
|
"grad_norm": 0.07212737947702408, |
|
"learning_rate": 2.459623273767354e-05, |
|
"loss": 0.0561, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 3.5160493827160493, |
|
"grad_norm": 0.05391577258706093, |
|
"learning_rate": 2.3398396174233178e-05, |
|
"loss": 0.0426, |
|
"step": 89 |
|
}, |
|
{ |
|
"epoch": 3.5555555555555554, |
|
"grad_norm": 0.0875517874956131, |
|
"learning_rate": 2.2221488349019903e-05, |
|
"loss": 0.0826, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 3.5555555555555554, |
|
"eval_loss": 0.05722694471478462, |
|
"eval_runtime": 21.8077, |
|
"eval_samples_per_second": 2.063, |
|
"eval_steps_per_second": 2.063, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 3.595061728395062, |
|
"grad_norm": 0.06631125509738922, |
|
"learning_rate": 2.1066435191009715e-05, |
|
"loss": 0.0744, |
|
"step": 91 |
|
}, |
|
{ |
|
"epoch": 3.634567901234568, |
|
"grad_norm": 0.062178321182727814, |
|
"learning_rate": 1.9934145435079702e-05, |
|
"loss": 0.0521, |
|
"step": 92 |
|
}, |
|
{ |
|
"epoch": 3.674074074074074, |
|
"grad_norm": 0.0757577121257782, |
|
"learning_rate": 1.8825509907063327e-05, |
|
"loss": 0.077, |
|
"step": 93 |
|
}, |
|
{ |
|
"epoch": 3.71358024691358, |
|
"grad_norm": 0.07429811358451843, |
|
"learning_rate": 1.774140082289563e-05, |
|
"loss": 0.1341, |
|
"step": 94 |
|
}, |
|
{ |
|
"epoch": 3.753086419753086, |
|
"grad_norm": 0.07854592055082321, |
|
"learning_rate": 1.6682671102399805e-05, |
|
"loss": 0.1004, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 3.7925925925925927, |
|
"grad_norm": 0.0755835473537445, |
|
"learning_rate": 1.5650153698254916e-05, |
|
"loss": 0.0846, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 3.832098765432099, |
|
"grad_norm": 0.09232587367296219, |
|
"learning_rate": 1.4644660940672627e-05, |
|
"loss": 0.1203, |
|
"step": 97 |
|
}, |
|
{ |
|
"epoch": 3.871604938271605, |
|
"grad_norm": 0.07877123355865479, |
|
"learning_rate": 1.3666983898298657e-05, |
|
"loss": 0.0578, |
|
"step": 98 |
|
}, |
|
{ |
|
"epoch": 3.911111111111111, |
|
"grad_norm": 0.08251766860485077, |
|
"learning_rate": 1.2717891755841722e-05, |
|
"loss": 0.1273, |
|
"step": 99 |
|
}, |
|
{ |
|
"epoch": 3.950617283950617, |
|
"grad_norm": 0.06056011840701103, |
|
"learning_rate": 1.1798131208919627e-05, |
|
"loss": 0.0248, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 3.950617283950617, |
|
"eval_loss": 0.05662662163376808, |
|
"eval_runtime": 21.8287, |
|
"eval_samples_per_second": 2.062, |
|
"eval_steps_per_second": 2.062, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 3.9901234567901236, |
|
"grad_norm": 0.0750073716044426, |
|
"learning_rate": 1.090842587659851e-05, |
|
"loss": 0.0654, |
|
"step": 101 |
|
}, |
|
{ |
|
"epoch": 4.029629629629629, |
|
"grad_norm": 0.13658201694488525, |
|
"learning_rate": 1.004947573208756e-05, |
|
"loss": 0.1595, |
|
"step": 102 |
|
}, |
|
{ |
|
"epoch": 4.069135802469136, |
|
"grad_norm": 0.06402350962162018, |
|
"learning_rate": 9.221956552036992e-06, |
|
"loss": 0.0637, |
|
"step": 103 |
|
}, |
|
{ |
|
"epoch": 4.108641975308642, |
|
"grad_norm": 0.06825728714466095, |
|
"learning_rate": 8.426519384872733e-06, |
|
"loss": 0.066, |
|
"step": 104 |
|
}, |
|
{ |
|
"epoch": 4.148148148148148, |
|
"grad_norm": 0.07006324827671051, |
|
"learning_rate": 7.663790038585793e-06, |
|
"loss": 0.1415, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 4.187654320987654, |
|
"grad_norm": 0.0746365636587143, |
|
"learning_rate": 6.934368588379553e-06, |
|
"loss": 0.092, |
|
"step": 106 |
|
}, |
|
{ |
|
"epoch": 4.22716049382716, |
|
"grad_norm": 0.07476723939180374, |
|
"learning_rate": 6.238828904562316e-06, |
|
"loss": 0.1299, |
|
"step": 107 |
|
}, |
|
{ |
|
"epoch": 4.266666666666667, |
|
"grad_norm": 0.06787648797035217, |
|
"learning_rate": 5.577718201056392e-06, |
|
"loss": 0.0674, |
|
"step": 108 |
|
}, |
|
{ |
|
"epoch": 4.306172839506173, |
|
"grad_norm": 0.07424931973218918, |
|
"learning_rate": 4.951556604879048e-06, |
|
"loss": 0.0575, |
|
"step": 109 |
|
}, |
|
{ |
|
"epoch": 4.345679012345679, |
|
"grad_norm": 0.07090545445680618, |
|
"learning_rate": 4.360836746934055e-06, |
|
"loss": 0.0626, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 4.345679012345679, |
|
"eval_loss": 0.056520648300647736, |
|
"eval_runtime": 21.8263, |
|
"eval_samples_per_second": 2.062, |
|
"eval_steps_per_second": 2.062, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 4.385185185185185, |
|
"grad_norm": 0.05021325871348381, |
|
"learning_rate": 3.8060233744356633e-06, |
|
"loss": 0.052, |
|
"step": 111 |
|
}, |
|
{ |
|
"epoch": 4.424691358024692, |
|
"grad_norm": 0.060442108660936356, |
|
"learning_rate": 3.2875529852700147e-06, |
|
"loss": 0.0603, |
|
"step": 112 |
|
}, |
|
{ |
|
"epoch": 4.4641975308641975, |
|
"grad_norm": 0.0718117505311966, |
|
"learning_rate": 2.8058334845816213e-06, |
|
"loss": 0.0655, |
|
"step": 113 |
|
}, |
|
{ |
|
"epoch": 4.503703703703704, |
|
"grad_norm": 0.0800413265824318, |
|
"learning_rate": 2.361243863855184e-06, |
|
"loss": 0.123, |
|
"step": 114 |
|
}, |
|
{ |
|
"epoch": 4.54320987654321, |
|
"grad_norm": 0.05817375332117081, |
|
"learning_rate": 1.9541339027450256e-06, |
|
"loss": 0.0424, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 4.582716049382716, |
|
"grad_norm": 0.06891554594039917, |
|
"learning_rate": 1.584823893886933e-06, |
|
"loss": 0.1112, |
|
"step": 116 |
|
}, |
|
{ |
|
"epoch": 4.622222222222222, |
|
"grad_norm": 0.07742012292146683, |
|
"learning_rate": 1.2536043909088191e-06, |
|
"loss": 0.0813, |
|
"step": 117 |
|
}, |
|
{ |
|
"epoch": 4.661728395061728, |
|
"grad_norm": 0.06016990542411804, |
|
"learning_rate": 9.607359798384785e-07, |
|
"loss": 0.0381, |
|
"step": 118 |
|
}, |
|
{ |
|
"epoch": 4.701234567901235, |
|
"grad_norm": 0.068426214158535, |
|
"learning_rate": 7.064490740882057e-07, |
|
"loss": 0.0937, |
|
"step": 119 |
|
}, |
|
{ |
|
"epoch": 4.7407407407407405, |
|
"grad_norm": 0.06560222059488297, |
|
"learning_rate": 4.909437331777179e-07, |
|
"loss": 0.0881, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 4.7407407407407405, |
|
"eval_loss": 0.05646544694900513, |
|
"eval_runtime": 21.7965, |
|
"eval_samples_per_second": 2.065, |
|
"eval_steps_per_second": 2.065, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 4.780246913580247, |
|
"grad_norm": 0.06821303814649582, |
|
"learning_rate": 3.143895053378698e-07, |
|
"loss": 0.0448, |
|
"step": 121 |
|
}, |
|
{ |
|
"epoch": 4.8197530864197535, |
|
"grad_norm": 0.06056409701704979, |
|
"learning_rate": 1.7692529411904578e-07, |
|
"loss": 0.0586, |
|
"step": 122 |
|
}, |
|
{ |
|
"epoch": 4.859259259259259, |
|
"grad_norm": 0.06379059702157974, |
|
"learning_rate": 7.865924910916977e-08, |
|
"loss": 0.0788, |
|
"step": 123 |
|
}, |
|
{ |
|
"epoch": 4.898765432098766, |
|
"grad_norm": 0.062441617250442505, |
|
"learning_rate": 1.9668680847356735e-08, |
|
"loss": 0.0915, |
|
"step": 124 |
|
}, |
|
{ |
|
"epoch": 4.938271604938271, |
|
"grad_norm": 0.0661565363407135, |
|
"learning_rate": 0.0, |
|
"loss": 0.1099, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 4.938271604938271, |
|
"step": 125, |
|
"total_flos": 1.4549445335280845e+17, |
|
"train_loss": 0.1123583979010582, |
|
"train_runtime": 3538.6493, |
|
"train_samples_per_second": 0.572, |
|
"train_steps_per_second": 0.035 |
|
} |
|
], |
|
"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": 1.4549445335280845e+17, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|