| { |
| "best_global_step": 2000, |
| "best_metric": 0.8990073204040527, |
| "best_model_checkpoint": "lfm2.5-350m-balanced/checkpoint-2000", |
| "epoch": 2.0, |
| "eval_steps": 200, |
| "global_step": 2730, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.20119291305542, |
| "epoch": 0.018315018315018316, |
| "grad_norm": 10.4375, |
| "learning_rate": 5.853658536585366e-06, |
| "loss": 2.8065673828125, |
| "mean_token_accuracy": 0.57585333943367, |
| "num_tokens": 148430.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 1.278236083984375, |
| "epoch": 0.03663003663003663, |
| "grad_norm": 4.125, |
| "learning_rate": 1.1951219512195123e-05, |
| "loss": 1.506644287109375, |
| "mean_token_accuracy": 0.7009313237667084, |
| "num_tokens": 301448.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.0903868675231934, |
| "epoch": 0.054945054945054944, |
| "grad_norm": 2.609375, |
| "learning_rate": 1.804878048780488e-05, |
| "loss": 1.0758729553222657, |
| "mean_token_accuracy": 0.7404501688480377, |
| "num_tokens": 458432.0, |
| "step": 75 |
| }, |
| { |
| "entropy": 1.0081040942668915, |
| "epoch": 0.07326007326007326, |
| "grad_norm": 2.4375, |
| "learning_rate": 1.9997966159416884e-05, |
| "loss": 0.9917147827148437, |
| "mean_token_accuracy": 0.7522138917446136, |
| "num_tokens": 616048.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 0.9854830229282379, |
| "epoch": 0.09157509157509157, |
| "grad_norm": 2.46875, |
| "learning_rate": 1.99875879788391e-05, |
| "loss": 0.9723490905761719, |
| "mean_token_accuracy": 0.7565386164188385, |
| "num_tokens": 772466.0, |
| "step": 125 |
| }, |
| { |
| "entropy": 0.9745642852783203, |
| "epoch": 0.10989010989010989, |
| "grad_norm": 2.25, |
| "learning_rate": 1.996842417490666e-05, |
| "loss": 0.9625119018554688, |
| "mean_token_accuracy": 0.760125788450241, |
| "num_tokens": 930723.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 0.9700245261192322, |
| "epoch": 0.1282051282051282, |
| "grad_norm": 2.234375, |
| "learning_rate": 1.99404916051395e-05, |
| "loss": 0.9550397491455078, |
| "mean_token_accuracy": 0.7578657758235932, |
| "num_tokens": 1091160.0, |
| "step": 175 |
| }, |
| { |
| "entropy": 0.9669338822364807, |
| "epoch": 0.14652014652014653, |
| "grad_norm": 2.359375, |
| "learning_rate": 1.9903814840538914e-05, |
| "loss": 0.9478360748291016, |
| "mean_token_accuracy": 0.7623070132732391, |
| "num_tokens": 1245781.0, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.14652014652014653, |
| "eval_entropy": 0.9581337045464251, |
| "eval_loss": 0.9430390000343323, |
| "eval_mean_token_accuracy": 0.7639545847972234, |
| "eval_num_tokens": 1245781.0, |
| "eval_runtime": 8.0902, |
| "eval_samples_per_second": 284.171, |
| "eval_steps_per_second": 17.799, |
| "step": 200 |
| }, |
| { |
| "entropy": 0.9653169775009155, |
| "epoch": 0.16483516483516483, |
| "grad_norm": 2.640625, |
| "learning_rate": 1.9858426143973623e-05, |
| "loss": 0.9534239959716797, |
| "mean_token_accuracy": 0.7631052339076996, |
| "num_tokens": 1395650.0, |
| "step": 225 |
| }, |
| { |
| "entropy": 0.962496577501297, |
| "epoch": 0.18315018315018314, |
| "grad_norm": 2.234375, |
| "learning_rate": 1.9804365441799555e-05, |
| "loss": 0.9441399383544922, |
| "mean_token_accuracy": 0.7629920542240143, |
| "num_tokens": 1553420.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 0.9607322406768799, |
| "epoch": 0.20146520146520147, |
| "grad_norm": 2.46875, |
| "learning_rate": 1.9741680288738495e-05, |
| "loss": 0.939505615234375, |
| "mean_token_accuracy": 0.7633682239055634, |
| "num_tokens": 1708083.0, |
| "step": 275 |
| }, |
| { |
| "entropy": 0.9339856076240539, |
| "epoch": 0.21978021978021978, |
| "grad_norm": 2.203125, |
| "learning_rate": 1.967042582604635e-05, |
| "loss": 0.9153070831298828, |
| "mean_token_accuracy": 0.767605767250061, |
| "num_tokens": 1862545.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 0.9721270000934601, |
| "epoch": 0.23809523809523808, |
| "grad_norm": 2.265625, |
| "learning_rate": 1.9590664733007947e-05, |
| "loss": 0.959111328125, |
| "mean_token_accuracy": 0.7571033167839051, |
| "num_tokens": 2017595.0, |
| "step": 325 |
| }, |
| { |
| "entropy": 0.961563161611557, |
| "epoch": 0.2564102564102564, |
| "grad_norm": 2.3125, |
| "learning_rate": 1.9502467171800902e-05, |
| "loss": 0.9458185577392578, |
| "mean_token_accuracy": 0.7628096437454224, |
| "num_tokens": 2166320.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 0.9491504514217377, |
| "epoch": 0.27472527472527475, |
| "grad_norm": 2.34375, |
| "learning_rate": 1.940591072577719e-05, |
| "loss": 0.9269615173339844, |
| "mean_token_accuracy": 0.7635479891300201, |
| "num_tokens": 2325678.0, |
| "step": 375 |
| }, |
| { |
| "entropy": 0.9450718343257904, |
| "epoch": 0.29304029304029305, |
| "grad_norm": 2.28125, |
| "learning_rate": 1.930108033121663e-05, |
| "loss": 0.9313880920410156, |
| "mean_token_accuracy": 0.7636011290550232, |
| "num_tokens": 2481053.0, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.29304029304029305, |
| "eval_entropy": 0.9506676958666908, |
| "eval_loss": 0.9265689849853516, |
| "eval_mean_token_accuracy": 0.7673345183332761, |
| "eval_num_tokens": 2481053.0, |
| "eval_runtime": 8.0719, |
| "eval_samples_per_second": 284.816, |
| "eval_steps_per_second": 17.84, |
| "step": 400 |
| }, |
| { |
| "entropy": 0.9616206979751587, |
| "epoch": 0.31135531135531136, |
| "grad_norm": 2.28125, |
| "learning_rate": 1.9188068202612317e-05, |
| "loss": 0.9455902862548828, |
| "mean_token_accuracy": 0.7630793690681458, |
| "num_tokens": 2633845.0, |
| "step": 425 |
| }, |
| { |
| "entropy": 0.9392594003677368, |
| "epoch": 0.32967032967032966, |
| "grad_norm": 2.3125, |
| "learning_rate": 1.906697375155377e-05, |
| "loss": 0.9156442260742188, |
| "mean_token_accuracy": 0.7659864926338196, |
| "num_tokens": 2790745.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 0.9245667338371277, |
| "epoch": 0.34798534798534797, |
| "grad_norm": 2.203125, |
| "learning_rate": 1.8937903499279104e-05, |
| "loss": 0.903341064453125, |
| "mean_token_accuracy": 0.7713142216205597, |
| "num_tokens": 2943444.0, |
| "step": 475 |
| }, |
| { |
| "entropy": 0.912586669921875, |
| "epoch": 0.3663003663003663, |
| "grad_norm": 2.390625, |
| "learning_rate": 1.880097098297319e-05, |
| "loss": 0.8922891235351562, |
| "mean_token_accuracy": 0.771296215057373, |
| "num_tokens": 3098959.0, |
| "step": 500 |
| }, |
| { |
| "entropy": 0.9415633583068848, |
| "epoch": 0.38461538461538464, |
| "grad_norm": 2.15625, |
| "learning_rate": 1.8656296655894205e-05, |
| "loss": 0.9213317108154296, |
| "mean_token_accuracy": 0.7668669641017913, |
| "num_tokens": 3248382.0, |
| "step": 525 |
| }, |
| { |
| "entropy": 0.9617620420455932, |
| "epoch": 0.40293040293040294, |
| "grad_norm": 2.109375, |
| "learning_rate": 1.8504007781416385e-05, |
| "loss": 0.9434718322753907, |
| "mean_token_accuracy": 0.7617218482494355, |
| "num_tokens": 3409803.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 0.9193656361103058, |
| "epoch": 0.42124542124542125, |
| "grad_norm": 2.0625, |
| "learning_rate": 1.8344238321082316e-05, |
| "loss": 0.901815185546875, |
| "mean_token_accuracy": 0.7707051420211792, |
| "num_tokens": 3559416.0, |
| "step": 575 |
| }, |
| { |
| "entropy": 0.9518638348579407, |
| "epoch": 0.43956043956043955, |
| "grad_norm": 2.15625, |
| "learning_rate": 1.817712881676307e-05, |
| "loss": 0.9327508544921875, |
| "mean_token_accuracy": 0.7644142961502075, |
| "num_tokens": 3710110.0, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.43956043956043955, |
| "eval_entropy": 0.9517907314002514, |
| "eval_loss": 0.9172877073287964, |
| "eval_mean_token_accuracy": 0.7684686299827364, |
| "eval_num_tokens": 3710110.0, |
| "eval_runtime": 8.0887, |
| "eval_samples_per_second": 284.222, |
| "eval_steps_per_second": 17.803, |
| "step": 600 |
| }, |
| { |
| "entropy": 0.9130004584789276, |
| "epoch": 0.45787545787545786, |
| "grad_norm": 2.21875, |
| "learning_rate": 1.8002826267029977e-05, |
| "loss": 0.8941175079345703, |
| "mean_token_accuracy": 0.7705032932758331, |
| "num_tokens": 3862020.0, |
| "step": 625 |
| }, |
| { |
| "entropy": 0.9252553701400756, |
| "epoch": 0.47619047619047616, |
| "grad_norm": 2.15625, |
| "learning_rate": 1.7821483997846722e-05, |
| "loss": 0.9165068054199219, |
| "mean_token_accuracy": 0.7672811985015869, |
| "num_tokens": 4018231.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 0.9462221479415893, |
| "epoch": 0.4945054945054945, |
| "grad_norm": 2.125, |
| "learning_rate": 1.763326152769551e-05, |
| "loss": 0.9259709167480469, |
| "mean_token_accuracy": 0.7658140981197357, |
| "num_tokens": 4173058.0, |
| "step": 675 |
| }, |
| { |
| "entropy": 0.9479129528999328, |
| "epoch": 0.5128205128205128, |
| "grad_norm": 2.234375, |
| "learning_rate": 1.743832442725599e-05, |
| "loss": 0.9296504974365234, |
| "mean_token_accuracy": 0.7648407304286957, |
| "num_tokens": 4327983.0, |
| "step": 700 |
| }, |
| { |
| "entropy": 0.9435758924484253, |
| "epoch": 0.5311355311355311, |
| "grad_norm": 2.046875, |
| "learning_rate": 1.7236844173760286e-05, |
| "loss": 0.9163207244873047, |
| "mean_token_accuracy": 0.7653989827632904, |
| "num_tokens": 4482610.0, |
| "step": 725 |
| }, |
| { |
| "entropy": 0.9563624393939972, |
| "epoch": 0.5494505494505495, |
| "grad_norm": 2.296875, |
| "learning_rate": 1.7028998000152368e-05, |
| "loss": 0.942515869140625, |
| "mean_token_accuracy": 0.7614016819000244, |
| "num_tokens": 4638096.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 0.9195479357242584, |
| "epoch": 0.5677655677655677, |
| "grad_norm": 2.3125, |
| "learning_rate": 1.681496873918434e-05, |
| "loss": 0.8994998931884766, |
| "mean_token_accuracy": 0.7696708023548127, |
| "num_tokens": 4796965.0, |
| "step": 775 |
| }, |
| { |
| "entropy": 0.9382291078567505, |
| "epoch": 0.5860805860805861, |
| "grad_norm": 2.453125, |
| "learning_rate": 1.659494466258685e-05, |
| "loss": 0.9111621856689454, |
| "mean_token_accuracy": 0.7701178181171418, |
| "num_tokens": 4954572.0, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.5860805860805861, |
| "eval_entropy": 0.9060760368075635, |
| "eval_loss": 0.9103703498840332, |
| "eval_mean_token_accuracy": 0.7709767441782687, |
| "eval_num_tokens": 4954572.0, |
| "eval_runtime": 8.0596, |
| "eval_samples_per_second": 285.248, |
| "eval_steps_per_second": 17.867, |
| "step": 800 |
| }, |
| { |
| "entropy": 0.9392394709587097, |
| "epoch": 0.6043956043956044, |
| "grad_norm": 2.34375, |
| "learning_rate": 1.6369119315455067e-05, |
| "loss": 0.9231902313232422, |
| "mean_token_accuracy": 0.7648055994510651, |
| "num_tokens": 5107234.0, |
| "step": 825 |
| }, |
| { |
| "entropy": 0.9370434725284577, |
| "epoch": 0.6227106227106227, |
| "grad_norm": 2.0625, |
| "learning_rate": 1.613769134599595e-05, |
| "loss": 0.9138022613525391, |
| "mean_token_accuracy": 0.7679059386253357, |
| "num_tokens": 5256697.0, |
| "step": 850 |
| }, |
| { |
| "entropy": 0.9104315054416656, |
| "epoch": 0.6410256410256411, |
| "grad_norm": 2.15625, |
| "learning_rate": 1.590086433078652e-05, |
| "loss": 0.8872809600830078, |
| "mean_token_accuracy": 0.7746103525161743, |
| "num_tokens": 5406816.0, |
| "step": 875 |
| }, |
| { |
| "entropy": 0.9144675505161285, |
| "epoch": 0.6593406593406593, |
| "grad_norm": 2.125, |
| "learning_rate": 1.5658846595696868e-05, |
| "loss": 0.8894432830810547, |
| "mean_token_accuracy": 0.7708098363876342, |
| "num_tokens": 5558294.0, |
| "step": 900 |
| }, |
| { |
| "entropy": 0.9206836307048798, |
| "epoch": 0.6776556776556777, |
| "grad_norm": 2.125, |
| "learning_rate": 1.541185103263545e-05, |
| "loss": 0.8961500549316406, |
| "mean_token_accuracy": 0.771810313463211, |
| "num_tokens": 5712111.0, |
| "step": 925 |
| }, |
| { |
| "entropy": 0.9454787099361419, |
| "epoch": 0.6959706959706959, |
| "grad_norm": 2.015625, |
| "learning_rate": 1.5160094912277816e-05, |
| "loss": 0.9270650482177735, |
| "mean_token_accuracy": 0.7659087121486664, |
| "num_tokens": 5867502.0, |
| "step": 950 |
| }, |
| { |
| "entropy": 0.9311832976341248, |
| "epoch": 0.7142857142857143, |
| "grad_norm": 2.3125, |
| "learning_rate": 1.4903799692943575e-05, |
| "loss": 0.9082266235351563, |
| "mean_token_accuracy": 0.7696301078796387, |
| "num_tokens": 6017997.0, |
| "step": 975 |
| }, |
| { |
| "entropy": 0.9084031569957733, |
| "epoch": 0.7326007326007326, |
| "grad_norm": 2.265625, |
| "learning_rate": 1.4643190825789646e-05, |
| "loss": 0.8856626129150391, |
| "mean_token_accuracy": 0.7754030025005341, |
| "num_tokens": 6170646.0, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.7326007326007326, |
| "eval_entropy": 0.9303645570245054, |
| "eval_loss": 0.9040034413337708, |
| "eval_mean_token_accuracy": 0.7716102877424823, |
| "eval_num_tokens": 6170646.0, |
| "eval_runtime": 8.0677, |
| "eval_samples_per_second": 284.963, |
| "eval_steps_per_second": 17.849, |
| "step": 1000 |
| }, |
| { |
| "entropy": 0.9288157105445862, |
| "epoch": 0.7509157509157509, |
| "grad_norm": 2.125, |
| "learning_rate": 1.4378497556491212e-05, |
| "loss": 0.9045313262939453, |
| "mean_token_accuracy": 0.7689747631549835, |
| "num_tokens": 6325950.0, |
| "step": 1025 |
| }, |
| { |
| "entropy": 0.9248845767974854, |
| "epoch": 0.7692307692307693, |
| "grad_norm": 2.296875, |
| "learning_rate": 1.410995272358482e-05, |
| "loss": 0.9021368408203125, |
| "mean_token_accuracy": 0.7702593433856965, |
| "num_tokens": 6475837.0, |
| "step": 1050 |
| }, |
| { |
| "entropy": 0.9433277988433838, |
| "epoch": 0.7875457875457875, |
| "grad_norm": 2.03125, |
| "learning_rate": 1.383779255365097e-05, |
| "loss": 0.9240187072753906, |
| "mean_token_accuracy": 0.7659425389766693, |
| "num_tokens": 6625842.0, |
| "step": 1075 |
| }, |
| { |
| "entropy": 0.9574247586727143, |
| "epoch": 0.8058608058608059, |
| "grad_norm": 2.265625, |
| "learning_rate": 1.356225645351645e-05, |
| "loss": 0.9296712493896484, |
| "mean_token_accuracy": 0.7633269345760345, |
| "num_tokens": 6777307.0, |
| "step": 1100 |
| }, |
| { |
| "entropy": 0.9137916600704193, |
| "epoch": 0.8241758241758241, |
| "grad_norm": 2.234375, |
| "learning_rate": 1.3283586799659083e-05, |
| "loss": 0.8911846160888672, |
| "mean_token_accuracy": 0.7715334737300873, |
| "num_tokens": 6932314.0, |
| "step": 1125 |
| }, |
| { |
| "entropy": 0.9397987961769104, |
| "epoch": 0.8424908424908425, |
| "grad_norm": 2.171875, |
| "learning_rate": 1.3002028725000296e-05, |
| "loss": 0.9209308624267578, |
| "mean_token_accuracy": 0.7674053549766541, |
| "num_tokens": 7082476.0, |
| "step": 1150 |
| }, |
| { |
| "entropy": 0.9472148299217225, |
| "epoch": 0.8608058608058609, |
| "grad_norm": 2.15625, |
| "learning_rate": 1.2717829903272889e-05, |
| "loss": 0.9266857147216797, |
| "mean_token_accuracy": 0.7626336240768432, |
| "num_tokens": 7239624.0, |
| "step": 1175 |
| }, |
| { |
| "entropy": 0.9480014276504517, |
| "epoch": 0.8791208791208791, |
| "grad_norm": 2.3125, |
| "learning_rate": 1.243124033115382e-05, |
| "loss": 0.9297947692871094, |
| "mean_token_accuracy": 0.762817633152008, |
| "num_tokens": 7394047.0, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.8791208791208791, |
| "eval_entropy": 0.9203641795449786, |
| "eval_loss": 0.8990768790245056, |
| "eval_mean_token_accuracy": 0.7723050812880198, |
| "eval_num_tokens": 7394047.0, |
| "eval_runtime": 8.072, |
| "eval_samples_per_second": 284.813, |
| "eval_steps_per_second": 17.84, |
| "step": 1200 |
| }, |
| { |
| "entropy": 0.9616302692890167, |
| "epoch": 0.8974358974358975, |
| "grad_norm": 2.640625, |
| "learning_rate": 1.2142512108353583e-05, |
| "loss": 0.9401410675048828, |
| "mean_token_accuracy": 0.7661498367786408, |
| "num_tokens": 7548323.0, |
| "step": 1225 |
| }, |
| { |
| "entropy": 0.9228850102424622, |
| "epoch": 0.9157509157509157, |
| "grad_norm": 2.21875, |
| "learning_rate": 1.1851899215855653e-05, |
| "loss": 0.8985552215576171, |
| "mean_token_accuracy": 0.7717998087406158, |
| "num_tokens": 7700481.0, |
| "step": 1250 |
| }, |
| { |
| "entropy": 0.8970145070552826, |
| "epoch": 0.9340659340659341, |
| "grad_norm": 2.296875, |
| "learning_rate": 1.1559657292501044e-05, |
| "loss": 0.87716064453125, |
| "mean_token_accuracy": 0.7763631820678711, |
| "num_tokens": 7852495.0, |
| "step": 1275 |
| }, |
| { |
| "entropy": 0.9301983499526978, |
| "epoch": 0.9523809523809523, |
| "grad_norm": 2.09375, |
| "learning_rate": 1.1266043410114557e-05, |
| "loss": 0.907692642211914, |
| "mean_token_accuracy": 0.7715549063682556, |
| "num_tokens": 8001324.0, |
| "step": 1300 |
| }, |
| { |
| "entropy": 0.91446182847023, |
| "epoch": 0.9706959706959707, |
| "grad_norm": 2.359375, |
| "learning_rate": 1.0971315847370463e-05, |
| "loss": 0.8939350891113281, |
| "mean_token_accuracy": 0.7720365560054779, |
| "num_tokens": 8161385.0, |
| "step": 1325 |
| }, |
| { |
| "entropy": 0.9196098625659943, |
| "epoch": 0.989010989010989, |
| "grad_norm": 2.109375, |
| "learning_rate": 1.06757338625966e-05, |
| "loss": 0.89285888671875, |
| "mean_token_accuracy": 0.7721686267852783, |
| "num_tokens": 8315619.0, |
| "step": 1350 |
| }, |
| { |
| "entropy": 0.9019503581523896, |
| "epoch": 1.0073260073260073, |
| "grad_norm": 1.8828125, |
| "learning_rate": 1.0379557465716696e-05, |
| "loss": 0.853975830078125, |
| "mean_token_accuracy": 0.7786379647254944, |
| "num_tokens": 8474116.0, |
| "step": 1375 |
| }, |
| { |
| "entropy": 0.8720257365703583, |
| "epoch": 1.0256410256410255, |
| "grad_norm": 2.140625, |
| "learning_rate": 1.0083047189531566e-05, |
| "loss": 0.8370319366455078, |
| "mean_token_accuracy": 0.7838277363777161, |
| "num_tokens": 8633284.0, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.0256410256410255, |
| "eval_entropy": 0.8584034711950355, |
| "eval_loss": 0.9003849029541016, |
| "eval_mean_token_accuracy": 0.7730862986710336, |
| "eval_num_tokens": 8633284.0, |
| "eval_runtime": 8.0586, |
| "eval_samples_per_second": 285.285, |
| "eval_steps_per_second": 17.869, |
| "step": 1400 |
| }, |
| { |
| "entropy": 0.8384023177623748, |
| "epoch": 1.043956043956044, |
| "grad_norm": 2.15625, |
| "learning_rate": 9.786463860540352e-06, |
| "loss": 0.7985468292236328, |
| "mean_token_accuracy": 0.7922709083557129, |
| "num_tokens": 8785152.0, |
| "step": 1425 |
| }, |
| { |
| "entropy": 0.848993946313858, |
| "epoch": 1.0622710622710623, |
| "grad_norm": 2.234375, |
| "learning_rate": 9.49006836950339e-06, |
| "loss": 0.8184638977050781, |
| "mean_token_accuracy": 0.7883424413204193, |
| "num_tokens": 8936429.0, |
| "step": 1450 |
| }, |
| { |
| "entropy": 0.8467873334884644, |
| "epoch": 1.0805860805860805, |
| "grad_norm": 2.140625, |
| "learning_rate": 9.194121441948596e-06, |
| "loss": 0.8056396484375, |
| "mean_token_accuracy": 0.7903980255126953, |
| "num_tokens": 9094633.0, |
| "step": 1475 |
| }, |
| { |
| "entropy": 0.8402684187889099, |
| "epoch": 1.098901098901099, |
| "grad_norm": 2.109375, |
| "learning_rate": 8.898883408823124e-06, |
| "loss": 0.8085630798339843, |
| "mean_token_accuracy": 0.7898635935783386, |
| "num_tokens": 9246323.0, |
| "step": 1500 |
| }, |
| { |
| "entropy": 0.8303942859172821, |
| "epoch": 1.1172161172161172, |
| "grad_norm": 2.0625, |
| "learning_rate": 8.604613977492212e-06, |
| "loss": 0.7932289123535157, |
| "mean_token_accuracy": 0.7939286470413208, |
| "num_tokens": 9395722.0, |
| "step": 1525 |
| }, |
| { |
| "entropy": 0.8481007432937622, |
| "epoch": 1.1355311355311355, |
| "grad_norm": 2.109375, |
| "learning_rate": 8.3115720032865e-06, |
| "loss": 0.8194800567626953, |
| "mean_token_accuracy": 0.7893430662155151, |
| "num_tokens": 9547484.0, |
| "step": 1550 |
| }, |
| { |
| "entropy": 0.8354680657386779, |
| "epoch": 1.1538461538461537, |
| "grad_norm": 2.265625, |
| "learning_rate": 8.02001526179883e-06, |
| "loss": 0.8005447387695312, |
| "mean_token_accuracy": 0.7913288366794586, |
| "num_tokens": 9699959.0, |
| "step": 1575 |
| }, |
| { |
| "entropy": 0.8411949121952057, |
| "epoch": 1.1721611721611722, |
| "grad_norm": 2.125, |
| "learning_rate": 7.730200222130932e-06, |
| "loss": 0.810956039428711, |
| "mean_token_accuracy": 0.7901583468914032, |
| "num_tokens": 9851149.0, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.1721611721611722, |
| "eval_entropy": 0.8544707364506192, |
| "eval_loss": 0.8998146057128906, |
| "eval_mean_token_accuracy": 0.7731748426126109, |
| "eval_num_tokens": 9851149.0, |
| "eval_runtime": 8.0715, |
| "eval_samples_per_second": 284.828, |
| "eval_steps_per_second": 17.84, |
| "step": 1600 |
| }, |
| { |
| "entropy": 0.8444626975059509, |
| "epoch": 1.1904761904761905, |
| "grad_norm": 2.328125, |
| "learning_rate": 7.442381821289248e-06, |
| "loss": 0.8108631896972657, |
| "mean_token_accuracy": 0.7912653696537018, |
| "num_tokens": 9998793.0, |
| "step": 1625 |
| }, |
| { |
| "entropy": 0.8223755669593811, |
| "epoch": 1.2087912087912087, |
| "grad_norm": 2.09375, |
| "learning_rate": 7.1568132399285794e-06, |
| "loss": 0.7869499969482422, |
| "mean_token_accuracy": 0.7936726534366607, |
| "num_tokens": 10152752.0, |
| "step": 1650 |
| }, |
| { |
| "entropy": 0.8130457592010498, |
| "epoch": 1.2271062271062272, |
| "grad_norm": 1.875, |
| "learning_rate": 6.8737456796406594e-06, |
| "loss": 0.78310546875, |
| "mean_token_accuracy": 0.7966435635089875, |
| "num_tokens": 10308001.0, |
| "step": 1675 |
| }, |
| { |
| "entropy": 0.8471330416202545, |
| "epoch": 1.2454212454212454, |
| "grad_norm": 2.046875, |
| "learning_rate": 6.593428141983595e-06, |
| "loss": 0.8101668548583985, |
| "mean_token_accuracy": 0.7890221488475799, |
| "num_tokens": 10459655.0, |
| "step": 1700 |
| }, |
| { |
| "entropy": 0.8247973656654358, |
| "epoch": 1.2637362637362637, |
| "grad_norm": 2.1875, |
| "learning_rate": 6.316107209446662e-06, |
| "loss": 0.796153564453125, |
| "mean_token_accuracy": 0.7926836657524109, |
| "num_tokens": 10615183.0, |
| "step": 1725 |
| }, |
| { |
| "entropy": 0.8476881444454193, |
| "epoch": 1.282051282051282, |
| "grad_norm": 2.1875, |
| "learning_rate": 6.042026828542942e-06, |
| "loss": 0.8173642730712891, |
| "mean_token_accuracy": 0.7872111082077027, |
| "num_tokens": 10774019.0, |
| "step": 1750 |
| }, |
| { |
| "entropy": 0.8313502633571624, |
| "epoch": 1.3003663003663004, |
| "grad_norm": 2.0, |
| "learning_rate": 5.7714280952207955e-06, |
| "loss": 0.8023670959472656, |
| "mean_token_accuracy": 0.7926879894733428, |
| "num_tokens": 10926453.0, |
| "step": 1775 |
| }, |
| { |
| "entropy": 0.8281714594364167, |
| "epoch": 1.3186813186813187, |
| "grad_norm": 2.296875, |
| "learning_rate": 5.504549042782779e-06, |
| "loss": 0.7919468688964844, |
| "mean_token_accuracy": 0.7943351435661316, |
| "num_tokens": 11076817.0, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.3186813186813187, |
| "eval_entropy": 0.8518242807024055, |
| "eval_loss": 0.8994762897491455, |
| "eval_mean_token_accuracy": 0.7733377065095637, |
| "eval_num_tokens": 11076817.0, |
| "eval_runtime": 8.0691, |
| "eval_samples_per_second": 284.912, |
| "eval_steps_per_second": 17.846, |
| "step": 1800 |
| }, |
| { |
| "entropy": 0.8253132402896881, |
| "epoch": 1.3369963369963371, |
| "grad_norm": 2.09375, |
| "learning_rate": 5.241624432498673e-06, |
| "loss": 0.7934477996826171, |
| "mean_token_accuracy": 0.7905769181251526, |
| "num_tokens": 11235359.0, |
| "step": 1825 |
| }, |
| { |
| "entropy": 0.8527077162265777, |
| "epoch": 1.3553113553113554, |
| "grad_norm": 2.25, |
| "learning_rate": 4.982885547096754e-06, |
| "loss": 0.8256228637695312, |
| "mean_token_accuracy": 0.7879673659801483, |
| "num_tokens": 11385249.0, |
| "step": 1850 |
| }, |
| { |
| "entropy": 0.8239582288265228, |
| "epoch": 1.3736263736263736, |
| "grad_norm": 2.09375, |
| "learning_rate": 4.728559987314975e-06, |
| "loss": 0.7923411560058594, |
| "mean_token_accuracy": 0.7940970385074615, |
| "num_tokens": 11539970.0, |
| "step": 1875 |
| }, |
| { |
| "entropy": 0.8423762857913971, |
| "epoch": 1.3919413919413919, |
| "grad_norm": 2.1875, |
| "learning_rate": 4.478871471691031e-06, |
| "loss": 0.8075601196289063, |
| "mean_token_accuracy": 0.7895544397830964, |
| "num_tokens": 11694684.0, |
| "step": 1900 |
| }, |
| { |
| "entropy": 0.8148546552658081, |
| "epoch": 1.4102564102564101, |
| "grad_norm": 2.125, |
| "learning_rate": 4.234039639767406e-06, |
| "loss": 0.7813822937011718, |
| "mean_token_accuracy": 0.7967073798179627, |
| "num_tokens": 11850074.0, |
| "step": 1925 |
| }, |
| { |
| "entropy": 0.840382571220398, |
| "epoch": 1.4285714285714286, |
| "grad_norm": 2.09375, |
| "learning_rate": 3.994279858884551e-06, |
| "loss": 0.8069898986816406, |
| "mean_token_accuracy": 0.7921997106075287, |
| "num_tokens": 12004729.0, |
| "step": 1950 |
| }, |
| { |
| "entropy": 0.8522861528396607, |
| "epoch": 1.4468864468864469, |
| "grad_norm": 2.03125, |
| "learning_rate": 3.7598030347321e-06, |
| "loss": 0.8208354187011718, |
| "mean_token_accuracy": 0.789222640991211, |
| "num_tokens": 12157974.0, |
| "step": 1975 |
| }, |
| { |
| "entropy": 0.8414350926876069, |
| "epoch": 1.4652014652014653, |
| "grad_norm": 2.078125, |
| "learning_rate": 3.530815425824797e-06, |
| "loss": 0.8093458557128906, |
| "mean_token_accuracy": 0.7892864966392517, |
| "num_tokens": 12306150.0, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.4652014652014653, |
| "eval_entropy": 0.8502832547658019, |
| "eval_loss": 0.8990073204040527, |
| "eval_mean_token_accuracy": 0.7732960196832815, |
| "eval_num_tokens": 12306150.0, |
| "eval_runtime": 8.068, |
| "eval_samples_per_second": 284.952, |
| "eval_steps_per_second": 17.848, |
| "step": 2000 |
| }, |
| { |
| "entropy": 0.8521664845943451, |
| "epoch": 1.4835164835164836, |
| "grad_norm": 2.0625, |
| "learning_rate": 3.307518462066344e-06, |
| "loss": 0.8166194915771484, |
| "mean_token_accuracy": 0.785648273229599, |
| "num_tokens": 12456962.0, |
| "step": 2025 |
| }, |
| { |
| "entropy": 0.8251003730297088, |
| "epoch": 1.5018315018315018, |
| "grad_norm": 2.203125, |
| "learning_rate": 3.0901085675607266e-06, |
| "loss": 0.7916029357910156, |
| "mean_token_accuracy": 0.7955028152465821, |
| "num_tokens": 12606544.0, |
| "step": 2050 |
| }, |
| { |
| "entropy": 0.8439912271499633, |
| "epoch": 1.52014652014652, |
| "grad_norm": 2.203125, |
| "learning_rate": 2.8787769878269667e-06, |
| "loss": 0.811083755493164, |
| "mean_token_accuracy": 0.7906605911254883, |
| "num_tokens": 12763473.0, |
| "step": 2075 |
| }, |
| { |
| "entropy": 0.8612873029708862, |
| "epoch": 1.5384615384615383, |
| "grad_norm": 2.21875, |
| "learning_rate": 2.673709621569167e-06, |
| "loss": 0.834039077758789, |
| "mean_token_accuracy": 0.786132972240448, |
| "num_tokens": 12917918.0, |
| "step": 2100 |
| }, |
| { |
| "entropy": 0.832386200428009, |
| "epoch": 1.5567765567765568, |
| "grad_norm": 2.15625, |
| "learning_rate": 2.475086857149982e-06, |
| "loss": 0.7950384521484375, |
| "mean_token_accuracy": 0.7901384067535401, |
| "num_tokens": 13072296.0, |
| "step": 2125 |
| }, |
| { |
| "entropy": 0.8401387500762939, |
| "epoch": 1.575091575091575, |
| "grad_norm": 2.140625, |
| "learning_rate": 2.2830834139112136e-06, |
| "loss": 0.8060906219482422, |
| "mean_token_accuracy": 0.7896384346485138, |
| "num_tokens": 13226077.0, |
| "step": 2150 |
| }, |
| { |
| "entropy": 0.8430456602573395, |
| "epoch": 1.5934065934065935, |
| "grad_norm": 2.28125, |
| "learning_rate": 2.097868188481217e-06, |
| "loss": 0.8120394134521485, |
| "mean_token_accuracy": 0.7886982035636901, |
| "num_tokens": 13379631.0, |
| "step": 2175 |
| }, |
| { |
| "entropy": 0.8341074979305267, |
| "epoch": 1.6117216117216118, |
| "grad_norm": 2.28125, |
| "learning_rate": 1.919604106204298e-06, |
| "loss": 0.7923731231689453, |
| "mean_token_accuracy": 0.7932259738445282, |
| "num_tokens": 13537431.0, |
| "step": 2200 |
| }, |
| { |
| "epoch": 1.6117216117216118, |
| "eval_entropy": 0.8466265425086021, |
| "eval_loss": 0.8991615176200867, |
| "eval_mean_token_accuracy": 0.7732404433190823, |
| "eval_num_tokens": 13537431.0, |
| "eval_runtime": 8.0784, |
| "eval_samples_per_second": 284.585, |
| "eval_steps_per_second": 17.825, |
| "step": 2200 |
| }, |
| { |
| "entropy": 0.829889565706253, |
| "epoch": 1.63003663003663, |
| "grad_norm": 2.09375, |
| "learning_rate": 1.7484479778227281e-06, |
| "loss": 0.7963677215576171, |
| "mean_token_accuracy": 0.7930803084373474, |
| "num_tokens": 13696124.0, |
| "step": 2225 |
| }, |
| { |
| "entropy": 0.8456670987606049, |
| "epoch": 1.6483516483516483, |
| "grad_norm": 2.125, |
| "learning_rate": 1.5845503615375534e-06, |
| "loss": 0.8171965789794922, |
| "mean_token_accuracy": 0.78998281955719, |
| "num_tokens": 13850353.0, |
| "step": 2250 |
| }, |
| { |
| "entropy": 0.834287303686142, |
| "epoch": 1.6666666666666665, |
| "grad_norm": 2.203125, |
| "learning_rate": 1.4280554305694205e-06, |
| "loss": 0.8009786987304688, |
| "mean_token_accuracy": 0.7929751622676849, |
| "num_tokens": 14002830.0, |
| "step": 2275 |
| }, |
| { |
| "entropy": 0.8210822236537934, |
| "epoch": 1.684981684981685, |
| "grad_norm": 2.171875, |
| "learning_rate": 1.2791008463360077e-06, |
| "loss": 0.7856560516357421, |
| "mean_token_accuracy": 0.7937294292449951, |
| "num_tokens": 14159802.0, |
| "step": 2300 |
| }, |
| { |
| "entropy": 0.8226444447040557, |
| "epoch": 1.7032967032967035, |
| "grad_norm": 2.09375, |
| "learning_rate": 1.1378176373575977e-06, |
| "loss": 0.7973332977294922, |
| "mean_token_accuracy": 0.7935956382751465, |
| "num_tokens": 14315490.0, |
| "step": 2325 |
| }, |
| { |
| "entropy": 0.8418577921390533, |
| "epoch": 1.7216117216117217, |
| "grad_norm": 2.203125, |
| "learning_rate": 1.004330083997278e-06, |
| "loss": 0.8100568389892578, |
| "mean_token_accuracy": 0.79057302236557, |
| "num_tokens": 14471457.0, |
| "step": 2350 |
| }, |
| { |
| "entropy": 0.8569370365142822, |
| "epoch": 1.73992673992674, |
| "grad_norm": 2.296875, |
| "learning_rate": 8.787556091372207e-07, |
| "loss": 0.8271647644042969, |
| "mean_token_accuracy": 0.783940087556839, |
| "num_tokens": 14627084.0, |
| "step": 2375 |
| }, |
| { |
| "entropy": 0.8276915633678437, |
| "epoch": 1.7582417582417582, |
| "grad_norm": 2.171875, |
| "learning_rate": 7.612046748871327e-07, |
| "loss": 0.8014369201660156, |
| "mean_token_accuracy": 0.790752956867218, |
| "num_tokens": 14772996.0, |
| "step": 2400 |
| }, |
| { |
| "epoch": 1.7582417582417582, |
| "eval_entropy": 0.8465850080053011, |
| "eval_loss": 0.899135172367096, |
| "eval_mean_token_accuracy": 0.7732518298758401, |
| "eval_num_tokens": 14772996.0, |
| "eval_runtime": 8.0715, |
| "eval_samples_per_second": 284.83, |
| "eval_steps_per_second": 17.841, |
| "step": 2400 |
| }, |
| { |
| "entropy": 0.8189385521411896, |
| "epoch": 1.7765567765567765, |
| "grad_norm": 2.09375, |
| "learning_rate": 6.517806854158204e-07, |
| "loss": 0.7890790557861328, |
| "mean_token_accuracy": 0.7950505125522613, |
| "num_tokens": 14926511.0, |
| "step": 2425 |
| }, |
| { |
| "entropy": 0.8378893113136292, |
| "epoch": 1.7948717948717947, |
| "grad_norm": 2.359375, |
| "learning_rate": 5.505798959912723e-07, |
| "loss": 0.8117930603027343, |
| "mean_token_accuracy": 0.7887657046318054, |
| "num_tokens": 15081687.0, |
| "step": 2450 |
| }, |
| { |
| "entropy": 0.8320703601837158, |
| "epoch": 1.8131868131868132, |
| "grad_norm": 2.140625, |
| "learning_rate": 4.576913283093098e-07, |
| "loss": 0.8038975524902344, |
| "mean_token_accuracy": 0.7904533529281617, |
| "num_tokens": 15236278.0, |
| "step": 2475 |
| }, |
| { |
| "entropy": 0.8401167035102844, |
| "epoch": 1.8315018315018317, |
| "grad_norm": 2.234375, |
| "learning_rate": 3.7319669218529475e-07, |
| "loss": 0.8033819580078125, |
| "mean_token_accuracy": 0.7910889124870301, |
| "num_tokens": 15391169.0, |
| "step": 2500 |
| }, |
| { |
| "entropy": 0.858134560585022, |
| "epoch": 1.84981684981685, |
| "grad_norm": 2.359375, |
| "learning_rate": 2.971703136777315e-07, |
| "loss": 0.8318187713623046, |
| "mean_token_accuracy": 0.784791008234024, |
| "num_tokens": 15548066.0, |
| "step": 2525 |
| }, |
| { |
| "entropy": 0.8192259454727173, |
| "epoch": 1.8681318681318682, |
| "grad_norm": 1.9453125, |
| "learning_rate": 2.2967906970705722e-07, |
| "loss": 0.7859656524658203, |
| "mean_token_accuracy": 0.7967568933963776, |
| "num_tokens": 15699746.0, |
| "step": 2550 |
| }, |
| { |
| "entropy": 0.8540216779708862, |
| "epoch": 1.8864468864468864, |
| "grad_norm": 2.171875, |
| "learning_rate": 1.7078232922706495e-07, |
| "loss": 0.8298044586181641, |
| "mean_token_accuracy": 0.7818279254436493, |
| "num_tokens": 15856690.0, |
| "step": 2575 |
| }, |
| { |
| "entropy": 0.8150307929515839, |
| "epoch": 1.9047619047619047, |
| "grad_norm": 2.109375, |
| "learning_rate": 1.2053190100077106e-07, |
| "loss": 0.7887921905517579, |
| "mean_token_accuracy": 0.7932768344879151, |
| "num_tokens": 16013738.0, |
| "step": 2600 |
| }, |
| { |
| "epoch": 1.9047619047619047, |
| "eval_entropy": 0.8467293654878935, |
| "eval_loss": 0.8991142511367798, |
| "eval_mean_token_accuracy": 0.7734044496383932, |
| "eval_num_tokens": 16013738.0, |
| "eval_runtime": 8.0684, |
| "eval_samples_per_second": 284.939, |
| "eval_steps_per_second": 17.847, |
| "step": 2600 |
| }, |
| { |
| "entropy": 0.8457963478565216, |
| "epoch": 1.9230769230769231, |
| "grad_norm": 2.1875, |
| "learning_rate": 7.897198802661266e-08, |
| "loss": 0.8114620971679688, |
| "mean_token_accuracy": 0.7876574242115021, |
| "num_tokens": 16168732.0, |
| "step": 2625 |
| }, |
| { |
| "entropy": 0.8315440094470978, |
| "epoch": 1.9413919413919414, |
| "grad_norm": 2.09375, |
| "learning_rate": 4.613914865509439e-08, |
| "loss": 0.8015847778320313, |
| "mean_token_accuracy": 0.7910509896278382, |
| "num_tokens": 16319610.0, |
| "step": 2650 |
| }, |
| { |
| "entropy": 0.8333329391479493, |
| "epoch": 1.9597069597069599, |
| "grad_norm": 2.1875, |
| "learning_rate": 2.2062264430087187e-08, |
| "loss": 0.8026151275634765, |
| "mean_token_accuracy": 0.7906608557701111, |
| "num_tokens": 16484108.0, |
| "step": 2675 |
| }, |
| { |
| "entropy": 0.8297130846977234, |
| "epoch": 1.978021978021978, |
| "grad_norm": 2.0625, |
| "learning_rate": 6.762514683058552e-09, |
| "loss": 0.7984342193603515, |
| "mean_token_accuracy": 0.7927398717403412, |
| "num_tokens": 16637988.0, |
| "step": 2700 |
| }, |
| { |
| "entropy": 0.8448534452915192, |
| "epoch": 1.9963369963369964, |
| "grad_norm": 2.1875, |
| "learning_rate": 2.5335790258207426e-10, |
| "loss": 0.8189653015136719, |
| "mean_token_accuracy": 0.7890227103233337, |
| "num_tokens": 16789803.0, |
| "step": 2725 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_entropy": 0.8461464825603697, |
| "eval_loss": 0.8991644978523254, |
| "eval_mean_token_accuracy": 0.7732141961654028, |
| "eval_num_tokens": 16819082.0, |
| "eval_runtime": 8.0725, |
| "eval_samples_per_second": 284.796, |
| "eval_steps_per_second": 17.838, |
| "step": 2730 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 2730, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.805484445629952e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
