| { | |
| "best_metric": 0.10044700652360916, | |
| "best_model_checkpoint": "saves/psy-course-doc/Ministral-8B-Instruct-2410/train/fold7/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": 0.25569042563438416, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.2217, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 0.29871875047683716, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.2342, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 0.27560147643089294, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.1733, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 0.24823977053165436, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.2002, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.2874525487422943, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.1917, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 0.27328264713287354, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.2079, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 0.21940472722053528, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.2551, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 0.2444743812084198, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.1674, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.2123764157295227, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.1217, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.20162788033485413, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.1429, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.16870030760765076, | |
| "eval_runtime": 23.6385, | |
| "eval_samples_per_second": 1.904, | |
| "eval_steps_per_second": 1.904, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 0.24168583750724792, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.0997, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 0.22949667274951935, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.1465, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.18780721724033356, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0732, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 0.2205672562122345, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.1697, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.20149117708206177, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.0969, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 0.20797108113765717, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.0587, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.15082800388336182, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.0843, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.1508992612361908, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.1063, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.13655465841293335, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.1126, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.11236004531383514, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.0619, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.1207745224237442, | |
| "eval_runtime": 23.6446, | |
| "eval_samples_per_second": 1.903, | |
| "eval_steps_per_second": 1.903, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.1275305300951004, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.0654, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.14964647591114044, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.0636, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.1144343763589859, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.0923, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.1199299618601799, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.0873, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.11135376244783401, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.098, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 0.10600176453590393, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.0818, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.12110491842031479, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0849, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.11677621304988861, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.0638, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.09996111690998077, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.0634, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.13052275776863098, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.0922, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.11041471362113953, | |
| "eval_runtime": 23.6555, | |
| "eval_samples_per_second": 1.902, | |
| "eval_steps_per_second": 1.902, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.09965930134057999, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.0515, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.12421140819787979, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.0951, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.11393923312425613, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.0414, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.0751267522573471, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0313, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.09794782847166061, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.0994, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.09191828221082687, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.0623, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.10882566124200821, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.0811, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.09541211277246475, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.0473, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.1109672337770462, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.0665, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.08999992161989212, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.0615, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.10694622248411179, | |
| "eval_runtime": 23.6445, | |
| "eval_samples_per_second": 1.903, | |
| "eval_steps_per_second": 1.903, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.09397738426923752, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0577, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.08805026113986969, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.0542, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.09687551110982895, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.0748, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.10689491033554077, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.0848, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.1095302626490593, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.0476, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.10803399980068207, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.0488, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.10936824977397919, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.1211, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.09340368956327438, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0546, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.11535226553678513, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.0848, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.10957583785057068, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.0949, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.1034923642873764, | |
| "eval_runtime": 23.6383, | |
| "eval_samples_per_second": 1.904, | |
| "eval_steps_per_second": 1.904, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 0.08498050272464752, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.0447, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.12527123093605042, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.0722, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.08322834968566895, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.0533, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.08857711404561996, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.0741, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.10554396361112595, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1147, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.09620149433612823, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.0789, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.10490215569734573, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.108, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.10010910034179688, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.0856, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.08154655247926712, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.0466, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.0757882371544838, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.0271, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.10128511488437653, | |
| "eval_runtime": 23.6183, | |
| "eval_samples_per_second": 1.905, | |
| "eval_steps_per_second": 1.905, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.10863827168941498, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0732, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.09465999156236649, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0483, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.10484308749437332, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.0415, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.09289147704839706, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.0518, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.12722858786582947, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.1005, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.10347144305706024, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.0503, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.09702008962631226, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.0547, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.08844641596078873, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.032, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.09974277019500732, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0179, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.10870665311813354, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.0407, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.10102660208940506, | |
| "eval_runtime": 23.6248, | |
| "eval_samples_per_second": 1.905, | |
| "eval_steps_per_second": 1.905, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.09725839644670486, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.0443, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.08974414318799973, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.0356, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.11754197627305984, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.0489, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.11163731664419174, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.0324, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.09928654879331589, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.0484, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 0.09480438381433487, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0641, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.10655804723501205, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0766, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.089079350233078, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.0535, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.10400664061307907, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.0392, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.12190098315477371, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.0854, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.10044700652360916, | |
| "eval_runtime": 23.6473, | |
| "eval_samples_per_second": 1.903, | |
| "eval_steps_per_second": 1.903, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.10139673948287964, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.0541, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.10099156200885773, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0682, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.10576161742210388, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0702, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.12816108763217926, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0715, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.09949860721826553, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.0381, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.11975599825382233, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0401, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.12045536935329437, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.0461, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.10882311314344406, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.0496, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.12156950682401657, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0544, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.12036237865686417, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.06, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.10165079683065414, | |
| "eval_runtime": 23.6194, | |
| "eval_samples_per_second": 1.905, | |
| "eval_steps_per_second": 1.905, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.1085641011595726, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.0394, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.12157600373029709, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.0494, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.14830715954303741, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0304, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.09224114567041397, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.0284, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.0957605317234993, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.0321, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.08004555851221085, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.0096, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.09555333852767944, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0303, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.12622949481010437, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.0719, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.13211506605148315, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.0581, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.12117306888103485, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.0408, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.10059414803981781, | |
| "eval_runtime": 23.6383, | |
| "eval_samples_per_second": 1.904, | |
| "eval_steps_per_second": 1.904, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.12755411863327026, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0672, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 0.09381228685379028, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.0349, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.1076236441731453, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.0536, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.12168881297111511, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0684, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.11629091948270798, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.0566, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.1083616316318512, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.0328, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.1155935674905777, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.0574, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.10672532021999359, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0322, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.13835300505161285, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0733, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.10545878112316132, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.0425, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.10094353556632996, | |
| "eval_runtime": 23.6371, | |
| "eval_samples_per_second": 1.904, | |
| "eval_steps_per_second": 1.904, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.08330988883972168, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0235, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.09586207568645477, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0325, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.10791750997304916, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0281, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.11704002320766449, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.0505, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.10637445747852325, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.0369, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.12142503261566162, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0629, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.12353110313415527, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0622, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.092849962413311, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0276, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.11315535753965378, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0413, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.12101279199123383, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0669, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.10109386593103409, | |
| "eval_runtime": 23.6277, | |
| "eval_samples_per_second": 1.905, | |
| "eval_steps_per_second": 1.905, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.1092996746301651, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0423, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.09168654680252075, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.0315, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.10469096899032593, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.0436, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.11545046418905258, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.039, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.11896267533302307, | |
| "learning_rate": 0.0, | |
| "loss": 0.0517, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.540045366145188e+17, | |
| "train_loss": 0.07140555449575185, | |
| "train_runtime": 3946.1475, | |
| "train_samples_per_second": 0.513, | |
| "train_steps_per_second": 0.032 | |
| } | |
| ], | |
| "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": 1.540045366145188e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |