| { | |
| "best_global_step": 4000, | |
| "best_metric": 0.10079683363437653, | |
| "best_model_checkpoint": "output/Tiger-classification/2025-07-13-16.35.13/checkpoint-4000", | |
| "epoch": 1.2254901960784315, | |
| "eval_steps": 1000, | |
| "global_step": 6000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002042483660130719, | |
| "grad_norm": 605.90966796875, | |
| "learning_rate": 3.673469387755102e-07, | |
| "loss": 23.6946, | |
| "mean_token_accuracy": 0.0, | |
| "num_tokens": 59398.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004084967320261438, | |
| "grad_norm": 575.8460083007812, | |
| "learning_rate": 7.755102040816327e-07, | |
| "loss": 23.3788, | |
| "mean_token_accuracy": 0.0, | |
| "num_tokens": 117685.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006127450980392157, | |
| "grad_norm": 629.7777099609375, | |
| "learning_rate": 1.183673469387755e-06, | |
| "loss": 23.0559, | |
| "mean_token_accuracy": 0.0, | |
| "num_tokens": 178062.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008169934640522876, | |
| "grad_norm": 546.323486328125, | |
| "learning_rate": 1.5918367346938775e-06, | |
| "loss": 22.3605, | |
| "mean_token_accuracy": 0.0, | |
| "num_tokens": 232540.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010212418300653595, | |
| "grad_norm": 457.29876708984375, | |
| "learning_rate": 2e-06, | |
| "loss": 21.4275, | |
| "mean_token_accuracy": 0.0, | |
| "num_tokens": 288974.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012254901960784314, | |
| "grad_norm": 515.7296142578125, | |
| "learning_rate": 2.4081632653061225e-06, | |
| "loss": 20.3691, | |
| "mean_token_accuracy": 0.0, | |
| "num_tokens": 348237.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.014297385620915032, | |
| "grad_norm": 542.2606811523438, | |
| "learning_rate": 2.816326530612245e-06, | |
| "loss": 19.0279, | |
| "mean_token_accuracy": 0.0, | |
| "num_tokens": 407496.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.016339869281045753, | |
| "grad_norm": 519.3001098632812, | |
| "learning_rate": 3.2244897959183677e-06, | |
| "loss": 17.8239, | |
| "mean_token_accuracy": 0.0, | |
| "num_tokens": 465147.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01838235294117647, | |
| "grad_norm": 726.2546997070312, | |
| "learning_rate": 3.63265306122449e-06, | |
| "loss": 16.3369, | |
| "mean_token_accuracy": 0.0, | |
| "num_tokens": 519594.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02042483660130719, | |
| "grad_norm": 525.6044921875, | |
| "learning_rate": 4.040816326530612e-06, | |
| "loss": 14.6413, | |
| "mean_token_accuracy": 0.0, | |
| "num_tokens": 580611.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02246732026143791, | |
| "grad_norm": 436.4392395019531, | |
| "learning_rate": 4.448979591836735e-06, | |
| "loss": 12.8592, | |
| "mean_token_accuracy": 0.0, | |
| "num_tokens": 634845.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.024509803921568627, | |
| "grad_norm": 435.2156677246094, | |
| "learning_rate": 4.857142857142858e-06, | |
| "loss": 10.7955, | |
| "mean_token_accuracy": 0.0, | |
| "num_tokens": 692187.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.026552287581699346, | |
| "grad_norm": 394.40850830078125, | |
| "learning_rate": 5.265306122448979e-06, | |
| "loss": 8.6123, | |
| "mean_token_accuracy": 0.0, | |
| "num_tokens": 752102.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.028594771241830064, | |
| "grad_norm": 348.3984069824219, | |
| "learning_rate": 5.673469387755103e-06, | |
| "loss": 6.755, | |
| "mean_token_accuracy": 0.0, | |
| "num_tokens": 807593.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.030637254901960783, | |
| "grad_norm": 506.72607421875, | |
| "learning_rate": 6.0816326530612245e-06, | |
| "loss": 4.7543, | |
| "mean_token_accuracy": 0.0, | |
| "num_tokens": 863923.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.032679738562091505, | |
| "grad_norm": 255.61703491210938, | |
| "learning_rate": 6.489795918367347e-06, | |
| "loss": 2.9545, | |
| "mean_token_accuracy": 0.0, | |
| "num_tokens": 918457.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.034722222222222224, | |
| "grad_norm": 156.01780700683594, | |
| "learning_rate": 6.89795918367347e-06, | |
| "loss": 1.3627, | |
| "mean_token_accuracy": 0.5375, | |
| "num_tokens": 975912.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.03676470588235294, | |
| "grad_norm": 90.10558319091797, | |
| "learning_rate": 7.306122448979591e-06, | |
| "loss": 0.7514, | |
| "mean_token_accuracy": 0.7625, | |
| "num_tokens": 1031481.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03880718954248366, | |
| "grad_norm": 44.40696334838867, | |
| "learning_rate": 7.714285714285714e-06, | |
| "loss": 0.5003, | |
| "mean_token_accuracy": 0.8375, | |
| "num_tokens": 1087664.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.04084967320261438, | |
| "grad_norm": 20.749303817749023, | |
| "learning_rate": 8.122448979591837e-06, | |
| "loss": 0.4515, | |
| "mean_token_accuracy": 0.85, | |
| "num_tokens": 1147055.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0428921568627451, | |
| "grad_norm": 19.873743057250977, | |
| "learning_rate": 8.53061224489796e-06, | |
| "loss": 0.3701, | |
| "mean_token_accuracy": 0.8875, | |
| "num_tokens": 1206863.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.04493464052287582, | |
| "grad_norm": 98.0947265625, | |
| "learning_rate": 8.938775510204082e-06, | |
| "loss": 0.3889, | |
| "mean_token_accuracy": 0.875, | |
| "num_tokens": 1262357.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.046977124183006536, | |
| "grad_norm": 16.434467315673828, | |
| "learning_rate": 9.346938775510204e-06, | |
| "loss": 0.463, | |
| "mean_token_accuracy": 0.8375, | |
| "num_tokens": 1321064.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.049019607843137254, | |
| "grad_norm": 19.866003036499023, | |
| "learning_rate": 9.755102040816327e-06, | |
| "loss": 0.4743, | |
| "mean_token_accuracy": 0.8125, | |
| "num_tokens": 1380556.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.05106209150326797, | |
| "grad_norm": 34.22461700439453, | |
| "learning_rate": 1.016326530612245e-05, | |
| "loss": 0.4524, | |
| "mean_token_accuracy": 0.825, | |
| "num_tokens": 1438777.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.05310457516339869, | |
| "grad_norm": 17.785221099853516, | |
| "learning_rate": 1.0571428571428572e-05, | |
| "loss": 0.4141, | |
| "mean_token_accuracy": 0.8625, | |
| "num_tokens": 1492157.0, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.05514705882352941, | |
| "grad_norm": 51.57341384887695, | |
| "learning_rate": 1.0979591836734693e-05, | |
| "loss": 0.4024, | |
| "mean_token_accuracy": 0.8625, | |
| "num_tokens": 1549918.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.05718954248366013, | |
| "grad_norm": 19.679533004760742, | |
| "learning_rate": 1.1387755102040817e-05, | |
| "loss": 0.2964, | |
| "mean_token_accuracy": 0.9125, | |
| "num_tokens": 1608117.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.05923202614379085, | |
| "grad_norm": 17.60881233215332, | |
| "learning_rate": 1.179591836734694e-05, | |
| "loss": 0.437, | |
| "mean_token_accuracy": 0.8375, | |
| "num_tokens": 1667175.0, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.061274509803921566, | |
| "grad_norm": 19.26199722290039, | |
| "learning_rate": 1.220408163265306e-05, | |
| "loss": 0.4516, | |
| "mean_token_accuracy": 0.8375, | |
| "num_tokens": 1725672.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.06331699346405228, | |
| "grad_norm": 73.5859603881836, | |
| "learning_rate": 1.2612244897959183e-05, | |
| "loss": 0.4344, | |
| "mean_token_accuracy": 0.8375, | |
| "num_tokens": 1782213.0, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.06535947712418301, | |
| "grad_norm": 76.99100494384766, | |
| "learning_rate": 1.3020408163265306e-05, | |
| "loss": 0.4884, | |
| "mean_token_accuracy": 0.8, | |
| "num_tokens": 1839747.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.06740196078431372, | |
| "grad_norm": 45.10923767089844, | |
| "learning_rate": 1.342857142857143e-05, | |
| "loss": 0.4898, | |
| "mean_token_accuracy": 0.8125, | |
| "num_tokens": 1893988.0, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.06944444444444445, | |
| "grad_norm": 19.993825912475586, | |
| "learning_rate": 1.3836734693877551e-05, | |
| "loss": 0.3189, | |
| "mean_token_accuracy": 0.9125, | |
| "num_tokens": 1949484.0, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.07148692810457516, | |
| "grad_norm": 73.58136749267578, | |
| "learning_rate": 1.4244897959183674e-05, | |
| "loss": 0.4051, | |
| "mean_token_accuracy": 0.875, | |
| "num_tokens": 2003136.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.07352941176470588, | |
| "grad_norm": 38.98894119262695, | |
| "learning_rate": 1.4653061224489796e-05, | |
| "loss": 0.2481, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 2061282.0, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.0755718954248366, | |
| "grad_norm": 76.9441909790039, | |
| "learning_rate": 1.5061224489795919e-05, | |
| "loss": 0.2633, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 2118497.0, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.07761437908496732, | |
| "grad_norm": 16.983497619628906, | |
| "learning_rate": 1.546938775510204e-05, | |
| "loss": 0.401, | |
| "mean_token_accuracy": 0.8625, | |
| "num_tokens": 2176397.0, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.07965686274509803, | |
| "grad_norm": 50.44063949584961, | |
| "learning_rate": 1.5877551020408166e-05, | |
| "loss": 0.3508, | |
| "mean_token_accuracy": 0.875, | |
| "num_tokens": 2228001.0, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.08169934640522876, | |
| "grad_norm": 23.372730255126953, | |
| "learning_rate": 1.6285714285714283e-05, | |
| "loss": 0.4327, | |
| "mean_token_accuracy": 0.8375, | |
| "num_tokens": 2281787.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.08374183006535947, | |
| "grad_norm": 31.091564178466797, | |
| "learning_rate": 1.6693877551020408e-05, | |
| "loss": 0.4008, | |
| "mean_token_accuracy": 0.8375, | |
| "num_tokens": 2336223.0, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.0857843137254902, | |
| "grad_norm": 40.28383255004883, | |
| "learning_rate": 1.7102040816326532e-05, | |
| "loss": 0.3637, | |
| "mean_token_accuracy": 0.8375, | |
| "num_tokens": 2393112.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.08782679738562091, | |
| "grad_norm": 190.91372680664062, | |
| "learning_rate": 1.7510204081632653e-05, | |
| "loss": 0.4448, | |
| "mean_token_accuracy": 0.8125, | |
| "num_tokens": 2450140.0, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.08986928104575163, | |
| "grad_norm": 66.45523834228516, | |
| "learning_rate": 1.7918367346938777e-05, | |
| "loss": 0.3855, | |
| "mean_token_accuracy": 0.8625, | |
| "num_tokens": 2507149.0, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.09191176470588236, | |
| "grad_norm": 246.1010284423828, | |
| "learning_rate": 1.8326530612244898e-05, | |
| "loss": 0.4065, | |
| "mean_token_accuracy": 0.825, | |
| "num_tokens": 2566708.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.09395424836601307, | |
| "grad_norm": 110.25304412841797, | |
| "learning_rate": 1.8734693877551022e-05, | |
| "loss": 0.3272, | |
| "mean_token_accuracy": 0.8875, | |
| "num_tokens": 2622103.0, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.0959967320261438, | |
| "grad_norm": 46.352264404296875, | |
| "learning_rate": 1.9142857142857143e-05, | |
| "loss": 0.2289, | |
| "mean_token_accuracy": 0.9125, | |
| "num_tokens": 2678253.0, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.09803921568627451, | |
| "grad_norm": 63.184757232666016, | |
| "learning_rate": 1.9551020408163264e-05, | |
| "loss": 0.3118, | |
| "mean_token_accuracy": 0.8625, | |
| "num_tokens": 2732060.0, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.10008169934640523, | |
| "grad_norm": 85.73307800292969, | |
| "learning_rate": 1.9959183673469388e-05, | |
| "loss": 0.2857, | |
| "mean_token_accuracy": 0.9, | |
| "num_tokens": 2786974.0, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.10212418300653595, | |
| "grad_norm": 62.449249267578125, | |
| "learning_rate": 2.036734693877551e-05, | |
| "loss": 0.3082, | |
| "mean_token_accuracy": 0.8875, | |
| "num_tokens": 2845404.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.10416666666666667, | |
| "grad_norm": 113.24309539794922, | |
| "learning_rate": 2.0775510204081633e-05, | |
| "loss": 0.2842, | |
| "mean_token_accuracy": 0.9125, | |
| "num_tokens": 2902907.0, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.10620915032679738, | |
| "grad_norm": 96.13944244384766, | |
| "learning_rate": 2.1183673469387758e-05, | |
| "loss": 0.1935, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 2959168.0, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.10825163398692811, | |
| "grad_norm": 129.3743896484375, | |
| "learning_rate": 2.159183673469388e-05, | |
| "loss": 0.2606, | |
| "mean_token_accuracy": 0.875, | |
| "num_tokens": 3013982.0, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.11029411764705882, | |
| "grad_norm": 75.24097442626953, | |
| "learning_rate": 2.2e-05, | |
| "loss": 0.1492, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 3072122.0, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.11233660130718955, | |
| "grad_norm": 162.96792602539062, | |
| "learning_rate": 2.240816326530612e-05, | |
| "loss": 0.2579, | |
| "mean_token_accuracy": 0.9125, | |
| "num_tokens": 3131116.0, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.11437908496732026, | |
| "grad_norm": 46.852962493896484, | |
| "learning_rate": 2.2816326530612245e-05, | |
| "loss": 0.2634, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 3186577.0, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.11642156862745098, | |
| "grad_norm": 136.53048706054688, | |
| "learning_rate": 2.322448979591837e-05, | |
| "loss": 0.2447, | |
| "mean_token_accuracy": 0.85, | |
| "num_tokens": 3245096.0, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.1184640522875817, | |
| "grad_norm": 31.598054885864258, | |
| "learning_rate": 2.363265306122449e-05, | |
| "loss": 0.2373, | |
| "mean_token_accuracy": 0.9125, | |
| "num_tokens": 3305902.0, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.12050653594771242, | |
| "grad_norm": 55.6317138671875, | |
| "learning_rate": 2.4040816326530614e-05, | |
| "loss": 0.1476, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 3360580.0, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.12254901960784313, | |
| "grad_norm": 134.1688995361328, | |
| "learning_rate": 2.4448979591836735e-05, | |
| "loss": 0.2767, | |
| "mean_token_accuracy": 0.85, | |
| "num_tokens": 3418039.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.12459150326797386, | |
| "grad_norm": 41.687259674072266, | |
| "learning_rate": 2.485714285714286e-05, | |
| "loss": 0.1983, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 3473528.0, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.12663398692810457, | |
| "grad_norm": 687.3442993164062, | |
| "learning_rate": 2.526530612244898e-05, | |
| "loss": 0.2262, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 3529846.0, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.12867647058823528, | |
| "grad_norm": 44.983642578125, | |
| "learning_rate": 2.56734693877551e-05, | |
| "loss": 0.1204, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 3589036.0, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.13071895424836602, | |
| "grad_norm": 55.48274230957031, | |
| "learning_rate": 2.6081632653061225e-05, | |
| "loss": 0.2012, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 3644290.0, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.13276143790849673, | |
| "grad_norm": 52.86427688598633, | |
| "learning_rate": 2.6489795918367346e-05, | |
| "loss": 0.2178, | |
| "mean_token_accuracy": 0.8875, | |
| "num_tokens": 3703010.0, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.13480392156862744, | |
| "grad_norm": 99.09281158447266, | |
| "learning_rate": 2.689795918367347e-05, | |
| "loss": 0.2965, | |
| "mean_token_accuracy": 0.875, | |
| "num_tokens": 3760936.0, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.13684640522875818, | |
| "grad_norm": 82.04771423339844, | |
| "learning_rate": 2.7306122448979595e-05, | |
| "loss": 0.1999, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 3818052.0, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.1388888888888889, | |
| "grad_norm": 34.1673469543457, | |
| "learning_rate": 2.7714285714285716e-05, | |
| "loss": 0.1205, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 3873573.0, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.1409313725490196, | |
| "grad_norm": 4.238792896270752, | |
| "learning_rate": 2.8122448979591837e-05, | |
| "loss": 0.0991, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 3930416.0, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.14297385620915032, | |
| "grad_norm": 54.01282501220703, | |
| "learning_rate": 2.8530612244897957e-05, | |
| "loss": 0.2126, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 3983537.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.14501633986928106, | |
| "grad_norm": 50.89653396606445, | |
| "learning_rate": 2.8938775510204082e-05, | |
| "loss": 0.1116, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 4037171.0, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.14705882352941177, | |
| "grad_norm": 117.79590606689453, | |
| "learning_rate": 2.9346938775510206e-05, | |
| "loss": 0.2448, | |
| "mean_token_accuracy": 0.875, | |
| "num_tokens": 4093028.0, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.14910130718954248, | |
| "grad_norm": 34.33708572387695, | |
| "learning_rate": 2.9755102040816327e-05, | |
| "loss": 0.1701, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 4153026.0, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.1511437908496732, | |
| "grad_norm": 19.832155227661133, | |
| "learning_rate": 2.9999997899432542e-05, | |
| "loss": 0.1477, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 4209611.0, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.15318627450980393, | |
| "grad_norm": 95.85489654541016, | |
| "learning_rate": 2.9999974268055377e-05, | |
| "loss": 0.2313, | |
| "mean_token_accuracy": 0.9, | |
| "num_tokens": 4262585.0, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.15522875816993464, | |
| "grad_norm": 26.036752700805664, | |
| "learning_rate": 2.9999924379633224e-05, | |
| "loss": 0.1625, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 4321740.0, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.15727124183006536, | |
| "grad_norm": 7.367165565490723, | |
| "learning_rate": 2.9999848234253418e-05, | |
| "loss": 0.2173, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 4379061.0, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.15931372549019607, | |
| "grad_norm": 40.99644470214844, | |
| "learning_rate": 2.9999745832049243e-05, | |
| "loss": 0.0891, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 4437270.0, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.1613562091503268, | |
| "grad_norm": 21.723899841308594, | |
| "learning_rate": 2.9999617173199948e-05, | |
| "loss": 0.0893, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 4496641.0, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.16339869281045752, | |
| "grad_norm": 7.67169189453125, | |
| "learning_rate": 2.9999462257930754e-05, | |
| "loss": 0.1063, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 4554052.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.16544117647058823, | |
| "grad_norm": 93.35088348388672, | |
| "learning_rate": 2.9999281086512836e-05, | |
| "loss": 0.0956, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 4611100.0, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.16748366013071894, | |
| "grad_norm": 28.59117317199707, | |
| "learning_rate": 2.9999073659263326e-05, | |
| "loss": 0.0931, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 4673277.0, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.16952614379084968, | |
| "grad_norm": 14.521586418151855, | |
| "learning_rate": 2.999883997654532e-05, | |
| "loss": 0.1654, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 4731704.0, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.1715686274509804, | |
| "grad_norm": 18.830577850341797, | |
| "learning_rate": 2.9998580038767878e-05, | |
| "loss": 0.2107, | |
| "mean_token_accuracy": 0.9125, | |
| "num_tokens": 4788663.0, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.1736111111111111, | |
| "grad_norm": 25.132598876953125, | |
| "learning_rate": 2.999829384638601e-05, | |
| "loss": 0.155, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 4846782.0, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.17565359477124182, | |
| "grad_norm": 82.75508117675781, | |
| "learning_rate": 2.9997981399900685e-05, | |
| "loss": 0.2943, | |
| "mean_token_accuracy": 0.875, | |
| "num_tokens": 4907742.0, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.17769607843137256, | |
| "grad_norm": 34.186092376708984, | |
| "learning_rate": 2.9997642699858835e-05, | |
| "loss": 0.1415, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 4965709.0, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.17973856209150327, | |
| "grad_norm": 15.364433288574219, | |
| "learning_rate": 2.9997277746853346e-05, | |
| "loss": 0.1022, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 5023369.0, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.18178104575163398, | |
| "grad_norm": 39.696449279785156, | |
| "learning_rate": 2.999688654152306e-05, | |
| "loss": 0.1556, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 5080312.0, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.18382352941176472, | |
| "grad_norm": 14.395807266235352, | |
| "learning_rate": 2.999646908455277e-05, | |
| "loss": 0.1818, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 5140366.0, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.18586601307189543, | |
| "grad_norm": 46.04245376586914, | |
| "learning_rate": 2.9996025376673218e-05, | |
| "loss": 0.084, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 5199778.0, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.18790849673202614, | |
| "grad_norm": 4.999418258666992, | |
| "learning_rate": 2.9995555418661106e-05, | |
| "loss": 0.1769, | |
| "mean_token_accuracy": 0.9125, | |
| "num_tokens": 5258520.0, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.18995098039215685, | |
| "grad_norm": 111.81785583496094, | |
| "learning_rate": 2.9995059211339086e-05, | |
| "loss": 0.0785, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 5315400.0, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.1919934640522876, | |
| "grad_norm": 5.296301364898682, | |
| "learning_rate": 2.9994536755575748e-05, | |
| "loss": 0.1944, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 5370066.0, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.1940359477124183, | |
| "grad_norm": 154.42257690429688, | |
| "learning_rate": 2.9993988052285645e-05, | |
| "loss": 0.1607, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 5432151.0, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.19607843137254902, | |
| "grad_norm": 76.13041687011719, | |
| "learning_rate": 2.9993413102429264e-05, | |
| "loss": 0.1002, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 5494596.0, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.19812091503267973, | |
| "grad_norm": 56.34494400024414, | |
| "learning_rate": 2.9992811907013036e-05, | |
| "loss": 0.2646, | |
| "mean_token_accuracy": 0.9, | |
| "num_tokens": 5550642.0, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.20016339869281047, | |
| "grad_norm": 53.10865020751953, | |
| "learning_rate": 2.999218446708934e-05, | |
| "loss": 0.1286, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 5611455.0, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.20220588235294118, | |
| "grad_norm": 12.334380149841309, | |
| "learning_rate": 2.999153078375649e-05, | |
| "loss": 0.1678, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 5668004.0, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.2042483660130719, | |
| "grad_norm": 55.23786163330078, | |
| "learning_rate": 2.9990850858158746e-05, | |
| "loss": 0.2287, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2042483660130719, | |
| "eval_loss": 0.12666510045528412, | |
| "eval_mean_token_accuracy": 0.9510517799352751, | |
| "eval_num_tokens": 5723317.0, | |
| "eval_runtime": 808.7837, | |
| "eval_samples_per_second": 6.113, | |
| "eval_steps_per_second": 1.528, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2062908496732026, | |
| "grad_norm": 34.77219772338867, | |
| "learning_rate": 2.999014469148629e-05, | |
| "loss": 0.0787, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 5779576.0, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.20833333333333334, | |
| "grad_norm": 83.19795989990234, | |
| "learning_rate": 2.9989412284975254e-05, | |
| "loss": 0.108, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 5838375.0, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.21037581699346405, | |
| "grad_norm": 8.245382308959961, | |
| "learning_rate": 2.99886536399077e-05, | |
| "loss": 0.1021, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 5894235.0, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.21241830065359477, | |
| "grad_norm": 11.434538841247559, | |
| "learning_rate": 2.998786875761161e-05, | |
| "loss": 0.1702, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 5951718.0, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.21446078431372548, | |
| "grad_norm": 41.023590087890625, | |
| "learning_rate": 2.998705763946089e-05, | |
| "loss": 0.1285, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 6006518.0, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.21650326797385622, | |
| "grad_norm": 82.64183044433594, | |
| "learning_rate": 2.99862202868754e-05, | |
| "loss": 0.1554, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 6064226.0, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.21854575163398693, | |
| "grad_norm": 10.80537223815918, | |
| "learning_rate": 2.998535670132089e-05, | |
| "loss": 0.1283, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 6120354.0, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.22058823529411764, | |
| "grad_norm": 50.733726501464844, | |
| "learning_rate": 2.9984466884309042e-05, | |
| "loss": 0.1703, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 6176051.0, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.22263071895424835, | |
| "grad_norm": 74.09884643554688, | |
| "learning_rate": 2.9983550837397458e-05, | |
| "loss": 0.201, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 6233454.0, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.2246732026143791, | |
| "grad_norm": 28.863571166992188, | |
| "learning_rate": 2.9982608562189657e-05, | |
| "loss": 0.1127, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 6287345.0, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.2267156862745098, | |
| "grad_norm": 42.05843734741211, | |
| "learning_rate": 2.9981640060335062e-05, | |
| "loss": 0.1891, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 6342718.0, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.22875816993464052, | |
| "grad_norm": 13.063857078552246, | |
| "learning_rate": 2.9980645333529013e-05, | |
| "loss": 0.0917, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 6397676.0, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.23080065359477125, | |
| "grad_norm": 80.61491394042969, | |
| "learning_rate": 2.997962438351275e-05, | |
| "loss": 0.1587, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 6455785.0, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.23284313725490197, | |
| "grad_norm": 42.99433517456055, | |
| "learning_rate": 2.9978577212073416e-05, | |
| "loss": 0.1338, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 6515158.0, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.23488562091503268, | |
| "grad_norm": 65.25582122802734, | |
| "learning_rate": 2.9977503821044056e-05, | |
| "loss": 0.1077, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 6574915.0, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.2369281045751634, | |
| "grad_norm": 80.2373275756836, | |
| "learning_rate": 2.9976404212303615e-05, | |
| "loss": 0.2923, | |
| "mean_token_accuracy": 0.9, | |
| "num_tokens": 6632790.0, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.23897058823529413, | |
| "grad_norm": 71.71034240722656, | |
| "learning_rate": 2.997527838777693e-05, | |
| "loss": 0.1391, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 6688987.0, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.24101307189542484, | |
| "grad_norm": 48.97968292236328, | |
| "learning_rate": 2.9974126349434714e-05, | |
| "loss": 0.1095, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 6749311.0, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.24305555555555555, | |
| "grad_norm": 51.00339126586914, | |
| "learning_rate": 2.997294809929359e-05, | |
| "loss": 0.1331, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 6804444.0, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.24509803921568626, | |
| "grad_norm": 24.34203338623047, | |
| "learning_rate": 2.9971743639416055e-05, | |
| "loss": 0.1193, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 6861665.0, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.247140522875817, | |
| "grad_norm": 2.4122538566589355, | |
| "learning_rate": 2.9970512971910473e-05, | |
| "loss": 0.0967, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 6916454.0, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.24918300653594772, | |
| "grad_norm": 67.16130828857422, | |
| "learning_rate": 2.9969256098931098e-05, | |
| "loss": 0.2242, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 6973102.0, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.2512254901960784, | |
| "grad_norm": 75.21226501464844, | |
| "learning_rate": 2.9967973022678058e-05, | |
| "loss": 0.1547, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 7029147.0, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.25326797385620914, | |
| "grad_norm": 34.8938102722168, | |
| "learning_rate": 2.9966663745397336e-05, | |
| "loss": 0.1501, | |
| "mean_token_accuracy": 0.9125, | |
| "num_tokens": 7084157.0, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.25531045751633985, | |
| "grad_norm": 4.6602559089660645, | |
| "learning_rate": 2.9965328269380783e-05, | |
| "loss": 0.0633, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 7141213.0, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.25735294117647056, | |
| "grad_norm": 8.57243537902832, | |
| "learning_rate": 2.996396659696612e-05, | |
| "loss": 0.0879, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 7197324.0, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.25939542483660133, | |
| "grad_norm": 7.631030082702637, | |
| "learning_rate": 2.9962578730536918e-05, | |
| "loss": 0.0972, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 7252652.0, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.26143790849673204, | |
| "grad_norm": 9.476561546325684, | |
| "learning_rate": 2.996116467252259e-05, | |
| "loss": 0.0971, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 7309087.0, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.26348039215686275, | |
| "grad_norm": 26.900814056396484, | |
| "learning_rate": 2.9959724425398418e-05, | |
| "loss": 0.0562, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 7366347.0, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.26552287581699346, | |
| "grad_norm": 2.2799110412597656, | |
| "learning_rate": 2.9958257991685507e-05, | |
| "loss": 0.1119, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 7420181.0, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.2675653594771242, | |
| "grad_norm": 2.8141064643859863, | |
| "learning_rate": 2.995676537395081e-05, | |
| "loss": 0.1186, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 7476933.0, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.2696078431372549, | |
| "grad_norm": 111.59835052490234, | |
| "learning_rate": 2.995524657480712e-05, | |
| "loss": 0.2957, | |
| "mean_token_accuracy": 0.9, | |
| "num_tokens": 7534064.0, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.2716503267973856, | |
| "grad_norm": 8.57293701171875, | |
| "learning_rate": 2.9953701596913046e-05, | |
| "loss": 0.1284, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 7591036.0, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.27369281045751637, | |
| "grad_norm": 54.44086456298828, | |
| "learning_rate": 2.995213044297303e-05, | |
| "loss": 0.243, | |
| "mean_token_accuracy": 0.9, | |
| "num_tokens": 7647476.0, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.2757352941176471, | |
| "grad_norm": 6.923019886016846, | |
| "learning_rate": 2.995053311573734e-05, | |
| "loss": 0.0965, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 7702859.0, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 4.539721965789795, | |
| "learning_rate": 2.9948909618002047e-05, | |
| "loss": 0.0476, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 7758913.0, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.2798202614379085, | |
| "grad_norm": 11.451420783996582, | |
| "learning_rate": 2.9947259952609043e-05, | |
| "loss": 0.2583, | |
| "mean_token_accuracy": 0.9125, | |
| "num_tokens": 7816969.0, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.2818627450980392, | |
| "grad_norm": 8.647933006286621, | |
| "learning_rate": 2.994558412244602e-05, | |
| "loss": 0.2105, | |
| "mean_token_accuracy": 0.9125, | |
| "num_tokens": 7874605.0, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.2839052287581699, | |
| "grad_norm": 29.564664840698242, | |
| "learning_rate": 2.9943882130446476e-05, | |
| "loss": 0.3191, | |
| "mean_token_accuracy": 0.9, | |
| "num_tokens": 7931881.0, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.28594771241830064, | |
| "grad_norm": 12.145886421203613, | |
| "learning_rate": 2.9942153979589698e-05, | |
| "loss": 0.1195, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 7990885.0, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.28799019607843135, | |
| "grad_norm": 8.08133602142334, | |
| "learning_rate": 2.994039967290077e-05, | |
| "loss": 0.1301, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 8049368.0, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.2900326797385621, | |
| "grad_norm": 11.652286529541016, | |
| "learning_rate": 2.9938619213450555e-05, | |
| "loss": 0.0771, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 8102454.0, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.2920751633986928, | |
| "grad_norm": 6.557082653045654, | |
| "learning_rate": 2.9936812604355705e-05, | |
| "loss": 0.1911, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 8159049.0, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.29411764705882354, | |
| "grad_norm": 10.887295722961426, | |
| "learning_rate": 2.993497984877863e-05, | |
| "loss": 0.1423, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 8216929.0, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.29616013071895425, | |
| "grad_norm": 54.76478958129883, | |
| "learning_rate": 2.993312094992753e-05, | |
| "loss": 0.1088, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 8273153.0, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.29820261437908496, | |
| "grad_norm": 52.17588806152344, | |
| "learning_rate": 2.993123591105634e-05, | |
| "loss": 0.0945, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 8330380.0, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.3002450980392157, | |
| "grad_norm": 5.6109490394592285, | |
| "learning_rate": 2.9929324735464787e-05, | |
| "loss": 0.1926, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 8385814.0, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.3022875816993464, | |
| "grad_norm": 16.524005889892578, | |
| "learning_rate": 2.9927387426498323e-05, | |
| "loss": 0.0927, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 8444834.0, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.3043300653594771, | |
| "grad_norm": 6.892605304718018, | |
| "learning_rate": 2.9925423987548154e-05, | |
| "loss": 0.1324, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 8501891.0, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.30637254901960786, | |
| "grad_norm": 4.4040937423706055, | |
| "learning_rate": 2.9923434422051224e-05, | |
| "loss": 0.1062, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 8560218.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.3084150326797386, | |
| "grad_norm": 5.095187187194824, | |
| "learning_rate": 2.992141873349022e-05, | |
| "loss": 0.062, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 8618219.0, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.3104575163398693, | |
| "grad_norm": 2.8270270824432373, | |
| "learning_rate": 2.9919376925393545e-05, | |
| "loss": 0.0602, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 8676709.0, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": 4.054996490478516, | |
| "learning_rate": 2.991730900133533e-05, | |
| "loss": 0.0558, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 8733735.0, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.3145424836601307, | |
| "grad_norm": 3.5190207958221436, | |
| "learning_rate": 2.9915214964935423e-05, | |
| "loss": 0.0778, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 8789035.0, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.3165849673202614, | |
| "grad_norm": 28.49373435974121, | |
| "learning_rate": 2.9913094819859368e-05, | |
| "loss": 0.1756, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 8843724.0, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.31862745098039214, | |
| "grad_norm": 4.07816219329834, | |
| "learning_rate": 2.991094856981843e-05, | |
| "loss": 0.1975, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 8899679.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.3206699346405229, | |
| "grad_norm": 56.522804260253906, | |
| "learning_rate": 2.9908776218569556e-05, | |
| "loss": 0.2788, | |
| "mean_token_accuracy": 0.8875, | |
| "num_tokens": 8953257.0, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.3227124183006536, | |
| "grad_norm": 26.952117919921875, | |
| "learning_rate": 2.9906577769915388e-05, | |
| "loss": 0.1065, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 9010519.0, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.3247549019607843, | |
| "grad_norm": 10.19631290435791, | |
| "learning_rate": 2.990435322770425e-05, | |
| "loss": 0.1131, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 9066124.0, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.32679738562091504, | |
| "grad_norm": 12.148405075073242, | |
| "learning_rate": 2.990210259583015e-05, | |
| "loss": 0.1517, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 9123952.0, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.32883986928104575, | |
| "grad_norm": 56.65703582763672, | |
| "learning_rate": 2.9899825878232745e-05, | |
| "loss": 0.1972, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 9181470.0, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.33088235294117646, | |
| "grad_norm": 37.153194427490234, | |
| "learning_rate": 2.9897523078897374e-05, | |
| "loss": 0.1774, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 9237818.0, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.3329248366013072, | |
| "grad_norm": 40.953372955322266, | |
| "learning_rate": 2.9895194201855027e-05, | |
| "loss": 0.1263, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 9295682.0, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.3349673202614379, | |
| "grad_norm": 59.88121032714844, | |
| "learning_rate": 2.989283925118233e-05, | |
| "loss": 0.0928, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 9354328.0, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.33700980392156865, | |
| "grad_norm": 6.743228435516357, | |
| "learning_rate": 2.989045823100157e-05, | |
| "loss": 0.0721, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 9411034.0, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.33905228758169936, | |
| "grad_norm": 10.568706512451172, | |
| "learning_rate": 2.988805114548066e-05, | |
| "loss": 0.2088, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 9469265.0, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.3410947712418301, | |
| "grad_norm": 9.200711250305176, | |
| "learning_rate": 2.988561799883312e-05, | |
| "loss": 0.0948, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 9525575.0, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.3431372549019608, | |
| "grad_norm": 49.522056579589844, | |
| "learning_rate": 2.988315879531812e-05, | |
| "loss": 0.1641, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 9580866.0, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.3451797385620915, | |
| "grad_norm": 58.79249572753906, | |
| "learning_rate": 2.9880673539240432e-05, | |
| "loss": 0.1376, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 9637237.0, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.3472222222222222, | |
| "grad_norm": 0.8544754385948181, | |
| "learning_rate": 2.9878162234950416e-05, | |
| "loss": 0.0512, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 9696029.0, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.3492647058823529, | |
| "grad_norm": 9.062536239624023, | |
| "learning_rate": 2.9875624886844053e-05, | |
| "loss": 0.0224, | |
| "mean_token_accuracy": 1.0, | |
| "num_tokens": 9756714.0, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.35130718954248363, | |
| "grad_norm": 1.6525501012802124, | |
| "learning_rate": 2.9873061499362897e-05, | |
| "loss": 0.0983, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 9813679.0, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.3533496732026144, | |
| "grad_norm": 16.253625869750977, | |
| "learning_rate": 2.9870472076994087e-05, | |
| "loss": 0.0113, | |
| "mean_token_accuracy": 1.0, | |
| "num_tokens": 9870172.0, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.3553921568627451, | |
| "grad_norm": 7.754807949066162, | |
| "learning_rate": 2.986785662427034e-05, | |
| "loss": 0.1001, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 9923651.0, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.3574346405228758, | |
| "grad_norm": 23.580707550048828, | |
| "learning_rate": 2.986521514576993e-05, | |
| "loss": 0.1799, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 9978550.0, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.35947712418300654, | |
| "grad_norm": 28.126249313354492, | |
| "learning_rate": 2.986254764611669e-05, | |
| "loss": 0.1269, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 10033737.0, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.36151960784313725, | |
| "grad_norm": 8.57662582397461, | |
| "learning_rate": 2.9859854129980014e-05, | |
| "loss": 0.0881, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 10089408.0, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.36356209150326796, | |
| "grad_norm": 20.33049774169922, | |
| "learning_rate": 2.9857134602074823e-05, | |
| "loss": 0.0567, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 10144175.0, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.36560457516339867, | |
| "grad_norm": 38.455657958984375, | |
| "learning_rate": 2.9854389067161574e-05, | |
| "loss": 0.2172, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 10201381.0, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.36764705882352944, | |
| "grad_norm": 12.118448257446289, | |
| "learning_rate": 2.985161753004626e-05, | |
| "loss": 0.0978, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 10259759.0, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.36968954248366015, | |
| "grad_norm": 8.415655136108398, | |
| "learning_rate": 2.984881999558037e-05, | |
| "loss": 0.092, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 10315176.0, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.37173202614379086, | |
| "grad_norm": 13.098966598510742, | |
| "learning_rate": 2.9845996468660918e-05, | |
| "loss": 0.0646, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 10371351.0, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.3737745098039216, | |
| "grad_norm": 2.3587121963500977, | |
| "learning_rate": 2.9843146954230413e-05, | |
| "loss": 0.0255, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 10428542.0, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.3758169934640523, | |
| "grad_norm": 29.751482009887695, | |
| "learning_rate": 2.9840271457276846e-05, | |
| "loss": 0.0779, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 10485722.0, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.377859477124183, | |
| "grad_norm": 3.134948253631592, | |
| "learning_rate": 2.9837369982833696e-05, | |
| "loss": 0.0811, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 10543425.0, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.3799019607843137, | |
| "grad_norm": 3.2231831550598145, | |
| "learning_rate": 2.983444253597992e-05, | |
| "loss": 0.1591, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 10599286.0, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.3819444444444444, | |
| "grad_norm": 40.43920135498047, | |
| "learning_rate": 2.983148912183993e-05, | |
| "loss": 0.1189, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 10652880.0, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.3839869281045752, | |
| "grad_norm": 15.982177734375, | |
| "learning_rate": 2.9828509745583596e-05, | |
| "loss": 0.0441, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 10709900.0, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.3860294117647059, | |
| "grad_norm": 0.6476036906242371, | |
| "learning_rate": 2.9825504412426243e-05, | |
| "loss": 0.0878, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 10766631.0, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.3880718954248366, | |
| "grad_norm": 7.733846664428711, | |
| "learning_rate": 2.9822473127628608e-05, | |
| "loss": 0.0935, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 10821577.0, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.3901143790849673, | |
| "grad_norm": 22.098432540893555, | |
| "learning_rate": 2.981941589649689e-05, | |
| "loss": 0.2046, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 10875732.0, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.39215686274509803, | |
| "grad_norm": 71.23796844482422, | |
| "learning_rate": 2.9816332724382673e-05, | |
| "loss": 0.1576, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 10934797.0, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.39419934640522875, | |
| "grad_norm": 22.423683166503906, | |
| "learning_rate": 2.981322361668298e-05, | |
| "loss": 0.1402, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 10994102.0, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.39624183006535946, | |
| "grad_norm": 33.4359016418457, | |
| "learning_rate": 2.9810088578840203e-05, | |
| "loss": 0.1029, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 11047827.0, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.39828431372549017, | |
| "grad_norm": 1.4670796394348145, | |
| "learning_rate": 2.9806927616342157e-05, | |
| "loss": 0.092, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 11102500.0, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.40032679738562094, | |
| "grad_norm": 15.171759605407715, | |
| "learning_rate": 2.9803740734722013e-05, | |
| "loss": 0.142, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 11158732.0, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.40236928104575165, | |
| "grad_norm": 21.65077781677246, | |
| "learning_rate": 2.9800527939558318e-05, | |
| "loss": 0.1096, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 11215262.0, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.40441176470588236, | |
| "grad_norm": 3.6921045780181885, | |
| "learning_rate": 2.979728923647498e-05, | |
| "loss": 0.1026, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 11272403.0, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.40645424836601307, | |
| "grad_norm": 11.374385833740234, | |
| "learning_rate": 2.979402463114127e-05, | |
| "loss": 0.0312, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 11329845.0, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.4084967320261438, | |
| "grad_norm": 3.781118869781494, | |
| "learning_rate": 2.9790734129271782e-05, | |
| "loss": 0.0566, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.4084967320261438, | |
| "eval_loss": 0.13250085711479187, | |
| "eval_mean_token_accuracy": 0.9532766990291263, | |
| "eval_num_tokens": 11389163.0, | |
| "eval_runtime": 809.889, | |
| "eval_samples_per_second": 6.105, | |
| "eval_steps_per_second": 1.526, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.4105392156862745, | |
| "grad_norm": 23.423870086669922, | |
| "learning_rate": 2.978741773662645e-05, | |
| "loss": 0.0692, | |
| "mean_token_accuracy": 0.98125, | |
| "num_tokens": 11447981.0, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.4125816993464052, | |
| "grad_norm": 75.1381607055664, | |
| "learning_rate": 2.9784075459010532e-05, | |
| "loss": 0.1588, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 11504310.0, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.414624183006536, | |
| "grad_norm": 6.686936378479004, | |
| "learning_rate": 2.9780707302274593e-05, | |
| "loss": 0.0471, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 11559179.0, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.4166666666666667, | |
| "grad_norm": 9.171430587768555, | |
| "learning_rate": 2.9777313272314502e-05, | |
| "loss": 0.1511, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 11614394.0, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.4187091503267974, | |
| "grad_norm": 2.0356650352478027, | |
| "learning_rate": 2.9773893375071407e-05, | |
| "loss": 0.1758, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 11672505.0, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.4207516339869281, | |
| "grad_norm": 33.719573974609375, | |
| "learning_rate": 2.9770447616531752e-05, | |
| "loss": 0.2445, | |
| "mean_token_accuracy": 0.8375, | |
| "num_tokens": 11728818.0, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.4227941176470588, | |
| "grad_norm": 67.09674835205078, | |
| "learning_rate": 2.9766976002727242e-05, | |
| "loss": 0.1211, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 11786812.0, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.42483660130718953, | |
| "grad_norm": 37.34446334838867, | |
| "learning_rate": 2.976347853973484e-05, | |
| "loss": 0.0349, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 11847294.0, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.42687908496732024, | |
| "grad_norm": 6.792061805725098, | |
| "learning_rate": 2.9759955233676763e-05, | |
| "loss": 0.1071, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 11901601.0, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.42892156862745096, | |
| "grad_norm": 56.84086608886719, | |
| "learning_rate": 2.975640609072046e-05, | |
| "loss": 0.1653, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 11958101.0, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.4309640522875817, | |
| "grad_norm": 1.3053244352340698, | |
| "learning_rate": 2.97528311170786e-05, | |
| "loss": 0.0804, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 12014876.0, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.43300653594771243, | |
| "grad_norm": 55.08369827270508, | |
| "learning_rate": 2.9749230319009093e-05, | |
| "loss": 0.2595, | |
| "mean_token_accuracy": 0.9, | |
| "num_tokens": 12071583.0, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.43504901960784315, | |
| "grad_norm": 3.933396816253662, | |
| "learning_rate": 2.9745603702815027e-05, | |
| "loss": 0.15, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 12129953.0, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.43709150326797386, | |
| "grad_norm": 4.168801307678223, | |
| "learning_rate": 2.97419512748447e-05, | |
| "loss": 0.0899, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 12187726.0, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.43913398692810457, | |
| "grad_norm": 2.617357015609741, | |
| "learning_rate": 2.9738273041491583e-05, | |
| "loss": 0.0707, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 12245660.0, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.4411764705882353, | |
| "grad_norm": 12.946272850036621, | |
| "learning_rate": 2.9734569009194326e-05, | |
| "loss": 0.1144, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 12302438.0, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.443218954248366, | |
| "grad_norm": 5.600825309753418, | |
| "learning_rate": 2.9730839184436732e-05, | |
| "loss": 0.0796, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 12360044.0, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.4452614379084967, | |
| "grad_norm": 3.2246789932250977, | |
| "learning_rate": 2.972708357374776e-05, | |
| "loss": 0.1272, | |
| "mean_token_accuracy": 0.9125, | |
| "num_tokens": 12413140.0, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.44730392156862747, | |
| "grad_norm": 8.543939590454102, | |
| "learning_rate": 2.9723302183701503e-05, | |
| "loss": 0.05, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 12468166.0, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.4493464052287582, | |
| "grad_norm": 3.576324701309204, | |
| "learning_rate": 2.9719495020917182e-05, | |
| "loss": 0.2156, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 12526394.0, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.4513888888888889, | |
| "grad_norm": 6.754723072052002, | |
| "learning_rate": 2.9715662092059132e-05, | |
| "loss": 0.1043, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 12582328.0, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.4534313725490196, | |
| "grad_norm": 19.64958381652832, | |
| "learning_rate": 2.9711803403836792e-05, | |
| "loss": 0.0798, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 12641212.0, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.4554738562091503, | |
| "grad_norm": 37.779457092285156, | |
| "learning_rate": 2.9707918963004687e-05, | |
| "loss": 0.1011, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 12700045.0, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.45751633986928103, | |
| "grad_norm": 6.258566379547119, | |
| "learning_rate": 2.9704008776362424e-05, | |
| "loss": 0.0552, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 12758041.0, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.45955882352941174, | |
| "grad_norm": 14.63425350189209, | |
| "learning_rate": 2.9700072850754675e-05, | |
| "loss": 0.0894, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 12816223.0, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.4616013071895425, | |
| "grad_norm": 21.317020416259766, | |
| "learning_rate": 2.969611119307118e-05, | |
| "loss": 0.047, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 12872384.0, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.4636437908496732, | |
| "grad_norm": 16.195510864257812, | |
| "learning_rate": 2.9692123810246706e-05, | |
| "loss": 0.0701, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 12927736.0, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.46568627450980393, | |
| "grad_norm": 1.098289966583252, | |
| "learning_rate": 2.9688110709261058e-05, | |
| "loss": 0.1359, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 12984503.0, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.46772875816993464, | |
| "grad_norm": 0.7165175080299377, | |
| "learning_rate": 2.968407189713906e-05, | |
| "loss": 0.0577, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 13042990.0, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.46977124183006536, | |
| "grad_norm": 18.359540939331055, | |
| "learning_rate": 2.968000738095054e-05, | |
| "loss": 0.1674, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 13098065.0, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.47181372549019607, | |
| "grad_norm": 75.84101867675781, | |
| "learning_rate": 2.9675917167810327e-05, | |
| "loss": 0.1336, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 13150937.0, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.4738562091503268, | |
| "grad_norm": 1.8416537046432495, | |
| "learning_rate": 2.9671801264878223e-05, | |
| "loss": 0.241, | |
| "mean_token_accuracy": 0.8875, | |
| "num_tokens": 13208458.0, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.4758986928104575, | |
| "grad_norm": 62.19666290283203, | |
| "learning_rate": 2.966765967935901e-05, | |
| "loss": 0.2419, | |
| "mean_token_accuracy": 0.9, | |
| "num_tokens": 13265425.0, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.47794117647058826, | |
| "grad_norm": 21.84758949279785, | |
| "learning_rate": 2.966349241850241e-05, | |
| "loss": 0.2482, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 13323785.0, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.47998366013071897, | |
| "grad_norm": 29.04265785217285, | |
| "learning_rate": 2.965929948960311e-05, | |
| "loss": 0.1321, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 13379555.0, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.4820261437908497, | |
| "grad_norm": 10.680397987365723, | |
| "learning_rate": 2.965508090000071e-05, | |
| "loss": 0.0633, | |
| "mean_token_accuracy": 1.0, | |
| "num_tokens": 13435161.0, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.4840686274509804, | |
| "grad_norm": 36.50301742553711, | |
| "learning_rate": 2.9650836657079737e-05, | |
| "loss": 0.0689, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 13489618.0, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.4861111111111111, | |
| "grad_norm": 40.39600372314453, | |
| "learning_rate": 2.9646566768269626e-05, | |
| "loss": 0.1448, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 13547326.0, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.4881535947712418, | |
| "grad_norm": 1.955034852027893, | |
| "learning_rate": 2.96422712410447e-05, | |
| "loss": 0.104, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 13606428.0, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.49019607843137253, | |
| "grad_norm": 0.8874222040176392, | |
| "learning_rate": 2.9637950082924156e-05, | |
| "loss": 0.0554, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 13666968.0, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.4922385620915033, | |
| "grad_norm": 14.693424224853516, | |
| "learning_rate": 2.963360330147207e-05, | |
| "loss": 0.095, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 13720520.0, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.494281045751634, | |
| "grad_norm": 12.833786010742188, | |
| "learning_rate": 2.9629230904297358e-05, | |
| "loss": 0.1608, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 13776744.0, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.4963235294117647, | |
| "grad_norm": 63.319339752197266, | |
| "learning_rate": 2.962483289905379e-05, | |
| "loss": 0.0745, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 13837592.0, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.49836601307189543, | |
| "grad_norm": 35.09154510498047, | |
| "learning_rate": 2.9620409293439945e-05, | |
| "loss": 0.1049, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 13891669.0, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.5004084967320261, | |
| "grad_norm": 5.915182590484619, | |
| "learning_rate": 2.9615960095199232e-05, | |
| "loss": 0.1048, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 13949012.0, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.5024509803921569, | |
| "grad_norm": 31.545791625976562, | |
| "learning_rate": 2.9611485312119845e-05, | |
| "loss": 0.0632, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 14010845.0, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.5044934640522876, | |
| "grad_norm": 15.069694519042969, | |
| "learning_rate": 2.960698495203477e-05, | |
| "loss": 0.0591, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 14067632.0, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.5065359477124183, | |
| "grad_norm": 1.3008288145065308, | |
| "learning_rate": 2.960245902282177e-05, | |
| "loss": 0.1095, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 14127463.0, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.508578431372549, | |
| "grad_norm": 52.66246795654297, | |
| "learning_rate": 2.959790753240335e-05, | |
| "loss": 0.118, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 14184653.0, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.5106209150326797, | |
| "grad_norm": 24.912080764770508, | |
| "learning_rate": 2.959333048874678e-05, | |
| "loss": 0.036, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 14241140.0, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.5126633986928104, | |
| "grad_norm": 16.306535720825195, | |
| "learning_rate": 2.958872789986405e-05, | |
| "loss": 0.0454, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 14298657.0, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.5147058823529411, | |
| "grad_norm": 12.53790283203125, | |
| "learning_rate": 2.9584099773811852e-05, | |
| "loss": 0.1929, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 14354028.0, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.516748366013072, | |
| "grad_norm": 17.714296340942383, | |
| "learning_rate": 2.957944611869161e-05, | |
| "loss": 0.1947, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 14412486.0, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.5187908496732027, | |
| "grad_norm": 1.6587852239608765, | |
| "learning_rate": 2.9574766942649408e-05, | |
| "loss": 0.1492, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 14470086.0, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.5208333333333334, | |
| "grad_norm": 14.6918363571167, | |
| "learning_rate": 2.9570062253876028e-05, | |
| "loss": 0.059, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 14525612.0, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.5228758169934641, | |
| "grad_norm": 2.3307137489318848, | |
| "learning_rate": 2.9565332060606892e-05, | |
| "loss": 0.0552, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 14582523.0, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.5249183006535948, | |
| "grad_norm": 39.48810577392578, | |
| "learning_rate": 2.9560576371122072e-05, | |
| "loss": 0.1049, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 14639137.0, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.5269607843137255, | |
| "grad_norm": 9.877236366271973, | |
| "learning_rate": 2.9555795193746277e-05, | |
| "loss": 0.1286, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 14694971.0, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.5290032679738562, | |
| "grad_norm": 37.56391906738281, | |
| "learning_rate": 2.955098853684882e-05, | |
| "loss": 0.0693, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 14752843.0, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.5310457516339869, | |
| "grad_norm": 3.2825965881347656, | |
| "learning_rate": 2.954615640884364e-05, | |
| "loss": 0.1239, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 14809693.0, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.5330882352941176, | |
| "grad_norm": 57.420738220214844, | |
| "learning_rate": 2.9541298818189225e-05, | |
| "loss": 0.1071, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 14867230.0, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.5351307189542484, | |
| "grad_norm": 3.8876490592956543, | |
| "learning_rate": 2.9536415773388662e-05, | |
| "loss": 0.0525, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 14924245.0, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.5371732026143791, | |
| "grad_norm": 6.963588237762451, | |
| "learning_rate": 2.9531507282989587e-05, | |
| "loss": 0.1504, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 14981280.0, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.5392156862745098, | |
| "grad_norm": 39.43886947631836, | |
| "learning_rate": 2.9526573355584183e-05, | |
| "loss": 0.1527, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 15037074.0, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.5412581699346405, | |
| "grad_norm": 1.8368042707443237, | |
| "learning_rate": 2.9521613999809154e-05, | |
| "loss": 0.0845, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 15091776.0, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.5433006535947712, | |
| "grad_norm": 50.89247512817383, | |
| "learning_rate": 2.951662922434571e-05, | |
| "loss": 0.0817, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 15148811.0, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.5453431372549019, | |
| "grad_norm": 22.547344207763672, | |
| "learning_rate": 2.951161903791957e-05, | |
| "loss": 0.0675, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 15205981.0, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.5473856209150327, | |
| "grad_norm": 3.4201929569244385, | |
| "learning_rate": 2.950658344930093e-05, | |
| "loss": 0.1562, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 15263893.0, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.5494281045751634, | |
| "grad_norm": 37.127105712890625, | |
| "learning_rate": 2.950152246730444e-05, | |
| "loss": 0.0918, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 15322264.0, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.5514705882352942, | |
| "grad_norm": 5.4527435302734375, | |
| "learning_rate": 2.949643610078922e-05, | |
| "loss": 0.205, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 15377574.0, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.5535130718954249, | |
| "grad_norm": 2.297999858856201, | |
| "learning_rate": 2.9491324358658814e-05, | |
| "loss": 0.1489, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 15434631.0, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 6.143980026245117, | |
| "learning_rate": 2.9486187249861187e-05, | |
| "loss": 0.1511, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 15494679.0, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.5575980392156863, | |
| "grad_norm": 29.435441970825195, | |
| "learning_rate": 2.9481024783388704e-05, | |
| "loss": 0.1168, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 15549964.0, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.559640522875817, | |
| "grad_norm": 24.83769989013672, | |
| "learning_rate": 2.947583696827813e-05, | |
| "loss": 0.0652, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 15606120.0, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.5616830065359477, | |
| "grad_norm": 2.2236409187316895, | |
| "learning_rate": 2.9470623813610587e-05, | |
| "loss": 0.1016, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 15663723.0, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.5637254901960784, | |
| "grad_norm": 24.802759170532227, | |
| "learning_rate": 2.9465385328511557e-05, | |
| "loss": 0.1143, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 15722744.0, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.5657679738562091, | |
| "grad_norm": 6.42663049697876, | |
| "learning_rate": 2.946012152215087e-05, | |
| "loss": 0.1381, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 15779824.0, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.5678104575163399, | |
| "grad_norm": 108.52812957763672, | |
| "learning_rate": 2.9454832403742675e-05, | |
| "loss": 0.1742, | |
| "mean_token_accuracy": 0.9125, | |
| "num_tokens": 15836869.0, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.5698529411764706, | |
| "grad_norm": 15.961712837219238, | |
| "learning_rate": 2.9449517982545428e-05, | |
| "loss": 0.2117, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 15892923.0, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.5718954248366013, | |
| "grad_norm": 3.1326401233673096, | |
| "learning_rate": 2.9444178267861876e-05, | |
| "loss": 0.0992, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 15949588.0, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.573937908496732, | |
| "grad_norm": 43.093685150146484, | |
| "learning_rate": 2.943881326903905e-05, | |
| "loss": 0.0776, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 16009234.0, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.5759803921568627, | |
| "grad_norm": 22.17841911315918, | |
| "learning_rate": 2.9433422995468223e-05, | |
| "loss": 0.2011, | |
| "mean_token_accuracy": 0.9125, | |
| "num_tokens": 16065431.0, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.5780228758169934, | |
| "grad_norm": 5.208857536315918, | |
| "learning_rate": 2.9428007456584934e-05, | |
| "loss": 0.1021, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 16120367.0, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.5800653594771242, | |
| "grad_norm": 5.491023063659668, | |
| "learning_rate": 2.9422566661868925e-05, | |
| "loss": 0.0938, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 16174385.0, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.5821078431372549, | |
| "grad_norm": 14.880546569824219, | |
| "learning_rate": 2.9417100620844166e-05, | |
| "loss": 0.1201, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 16231439.0, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.5841503267973857, | |
| "grad_norm": 6.449217796325684, | |
| "learning_rate": 2.9411609343078806e-05, | |
| "loss": 0.0399, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 16290113.0, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.5861928104575164, | |
| "grad_norm": 28.87753677368164, | |
| "learning_rate": 2.9406092838185184e-05, | |
| "loss": 0.0968, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 16346721.0, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 2.4041357040405273, | |
| "learning_rate": 2.9400551115819786e-05, | |
| "loss": 0.1239, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 16402738.0, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.5902777777777778, | |
| "grad_norm": 7.619312763214111, | |
| "learning_rate": 2.9394984185683248e-05, | |
| "loss": 0.1081, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 16459782.0, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.5923202614379085, | |
| "grad_norm": 1.945746660232544, | |
| "learning_rate": 2.938939205752033e-05, | |
| "loss": 0.1147, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 16518655.0, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.5943627450980392, | |
| "grad_norm": 24.229825973510742, | |
| "learning_rate": 2.9383774741119894e-05, | |
| "loss": 0.1337, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 16574774.0, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.5964052287581699, | |
| "grad_norm": 0.2752137780189514, | |
| "learning_rate": 2.93781322463149e-05, | |
| "loss": 0.0921, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 16630538.0, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.5984477124183006, | |
| "grad_norm": 51.32651901245117, | |
| "learning_rate": 2.9372464582982388e-05, | |
| "loss": 0.2974, | |
| "mean_token_accuracy": 0.9, | |
| "num_tokens": 16689710.0, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.6004901960784313, | |
| "grad_norm": 41.40073776245117, | |
| "learning_rate": 2.9366771761043442e-05, | |
| "loss": 0.1256, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 16743859.0, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.6025326797385621, | |
| "grad_norm": 1.7411084175109863, | |
| "learning_rate": 2.9361053790463192e-05, | |
| "loss": 0.1034, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 16798426.0, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.6045751633986928, | |
| "grad_norm": 43.97066879272461, | |
| "learning_rate": 2.935531068125079e-05, | |
| "loss": 0.1272, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 16853125.0, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.6066176470588235, | |
| "grad_norm": 4.123895645141602, | |
| "learning_rate": 2.934954244345939e-05, | |
| "loss": 0.0484, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 16910964.0, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.6086601307189542, | |
| "grad_norm": 1.6967579126358032, | |
| "learning_rate": 2.9343749087186134e-05, | |
| "loss": 0.035, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 16967668.0, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.610702614379085, | |
| "grad_norm": 1.5913289785385132, | |
| "learning_rate": 2.9337930622572138e-05, | |
| "loss": 0.0664, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 17026588.0, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.6127450980392157, | |
| "grad_norm": 7.896902084350586, | |
| "learning_rate": 2.9332087059802462e-05, | |
| "loss": 0.131, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.6127450980392157, | |
| "eval_loss": 0.10813894122838974, | |
| "eval_mean_token_accuracy": 0.9591423948220065, | |
| "eval_num_tokens": 17085192.0, | |
| "eval_runtime": 809.7899, | |
| "eval_samples_per_second": 6.105, | |
| "eval_steps_per_second": 1.526, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.6147875816993464, | |
| "grad_norm": 26.613706588745117, | |
| "learning_rate": 2.9326218409106102e-05, | |
| "loss": 0.108, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 17142374.0, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.6168300653594772, | |
| "grad_norm": 5.8097825050354, | |
| "learning_rate": 2.9320324680755975e-05, | |
| "loss": 0.0726, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 17197816.0, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.6188725490196079, | |
| "grad_norm": 23.257431030273438, | |
| "learning_rate": 2.9314405885068893e-05, | |
| "loss": 0.1037, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 17253708.0, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.6209150326797386, | |
| "grad_norm": 42.658084869384766, | |
| "learning_rate": 2.930846203240553e-05, | |
| "loss": 0.0614, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 17312227.0, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.6229575163398693, | |
| "grad_norm": 1.2262073755264282, | |
| "learning_rate": 2.930249313317046e-05, | |
| "loss": 0.0522, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 17370352.0, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 45.38578796386719, | |
| "learning_rate": 2.9296499197812067e-05, | |
| "loss": 0.1835, | |
| "mean_token_accuracy": 0.9125, | |
| "num_tokens": 17421529.0, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.6270424836601307, | |
| "grad_norm": 43.8832893371582, | |
| "learning_rate": 2.9290480236822564e-05, | |
| "loss": 0.1849, | |
| "mean_token_accuracy": 0.9125, | |
| "num_tokens": 17478183.0, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.6290849673202614, | |
| "grad_norm": 3.535942316055298, | |
| "learning_rate": 2.928443626073799e-05, | |
| "loss": 0.1372, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 17536881.0, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.6311274509803921, | |
| "grad_norm": 63.15715026855469, | |
| "learning_rate": 2.9278367280138157e-05, | |
| "loss": 0.22, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 17596476.0, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.6331699346405228, | |
| "grad_norm": 29.677549362182617, | |
| "learning_rate": 2.9272273305646645e-05, | |
| "loss": 0.1537, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 17655173.0, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.6352124183006536, | |
| "grad_norm": 8.397191047668457, | |
| "learning_rate": 2.9266154347930793e-05, | |
| "loss": 0.1305, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 17713776.0, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 0.6372549019607843, | |
| "grad_norm": 1.2498701810836792, | |
| "learning_rate": 2.926001041770167e-05, | |
| "loss": 0.0891, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 17773799.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.639297385620915, | |
| "grad_norm": 4.703813552856445, | |
| "learning_rate": 2.9253841525714055e-05, | |
| "loss": 0.0761, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 17830772.0, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 0.6413398692810458, | |
| "grad_norm": 7.442814826965332, | |
| "learning_rate": 2.9247647682766428e-05, | |
| "loss": 0.0466, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 17889145.0, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.6433823529411765, | |
| "grad_norm": 24.524503707885742, | |
| "learning_rate": 2.924142889970094e-05, | |
| "loss": 0.1878, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 17944180.0, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.6454248366013072, | |
| "grad_norm": 4.501238822937012, | |
| "learning_rate": 2.9235185187403397e-05, | |
| "loss": 0.1226, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 18001420.0, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.6474673202614379, | |
| "grad_norm": 14.595519065856934, | |
| "learning_rate": 2.922891655680326e-05, | |
| "loss": 0.1128, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 18057686.0, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 0.6495098039215687, | |
| "grad_norm": 9.303730964660645, | |
| "learning_rate": 2.9222623018873578e-05, | |
| "loss": 0.2113, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 18112945.0, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.6515522875816994, | |
| "grad_norm": 5.784854412078857, | |
| "learning_rate": 2.9216304584631032e-05, | |
| "loss": 0.0989, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 18168835.0, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 0.6535947712418301, | |
| "grad_norm": 4.39665412902832, | |
| "learning_rate": 2.9209961265135858e-05, | |
| "loss": 0.0725, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 18225072.0, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.6556372549019608, | |
| "grad_norm": 0.7640413641929626, | |
| "learning_rate": 2.9203593071491865e-05, | |
| "loss": 0.0652, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 18284595.0, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 0.6576797385620915, | |
| "grad_norm": 1.6449602842330933, | |
| "learning_rate": 2.919720001484641e-05, | |
| "loss": 0.0366, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 18343202.0, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.6597222222222222, | |
| "grad_norm": 49.60608673095703, | |
| "learning_rate": 2.9190782106390356e-05, | |
| "loss": 0.1384, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 18403794.0, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 0.6617647058823529, | |
| "grad_norm": 1.3005566596984863, | |
| "learning_rate": 2.918433935735808e-05, | |
| "loss": 0.1473, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 18463123.0, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.6638071895424836, | |
| "grad_norm": 42.28525924682617, | |
| "learning_rate": 2.917787177902743e-05, | |
| "loss": 0.1027, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 18519828.0, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.6658496732026143, | |
| "grad_norm": 11.0750732421875, | |
| "learning_rate": 2.917137938271974e-05, | |
| "loss": 0.1378, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 18575487.0, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.6678921568627451, | |
| "grad_norm": 1.85812509059906, | |
| "learning_rate": 2.916486217979976e-05, | |
| "loss": 0.0961, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 18629296.0, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 0.6699346405228758, | |
| "grad_norm": 21.419336318969727, | |
| "learning_rate": 2.9158320181675682e-05, | |
| "loss": 0.0753, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 18685648.0, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.6719771241830066, | |
| "grad_norm": 9.502741813659668, | |
| "learning_rate": 2.9151753399799096e-05, | |
| "loss": 0.1725, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 18741021.0, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 0.6740196078431373, | |
| "grad_norm": 7.341395854949951, | |
| "learning_rate": 2.9145161845664965e-05, | |
| "loss": 0.0706, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 18797935.0, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.676062091503268, | |
| "grad_norm": 32.45710372924805, | |
| "learning_rate": 2.913854553081163e-05, | |
| "loss": 0.1028, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 18853339.0, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 0.6781045751633987, | |
| "grad_norm": 7.8983612060546875, | |
| "learning_rate": 2.9131904466820768e-05, | |
| "loss": 0.0763, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 18910850.0, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.6801470588235294, | |
| "grad_norm": 45.291114807128906, | |
| "learning_rate": 2.9125238665317388e-05, | |
| "loss": 0.1381, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 18967205.0, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 0.6821895424836601, | |
| "grad_norm": 4.030833721160889, | |
| "learning_rate": 2.9118548137969785e-05, | |
| "loss": 0.1124, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 19024723.0, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.6842320261437909, | |
| "grad_norm": 31.683691024780273, | |
| "learning_rate": 2.9111832896489543e-05, | |
| "loss": 0.1299, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 19080872.0, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.6862745098039216, | |
| "grad_norm": 6.684524059295654, | |
| "learning_rate": 2.910509295263151e-05, | |
| "loss": 0.0748, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 19138096.0, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.6883169934640523, | |
| "grad_norm": 9.418529510498047, | |
| "learning_rate": 2.909832831819378e-05, | |
| "loss": 0.0949, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 19194107.0, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 0.690359477124183, | |
| "grad_norm": 9.377076148986816, | |
| "learning_rate": 2.9091539005017655e-05, | |
| "loss": 0.0663, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 19249401.0, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.6924019607843137, | |
| "grad_norm": 3.4610469341278076, | |
| "learning_rate": 2.9084725024987643e-05, | |
| "loss": 0.1706, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 19307775.0, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 0.6944444444444444, | |
| "grad_norm": 7.659508228302002, | |
| "learning_rate": 2.9077886390031428e-05, | |
| "loss": 0.0419, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 19365940.0, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.6964869281045751, | |
| "grad_norm": 9.174589157104492, | |
| "learning_rate": 2.907102311211986e-05, | |
| "loss": 0.112, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 19424137.0, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 0.6985294117647058, | |
| "grad_norm": 41.201385498046875, | |
| "learning_rate": 2.9064135203266912e-05, | |
| "loss": 0.275, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 19482521.0, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.7005718954248366, | |
| "grad_norm": 64.74032592773438, | |
| "learning_rate": 2.905722267552968e-05, | |
| "loss": 0.101, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 19538696.0, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 0.7026143790849673, | |
| "grad_norm": 1.4689619541168213, | |
| "learning_rate": 2.9050285541008364e-05, | |
| "loss": 0.2244, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 19592260.0, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.7046568627450981, | |
| "grad_norm": 9.241630554199219, | |
| "learning_rate": 2.9043323811846216e-05, | |
| "loss": 0.0819, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 19653482.0, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.7066993464052288, | |
| "grad_norm": 11.967839241027832, | |
| "learning_rate": 2.9036337500229564e-05, | |
| "loss": 0.0757, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 19710073.0, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.7087418300653595, | |
| "grad_norm": 43.14140701293945, | |
| "learning_rate": 2.902932661838775e-05, | |
| "loss": 0.1849, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 19769024.0, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 0.7107843137254902, | |
| "grad_norm": 25.586454391479492, | |
| "learning_rate": 2.9022291178593133e-05, | |
| "loss": 0.193, | |
| "mean_token_accuracy": 0.9125, | |
| "num_tokens": 19823102.0, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.7128267973856209, | |
| "grad_norm": 8.806061744689941, | |
| "learning_rate": 2.901523119316105e-05, | |
| "loss": 0.0413, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 19878262.0, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 0.7148692810457516, | |
| "grad_norm": 63.22514724731445, | |
| "learning_rate": 2.9008146674449825e-05, | |
| "loss": 0.1523, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 19935895.0, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.7169117647058824, | |
| "grad_norm": 37.747344970703125, | |
| "learning_rate": 2.9001037634860705e-05, | |
| "loss": 0.1331, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 19992888.0, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 0.7189542483660131, | |
| "grad_norm": 19.918804168701172, | |
| "learning_rate": 2.899390408683788e-05, | |
| "loss": 0.1538, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 20047270.0, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.7209967320261438, | |
| "grad_norm": 7.661492824554443, | |
| "learning_rate": 2.8986746042868416e-05, | |
| "loss": 0.0699, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 20104759.0, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 0.7230392156862745, | |
| "grad_norm": 21.62274169921875, | |
| "learning_rate": 2.8979563515482285e-05, | |
| "loss": 0.0679, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 20163856.0, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.7250816993464052, | |
| "grad_norm": 13.347561836242676, | |
| "learning_rate": 2.89723565172523e-05, | |
| "loss": 0.0644, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 20219840.0, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.7271241830065359, | |
| "grad_norm": 9.253806114196777, | |
| "learning_rate": 2.8965125060794116e-05, | |
| "loss": 0.1051, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 20279903.0, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.7291666666666666, | |
| "grad_norm": 18.545562744140625, | |
| "learning_rate": 2.8957869158766197e-05, | |
| "loss": 0.1434, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 20337053.0, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 0.7312091503267973, | |
| "grad_norm": 10.205347061157227, | |
| "learning_rate": 2.8950588823869805e-05, | |
| "loss": 0.1636, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 20394775.0, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.733251633986928, | |
| "grad_norm": 26.28488540649414, | |
| "learning_rate": 2.8943284068848966e-05, | |
| "loss": 0.1327, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 20453059.0, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 0.7352941176470589, | |
| "grad_norm": 22.38806915283203, | |
| "learning_rate": 2.893595490649046e-05, | |
| "loss": 0.1262, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 20510128.0, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.7373366013071896, | |
| "grad_norm": 8.573931694030762, | |
| "learning_rate": 2.892860134962377e-05, | |
| "loss": 0.1148, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 20572963.0, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 0.7393790849673203, | |
| "grad_norm": 42.20366287231445, | |
| "learning_rate": 2.892122341112111e-05, | |
| "loss": 0.1201, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 20628246.0, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.741421568627451, | |
| "grad_norm": 1.183760643005371, | |
| "learning_rate": 2.8913821103897354e-05, | |
| "loss": 0.2519, | |
| "mean_token_accuracy": 0.9, | |
| "num_tokens": 20685278.0, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 0.7434640522875817, | |
| "grad_norm": 27.19111442565918, | |
| "learning_rate": 2.8906394440910043e-05, | |
| "loss": 0.111, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 20739826.0, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.7455065359477124, | |
| "grad_norm": 9.145739555358887, | |
| "learning_rate": 2.889894343515934e-05, | |
| "loss": 0.1096, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 20798060.0, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.7475490196078431, | |
| "grad_norm": 8.899723052978516, | |
| "learning_rate": 2.8891468099688035e-05, | |
| "loss": 0.0657, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 20856959.0, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.7495915032679739, | |
| "grad_norm": 24.127330780029297, | |
| "learning_rate": 2.8883968447581492e-05, | |
| "loss": 0.0888, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 20913806.0, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 0.7516339869281046, | |
| "grad_norm": 32.30192565917969, | |
| "learning_rate": 2.887644449196765e-05, | |
| "loss": 0.135, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 20971323.0, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.7536764705882353, | |
| "grad_norm": 2.532961368560791, | |
| "learning_rate": 2.8868896246016986e-05, | |
| "loss": 0.08, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 21026791.0, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 0.755718954248366, | |
| "grad_norm": 9.279903411865234, | |
| "learning_rate": 2.8861323722942506e-05, | |
| "loss": 0.1096, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 21083441.0, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.7577614379084967, | |
| "grad_norm": 7.408401012420654, | |
| "learning_rate": 2.885372693599969e-05, | |
| "loss": 0.0907, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 21137596.0, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 0.7598039215686274, | |
| "grad_norm": 15.64964485168457, | |
| "learning_rate": 2.884610589848652e-05, | |
| "loss": 0.0548, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 21190602.0, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.7618464052287581, | |
| "grad_norm": 30.637798309326172, | |
| "learning_rate": 2.8838460623743403e-05, | |
| "loss": 0.1063, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 21245993.0, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 0.7638888888888888, | |
| "grad_norm": 30.2146053314209, | |
| "learning_rate": 2.8830791125153194e-05, | |
| "loss": 0.0738, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 21302519.0, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.7659313725490197, | |
| "grad_norm": 14.198923110961914, | |
| "learning_rate": 2.882309741614113e-05, | |
| "loss": 0.1275, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 21357255.0, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.7679738562091504, | |
| "grad_norm": 10.301222801208496, | |
| "learning_rate": 2.881537951017485e-05, | |
| "loss": 0.0744, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 21413001.0, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.7700163398692811, | |
| "grad_norm": 25.676176071166992, | |
| "learning_rate": 2.8807637420764328e-05, | |
| "loss": 0.0905, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 21470283.0, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 0.7720588235294118, | |
| "grad_norm": 6.281707763671875, | |
| "learning_rate": 2.879987116146188e-05, | |
| "loss": 0.068, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 21529700.0, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.7741013071895425, | |
| "grad_norm": 17.27916145324707, | |
| "learning_rate": 2.8792080745862136e-05, | |
| "loss": 0.183, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 21587863.0, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 0.7761437908496732, | |
| "grad_norm": 10.464910507202148, | |
| "learning_rate": 2.8784266187602e-05, | |
| "loss": 0.1396, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 21647504.0, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.7781862745098039, | |
| "grad_norm": 3.049433708190918, | |
| "learning_rate": 2.8776427500360653e-05, | |
| "loss": 0.1275, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 21702433.0, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 0.7802287581699346, | |
| "grad_norm": 32.31922149658203, | |
| "learning_rate": 2.876856469785949e-05, | |
| "loss": 0.0922, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 21758033.0, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.7822712418300654, | |
| "grad_norm": 16.604930877685547, | |
| "learning_rate": 2.876067779386214e-05, | |
| "loss": 0.0696, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 21813902.0, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 0.7843137254901961, | |
| "grad_norm": 1.068522334098816, | |
| "learning_rate": 2.8752766802174408e-05, | |
| "loss": 0.1075, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 21870750.0, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.7863562091503268, | |
| "grad_norm": 39.15222930908203, | |
| "learning_rate": 2.8744831736644274e-05, | |
| "loss": 0.116, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 21928793.0, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.7883986928104575, | |
| "grad_norm": 16.060745239257812, | |
| "learning_rate": 2.873687261116185e-05, | |
| "loss": 0.064, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 21985748.0, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.7904411764705882, | |
| "grad_norm": 29.47675323486328, | |
| "learning_rate": 2.8728889439659365e-05, | |
| "loss": 0.0992, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 22045078.0, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 0.7924836601307189, | |
| "grad_norm": 49.59507751464844, | |
| "learning_rate": 2.8720882236111148e-05, | |
| "loss": 0.1062, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 22101426.0, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.7945261437908496, | |
| "grad_norm": 2.6633102893829346, | |
| "learning_rate": 2.8712851014533585e-05, | |
| "loss": 0.0555, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 22160445.0, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 0.7965686274509803, | |
| "grad_norm": 0.9626659750938416, | |
| "learning_rate": 2.870479578898512e-05, | |
| "loss": 0.0475, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 22217889.0, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.7986111111111112, | |
| "grad_norm": 53.19972610473633, | |
| "learning_rate": 2.8696716573566188e-05, | |
| "loss": 0.0538, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 22273579.0, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 0.8006535947712419, | |
| "grad_norm": 0.5886871814727783, | |
| "learning_rate": 2.868861338241925e-05, | |
| "loss": 0.1633, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 22331476.0, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.8026960784313726, | |
| "grad_norm": 17.175018310546875, | |
| "learning_rate": 2.8680486229728714e-05, | |
| "loss": 0.1617, | |
| "mean_token_accuracy": 0.9125, | |
| "num_tokens": 22388098.0, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 0.8047385620915033, | |
| "grad_norm": 9.093750953674316, | |
| "learning_rate": 2.8672335129720937e-05, | |
| "loss": 0.0851, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 22445956.0, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.806781045751634, | |
| "grad_norm": 0.5264254212379456, | |
| "learning_rate": 2.86641600966642e-05, | |
| "loss": 0.0651, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 22503455.0, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.8088235294117647, | |
| "grad_norm": 11.952925682067871, | |
| "learning_rate": 2.8655961144868677e-05, | |
| "loss": 0.2378, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 22561539.0, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.8108660130718954, | |
| "grad_norm": 34.196285247802734, | |
| "learning_rate": 2.8647738288686407e-05, | |
| "loss": 0.1101, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 22617371.0, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 0.8129084967320261, | |
| "grad_norm": 6.872988224029541, | |
| "learning_rate": 2.863949154251127e-05, | |
| "loss": 0.1164, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 22675936.0, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.8149509803921569, | |
| "grad_norm": 28.016273498535156, | |
| "learning_rate": 2.8631220920778976e-05, | |
| "loss": 0.13, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 22737270.0, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 0.8169934640522876, | |
| "grad_norm": 6.578229904174805, | |
| "learning_rate": 2.862292643796702e-05, | |
| "loss": 0.0986, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.8169934640522876, | |
| "eval_loss": 0.10079683363437653, | |
| "eval_mean_token_accuracy": 0.9607605177993528, | |
| "eval_num_tokens": 22792620.0, | |
| "eval_runtime": 810.8375, | |
| "eval_samples_per_second": 6.097, | |
| "eval_steps_per_second": 1.524, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.8190359477124183, | |
| "grad_norm": 27.21574592590332, | |
| "learning_rate": 2.8614608108594673e-05, | |
| "loss": 0.0664, | |
| "mean_token_accuracy": 0.98125, | |
| "num_tokens": 22848760.0, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 0.821078431372549, | |
| "grad_norm": 6.78397274017334, | |
| "learning_rate": 2.860626594722293e-05, | |
| "loss": 0.1307, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 22901383.0, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.8231209150326797, | |
| "grad_norm": 26.287321090698242, | |
| "learning_rate": 2.859789996845453e-05, | |
| "loss": 0.1149, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 22962631.0, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 0.8251633986928104, | |
| "grad_norm": 17.195676803588867, | |
| "learning_rate": 2.8589510186933882e-05, | |
| "loss": 0.164, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 23021262.0, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.8272058823529411, | |
| "grad_norm": 10.358476638793945, | |
| "learning_rate": 2.8581096617347077e-05, | |
| "loss": 0.0457, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 23077066.0, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.829248366013072, | |
| "grad_norm": 48.052085876464844, | |
| "learning_rate": 2.857265927442183e-05, | |
| "loss": 0.131, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 23133529.0, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.8312908496732027, | |
| "grad_norm": 29.905176162719727, | |
| "learning_rate": 2.856419817292748e-05, | |
| "loss": 0.1316, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 23191509.0, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 31.776182174682617, | |
| "learning_rate": 2.855571332767496e-05, | |
| "loss": 0.121, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 23248041.0, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.8353758169934641, | |
| "grad_norm": 2.2471940517425537, | |
| "learning_rate": 2.854720475351676e-05, | |
| "loss": 0.0707, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 23303443.0, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 0.8374183006535948, | |
| "grad_norm": 16.62605857849121, | |
| "learning_rate": 2.8538672465346896e-05, | |
| "loss": 0.0419, | |
| "mean_token_accuracy": 1.0, | |
| "num_tokens": 23356887.0, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.8394607843137255, | |
| "grad_norm": 0.5404797196388245, | |
| "learning_rate": 2.8530116478100917e-05, | |
| "loss": 0.1054, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 23409571.0, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 0.8415032679738562, | |
| "grad_norm": 3.866452932357788, | |
| "learning_rate": 2.8521536806755836e-05, | |
| "loss": 0.1208, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 23465224.0, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.8435457516339869, | |
| "grad_norm": 21.41689109802246, | |
| "learning_rate": 2.8512933466330143e-05, | |
| "loss": 0.034, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 23526042.0, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 0.8455882352941176, | |
| "grad_norm": 11.106511116027832, | |
| "learning_rate": 2.850430647188374e-05, | |
| "loss": 0.0646, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 23583180.0, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.8476307189542484, | |
| "grad_norm": 7.460954189300537, | |
| "learning_rate": 2.849565583851795e-05, | |
| "loss": 0.1256, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 23640539.0, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.8496732026143791, | |
| "grad_norm": 24.152311325073242, | |
| "learning_rate": 2.8486981581375468e-05, | |
| "loss": 0.1679, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 23697670.0, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.8517156862745098, | |
| "grad_norm": 14.378288269042969, | |
| "learning_rate": 2.847828371564035e-05, | |
| "loss": 0.0843, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 23756071.0, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 0.8537581699346405, | |
| "grad_norm": 3.5071709156036377, | |
| "learning_rate": 2.8469562256537967e-05, | |
| "loss": 0.0848, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 23812091.0, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.8558006535947712, | |
| "grad_norm": 2.0785250663757324, | |
| "learning_rate": 2.8460817219334994e-05, | |
| "loss": 0.1227, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 23868936.0, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 0.8578431372549019, | |
| "grad_norm": 25.34217071533203, | |
| "learning_rate": 2.8452048619339387e-05, | |
| "loss": 0.2303, | |
| "mean_token_accuracy": 0.875, | |
| "num_tokens": 23918707.0, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.8598856209150327, | |
| "grad_norm": 14.897515296936035, | |
| "learning_rate": 2.844325647190033e-05, | |
| "loss": 0.1036, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 23977510.0, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 0.8619281045751634, | |
| "grad_norm": 5.785155773162842, | |
| "learning_rate": 2.843444079240824e-05, | |
| "loss": 0.054, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 24035738.0, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.8639705882352942, | |
| "grad_norm": 24.463634490966797, | |
| "learning_rate": 2.842560159629473e-05, | |
| "loss": 0.1316, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 24093848.0, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 0.8660130718954249, | |
| "grad_norm": 15.784440994262695, | |
| "learning_rate": 2.8416738899032563e-05, | |
| "loss": 0.1594, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 24153372.0, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.8680555555555556, | |
| "grad_norm": 7.084226608276367, | |
| "learning_rate": 2.8407852716135652e-05, | |
| "loss": 0.0321, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 24211102.0, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.8700980392156863, | |
| "grad_norm": 5.852084159851074, | |
| "learning_rate": 2.8398943063159016e-05, | |
| "loss": 0.0919, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 24271539.0, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.872140522875817, | |
| "grad_norm": 9.230666160583496, | |
| "learning_rate": 2.839000995569876e-05, | |
| "loss": 0.139, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 24327269.0, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 0.8741830065359477, | |
| "grad_norm": 0.5771356821060181, | |
| "learning_rate": 2.8381053409392043e-05, | |
| "loss": 0.0964, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 24384539.0, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.8762254901960784, | |
| "grad_norm": 1.236478567123413, | |
| "learning_rate": 2.837207343991706e-05, | |
| "loss": 0.1023, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 24440899.0, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 0.8782679738562091, | |
| "grad_norm": 13.615274429321289, | |
| "learning_rate": 2.8363070062992994e-05, | |
| "loss": 0.0877, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 24497902.0, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.8803104575163399, | |
| "grad_norm": 9.115948677062988, | |
| "learning_rate": 2.8354043294380017e-05, | |
| "loss": 0.1171, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 24550190.0, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 0.8823529411764706, | |
| "grad_norm": 22.52690315246582, | |
| "learning_rate": 2.8344993149879232e-05, | |
| "loss": 0.1951, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 24606994.0, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.8843954248366013, | |
| "grad_norm": 6.182473182678223, | |
| "learning_rate": 2.833591964533268e-05, | |
| "loss": 0.0664, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 24664728.0, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 0.886437908496732, | |
| "grad_norm": 12.18122386932373, | |
| "learning_rate": 2.832682279662328e-05, | |
| "loss": 0.0412, | |
| "mean_token_accuracy": 1.0, | |
| "num_tokens": 24719387.0, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.8884803921568627, | |
| "grad_norm": 40.135284423828125, | |
| "learning_rate": 2.831770261967481e-05, | |
| "loss": 0.1624, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 24773982.0, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.8905228758169934, | |
| "grad_norm": 3.5626063346862793, | |
| "learning_rate": 2.83085591304519e-05, | |
| "loss": 0.039, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 24832138.0, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.8925653594771242, | |
| "grad_norm": 20.827966690063477, | |
| "learning_rate": 2.8299392344959972e-05, | |
| "loss": 0.0764, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 24886600.0, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 0.8946078431372549, | |
| "grad_norm": 16.832252502441406, | |
| "learning_rate": 2.8290202279245236e-05, | |
| "loss": 0.1277, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 24939880.0, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.8966503267973857, | |
| "grad_norm": 4.561303615570068, | |
| "learning_rate": 2.8280988949394646e-05, | |
| "loss": 0.2022, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 24995207.0, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 0.8986928104575164, | |
| "grad_norm": 4.674731731414795, | |
| "learning_rate": 2.8271752371535893e-05, | |
| "loss": 0.1197, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 25051596.0, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.9007352941176471, | |
| "grad_norm": 34.2387809753418, | |
| "learning_rate": 2.8262492561837348e-05, | |
| "loss": 0.1182, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 25108110.0, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 0.9027777777777778, | |
| "grad_norm": 20.02591896057129, | |
| "learning_rate": 2.8253209536508054e-05, | |
| "loss": 0.1038, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 25162639.0, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.9048202614379085, | |
| "grad_norm": 17.26310157775879, | |
| "learning_rate": 2.8243903311797697e-05, | |
| "loss": 0.0589, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 25221203.0, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 0.9068627450980392, | |
| "grad_norm": 0.9990586638450623, | |
| "learning_rate": 2.823457390399657e-05, | |
| "loss": 0.0523, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 25277241.0, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.9089052287581699, | |
| "grad_norm": 15.46597671508789, | |
| "learning_rate": 2.8225221329435534e-05, | |
| "loss": 0.116, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 25330685.0, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.9109477124183006, | |
| "grad_norm": 5.425116539001465, | |
| "learning_rate": 2.821584560448603e-05, | |
| "loss": 0.0563, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 25386261.0, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.9129901960784313, | |
| "grad_norm": 51.31437301635742, | |
| "learning_rate": 2.8206446745560003e-05, | |
| "loss": 0.0918, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 25440917.0, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 0.9150326797385621, | |
| "grad_norm": 25.074411392211914, | |
| "learning_rate": 2.8197024769109904e-05, | |
| "loss": 0.0689, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 25502819.0, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.9170751633986928, | |
| "grad_norm": 8.729722023010254, | |
| "learning_rate": 2.818757969162863e-05, | |
| "loss": 0.1998, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 25559542.0, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 0.9191176470588235, | |
| "grad_norm": 30.93926429748535, | |
| "learning_rate": 2.8178111529649543e-05, | |
| "loss": 0.0612, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 25614234.0, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.9211601307189542, | |
| "grad_norm": 8.463629722595215, | |
| "learning_rate": 2.8168620299746405e-05, | |
| "loss": 0.1316, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 25670102.0, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 0.923202614379085, | |
| "grad_norm": 28.561185836791992, | |
| "learning_rate": 2.815910601853334e-05, | |
| "loss": 0.0977, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 25725806.0, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.9252450980392157, | |
| "grad_norm": 74.41934204101562, | |
| "learning_rate": 2.814956870266486e-05, | |
| "loss": 0.1493, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 25781054.0, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 0.9272875816993464, | |
| "grad_norm": 5.218599796295166, | |
| "learning_rate": 2.814000836883575e-05, | |
| "loss": 0.1185, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 25836624.0, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.9293300653594772, | |
| "grad_norm": 10.816539764404297, | |
| "learning_rate": 2.813042503378113e-05, | |
| "loss": 0.0639, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 25891467.0, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.9313725490196079, | |
| "grad_norm": 3.6550261974334717, | |
| "learning_rate": 2.812081871427636e-05, | |
| "loss": 0.1644, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 25946669.0, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.9334150326797386, | |
| "grad_norm": 21.366464614868164, | |
| "learning_rate": 2.811118942713704e-05, | |
| "loss": 0.1076, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 25999942.0, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 0.9354575163398693, | |
| "grad_norm": 9.96731948852539, | |
| "learning_rate": 2.8101537189218978e-05, | |
| "loss": 0.1688, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 26058898.0, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.9375, | |
| "grad_norm": 1.5499980449676514, | |
| "learning_rate": 2.8091862017418146e-05, | |
| "loss": 0.119, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 26114765.0, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 0.9395424836601307, | |
| "grad_norm": 8.301247596740723, | |
| "learning_rate": 2.8082163928670673e-05, | |
| "loss": 0.1048, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 26171699.0, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.9415849673202614, | |
| "grad_norm": 1.0973705053329468, | |
| "learning_rate": 2.8072442939952798e-05, | |
| "loss": 0.0233, | |
| "mean_token_accuracy": 1.0, | |
| "num_tokens": 26228910.0, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 0.9436274509803921, | |
| "grad_norm": 4.965464115142822, | |
| "learning_rate": 2.8062699068280843e-05, | |
| "loss": 0.1248, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 26287012.0, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.9456699346405228, | |
| "grad_norm": 0.6280749440193176, | |
| "learning_rate": 2.8052932330711188e-05, | |
| "loss": 0.0838, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 26341629.0, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 0.9477124183006536, | |
| "grad_norm": 3.6027112007141113, | |
| "learning_rate": 2.804314274434025e-05, | |
| "loss": 0.0746, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 26399931.0, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.9497549019607843, | |
| "grad_norm": 0.5427176356315613, | |
| "learning_rate": 2.803333032630442e-05, | |
| "loss": 0.0438, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 26457745.0, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.951797385620915, | |
| "grad_norm": 17.886228561401367, | |
| "learning_rate": 2.8023495093780073e-05, | |
| "loss": 0.0458, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 26518664.0, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.9538398692810458, | |
| "grad_norm": 15.521048545837402, | |
| "learning_rate": 2.8013637063983517e-05, | |
| "loss": 0.111, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 26575108.0, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 0.9558823529411765, | |
| "grad_norm": 15.815393447875977, | |
| "learning_rate": 2.800375625417096e-05, | |
| "loss": 0.1225, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 26627287.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.9579248366013072, | |
| "grad_norm": 1.1828938722610474, | |
| "learning_rate": 2.799385268163849e-05, | |
| "loss": 0.1259, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 26683477.0, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 0.9599673202614379, | |
| "grad_norm": 36.22898864746094, | |
| "learning_rate": 2.7983926363722042e-05, | |
| "loss": 0.0514, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 26738830.0, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.9620098039215687, | |
| "grad_norm": 0.5772074460983276, | |
| "learning_rate": 2.7973977317797364e-05, | |
| "loss": 0.0904, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 26793334.0, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 0.9640522875816994, | |
| "grad_norm": 3.8460426330566406, | |
| "learning_rate": 2.7964005561279988e-05, | |
| "loss": 0.0986, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 26849690.0, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.9660947712418301, | |
| "grad_norm": 0.71978360414505, | |
| "learning_rate": 2.79540111116252e-05, | |
| "loss": 0.1316, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 26905120.0, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 0.9681372549019608, | |
| "grad_norm": 35.518123626708984, | |
| "learning_rate": 2.7943993986328013e-05, | |
| "loss": 0.0587, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 26961145.0, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.9701797385620915, | |
| "grad_norm": 10.702627182006836, | |
| "learning_rate": 2.7933954202923132e-05, | |
| "loss": 0.0964, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 27022170.0, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.9722222222222222, | |
| "grad_norm": 20.099260330200195, | |
| "learning_rate": 2.7923891778984916e-05, | |
| "loss": 0.045, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 27078838.0, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.9742647058823529, | |
| "grad_norm": 0.15223483741283417, | |
| "learning_rate": 2.791380673212737e-05, | |
| "loss": 0.0569, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 27136528.0, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 0.9763071895424836, | |
| "grad_norm": 0.28072282671928406, | |
| "learning_rate": 2.7903699080004097e-05, | |
| "loss": 0.0422, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 27196852.0, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.9783496732026143, | |
| "grad_norm": 0.7314508557319641, | |
| "learning_rate": 2.7893568840308257e-05, | |
| "loss": 0.0863, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 27252620.0, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 0.9803921568627451, | |
| "grad_norm": 23.794876098632812, | |
| "learning_rate": 2.7883416030772567e-05, | |
| "loss": 0.1441, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 27309054.0, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.9824346405228758, | |
| "grad_norm": 22.492589950561523, | |
| "learning_rate": 2.7873240669169227e-05, | |
| "loss": 0.1654, | |
| "mean_token_accuracy": 0.9, | |
| "num_tokens": 27367303.0, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 0.9844771241830066, | |
| "grad_norm": 3.6776044368743896, | |
| "learning_rate": 2.7863042773309946e-05, | |
| "loss": 0.0793, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 27425851.0, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.9865196078431373, | |
| "grad_norm": 55.13927459716797, | |
| "learning_rate": 2.7852822361045855e-05, | |
| "loss": 0.1436, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 27483689.0, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 0.988562091503268, | |
| "grad_norm": 12.294445037841797, | |
| "learning_rate": 2.7842579450267508e-05, | |
| "loss": 0.0404, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 27543362.0, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.9906045751633987, | |
| "grad_norm": 10.185964584350586, | |
| "learning_rate": 2.7832314058904832e-05, | |
| "loss": 0.1159, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 27601453.0, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.9926470588235294, | |
| "grad_norm": 35.53095626831055, | |
| "learning_rate": 2.7822026204927126e-05, | |
| "loss": 0.186, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 27657056.0, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.9946895424836601, | |
| "grad_norm": 31.025978088378906, | |
| "learning_rate": 2.7811715906342988e-05, | |
| "loss": 0.1291, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 27709083.0, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 0.9967320261437909, | |
| "grad_norm": 13.313756942749023, | |
| "learning_rate": 2.7801383181200322e-05, | |
| "loss": 0.0644, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 27764742.0, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.9987745098039216, | |
| "grad_norm": 28.133087158203125, | |
| "learning_rate": 2.779102804758628e-05, | |
| "loss": 0.1292, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 27826236.0, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 1.0008169934640523, | |
| "grad_norm": 0.21439827978610992, | |
| "learning_rate": 2.778065052362723e-05, | |
| "loss": 0.1475, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 27881489.0, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.002859477124183, | |
| "grad_norm": 0.6955719590187073, | |
| "learning_rate": 2.7770250627488757e-05, | |
| "loss": 0.0586, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 27938461.0, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 1.0049019607843137, | |
| "grad_norm": 0.6030513644218445, | |
| "learning_rate": 2.775982837737559e-05, | |
| "loss": 0.0273, | |
| "mean_token_accuracy": 1.0, | |
| "num_tokens": 27995549.0, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 1.0069444444444444, | |
| "grad_norm": 21.55865478515625, | |
| "learning_rate": 2.7749383791531583e-05, | |
| "loss": 0.0353, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 28053106.0, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 1.0089869281045751, | |
| "grad_norm": 20.435653686523438, | |
| "learning_rate": 2.7738916888239714e-05, | |
| "loss": 0.0829, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 28112527.0, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 1.0110294117647058, | |
| "grad_norm": 2.3663268089294434, | |
| "learning_rate": 2.772842768582201e-05, | |
| "loss": 0.1128, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 28168327.0, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 1.0130718954248366, | |
| "grad_norm": 0.33363038301467896, | |
| "learning_rate": 2.771791620263952e-05, | |
| "loss": 0.0151, | |
| "mean_token_accuracy": 1.0, | |
| "num_tokens": 28227188.0, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 1.0151143790849673, | |
| "grad_norm": 0.7272204756736755, | |
| "learning_rate": 2.7707382457092317e-05, | |
| "loss": 0.1329, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 28285041.0, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 1.017156862745098, | |
| "grad_norm": 25.459142684936523, | |
| "learning_rate": 2.7696826467619436e-05, | |
| "loss": 0.1108, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 28342482.0, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 1.0191993464052287, | |
| "grad_norm": 0.5758032202720642, | |
| "learning_rate": 2.768624825269884e-05, | |
| "loss": 0.0777, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 28399704.0, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 1.0212418300653594, | |
| "grad_norm": 33.58235168457031, | |
| "learning_rate": 2.7675647830847416e-05, | |
| "loss": 0.0552, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.0212418300653594, | |
| "eval_loss": 0.12147825956344604, | |
| "eval_mean_token_accuracy": 0.9550970873786407, | |
| "eval_num_tokens": 28452718.0, | |
| "eval_runtime": 810.6362, | |
| "eval_samples_per_second": 6.099, | |
| "eval_steps_per_second": 1.525, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.0232843137254901, | |
| "grad_norm": 0.7213440537452698, | |
| "learning_rate": 2.7665025220620904e-05, | |
| "loss": 0.0432, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 28506600.0, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 1.0253267973856208, | |
| "grad_norm": 1.436112880706787, | |
| "learning_rate": 2.7654380440613897e-05, | |
| "loss": 0.0388, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 28567677.0, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 1.0273692810457515, | |
| "grad_norm": 0.5829581022262573, | |
| "learning_rate": 2.764371350945979e-05, | |
| "loss": 0.0342, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 28620624.0, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 1.0294117647058822, | |
| "grad_norm": 9.395753860473633, | |
| "learning_rate": 2.7633024445830754e-05, | |
| "loss": 0.0977, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 28679429.0, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 1.0314542483660132, | |
| "grad_norm": 2.6646909713745117, | |
| "learning_rate": 2.7622313268437708e-05, | |
| "loss": 0.0491, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 28736423.0, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 1.033496732026144, | |
| "grad_norm": 52.95351028442383, | |
| "learning_rate": 2.761157999603027e-05, | |
| "loss": 0.1486, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 28790818.0, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 1.0355392156862746, | |
| "grad_norm": 10.442845344543457, | |
| "learning_rate": 2.7600824647396742e-05, | |
| "loss": 0.2205, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 28848705.0, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 1.0375816993464053, | |
| "grad_norm": 1.1016476154327393, | |
| "learning_rate": 2.759004724136406e-05, | |
| "loss": 0.0368, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 28905312.0, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 1.039624183006536, | |
| "grad_norm": 35.47031784057617, | |
| "learning_rate": 2.7579247796797792e-05, | |
| "loss": 0.1852, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 28966131.0, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 1.0416666666666667, | |
| "grad_norm": 11.970342636108398, | |
| "learning_rate": 2.7568426332602062e-05, | |
| "loss": 0.0364, | |
| "mean_token_accuracy": 1.0, | |
| "num_tokens": 29023307.0, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.0437091503267975, | |
| "grad_norm": 9.656310081481934, | |
| "learning_rate": 2.755758286771955e-05, | |
| "loss": 0.1115, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 29084169.0, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 1.0457516339869282, | |
| "grad_norm": 21.730113983154297, | |
| "learning_rate": 2.7546717421131444e-05, | |
| "loss": 0.0516, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 29141150.0, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 1.0477941176470589, | |
| "grad_norm": 0.4055536389350891, | |
| "learning_rate": 2.753583001185741e-05, | |
| "loss": 0.089, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 29197509.0, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 1.0498366013071896, | |
| "grad_norm": 2.3713672161102295, | |
| "learning_rate": 2.7524920658955566e-05, | |
| "loss": 0.0732, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 29256807.0, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 1.0518790849673203, | |
| "grad_norm": 4.789560794830322, | |
| "learning_rate": 2.7513989381522424e-05, | |
| "loss": 0.1311, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 29310481.0, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 1.053921568627451, | |
| "grad_norm": 6.911066055297852, | |
| "learning_rate": 2.7503036198692902e-05, | |
| "loss": 0.0151, | |
| "mean_token_accuracy": 1.0, | |
| "num_tokens": 29367380.0, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 1.0559640522875817, | |
| "grad_norm": 12.303529739379883, | |
| "learning_rate": 2.749206112964024e-05, | |
| "loss": 0.1233, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 29424716.0, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 1.0580065359477124, | |
| "grad_norm": 56.061126708984375, | |
| "learning_rate": 2.7481064193575992e-05, | |
| "loss": 0.1048, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 29485033.0, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 1.0600490196078431, | |
| "grad_norm": 4.965761661529541, | |
| "learning_rate": 2.747004540975e-05, | |
| "loss": 0.0734, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 29543345.0, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 1.0620915032679739, | |
| "grad_norm": 25.311176300048828, | |
| "learning_rate": 2.745900479745034e-05, | |
| "loss": 0.1169, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 29602523.0, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.0641339869281046, | |
| "grad_norm": 1.0157766342163086, | |
| "learning_rate": 2.744794237600331e-05, | |
| "loss": 0.0784, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 29657499.0, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 1.0661764705882353, | |
| "grad_norm": 0.7529796361923218, | |
| "learning_rate": 2.743685816477336e-05, | |
| "loss": 0.1741, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 29714867.0, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 1.068218954248366, | |
| "grad_norm": 14.847443580627441, | |
| "learning_rate": 2.7425752183163116e-05, | |
| "loss": 0.0872, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 29771136.0, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 1.0702614379084967, | |
| "grad_norm": 4.794808387756348, | |
| "learning_rate": 2.7414624450613287e-05, | |
| "loss": 0.0485, | |
| "mean_token_accuracy": 1.0, | |
| "num_tokens": 29831591.0, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 1.0723039215686274, | |
| "grad_norm": 9.673328399658203, | |
| "learning_rate": 2.7403474986602667e-05, | |
| "loss": 0.1768, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 29889578.0, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 1.0743464052287581, | |
| "grad_norm": 12.984060287475586, | |
| "learning_rate": 2.7392303810648088e-05, | |
| "loss": 0.0792, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 29944876.0, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 1.0763888888888888, | |
| "grad_norm": 8.787713050842285, | |
| "learning_rate": 2.7381110942304386e-05, | |
| "loss": 0.0799, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 30004970.0, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 1.0784313725490196, | |
| "grad_norm": 4.43798303604126, | |
| "learning_rate": 2.7369896401164375e-05, | |
| "loss": 0.1244, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 30059502.0, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 1.0804738562091503, | |
| "grad_norm": 8.726995468139648, | |
| "learning_rate": 2.7358660206858795e-05, | |
| "loss": 0.0614, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 30116567.0, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 1.082516339869281, | |
| "grad_norm": 11.700401306152344, | |
| "learning_rate": 2.7347402379056308e-05, | |
| "loss": 0.0554, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 30173288.0, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.0845588235294117, | |
| "grad_norm": 47.74766159057617, | |
| "learning_rate": 2.7336122937463422e-05, | |
| "loss": 0.1471, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 30229568.0, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 1.0866013071895424, | |
| "grad_norm": 32.707061767578125, | |
| "learning_rate": 2.73248219018245e-05, | |
| "loss": 0.0999, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 30287758.0, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 1.088643790849673, | |
| "grad_norm": 49.123748779296875, | |
| "learning_rate": 2.73134992919217e-05, | |
| "loss": 0.1052, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 30344495.0, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 1.0906862745098038, | |
| "grad_norm": 8.104400634765625, | |
| "learning_rate": 2.730215512757493e-05, | |
| "loss": 0.069, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 30400480.0, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 1.0927287581699345, | |
| "grad_norm": 1.7775150537490845, | |
| "learning_rate": 2.7290789428641842e-05, | |
| "loss": 0.0736, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 30457097.0, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 1.0947712418300655, | |
| "grad_norm": 4.328672885894775, | |
| "learning_rate": 2.7279402215017786e-05, | |
| "loss": 0.0635, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 30512232.0, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 1.0968137254901962, | |
| "grad_norm": 5.131505012512207, | |
| "learning_rate": 2.726799350663576e-05, | |
| "loss": 0.084, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 30570004.0, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 1.098856209150327, | |
| "grad_norm": 9.125676155090332, | |
| "learning_rate": 2.725656332346641e-05, | |
| "loss": 0.0319, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 30626019.0, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 1.1008986928104576, | |
| "grad_norm": 27.733264923095703, | |
| "learning_rate": 2.7245111685517948e-05, | |
| "loss": 0.1653, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 30684003.0, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 1.1029411764705883, | |
| "grad_norm": 40.29157638549805, | |
| "learning_rate": 2.7233638612836157e-05, | |
| "loss": 0.1619, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 30740475.0, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.104983660130719, | |
| "grad_norm": 26.46239471435547, | |
| "learning_rate": 2.7222144125504335e-05, | |
| "loss": 0.1894, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 30797110.0, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 1.1070261437908497, | |
| "grad_norm": 0.4306439161300659, | |
| "learning_rate": 2.721062824364327e-05, | |
| "loss": 0.1904, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 30855363.0, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 1.1090686274509804, | |
| "grad_norm": 5.376334190368652, | |
| "learning_rate": 2.71990909874112e-05, | |
| "loss": 0.1235, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 30913759.0, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 41.002925872802734, | |
| "learning_rate": 2.718753237700377e-05, | |
| "loss": 0.1217, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 30968879.0, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 1.1131535947712419, | |
| "grad_norm": 19.044763565063477, | |
| "learning_rate": 2.7175952432654022e-05, | |
| "loss": 0.0869, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 31027343.0, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 1.1151960784313726, | |
| "grad_norm": 14.827445983886719, | |
| "learning_rate": 2.716435117463233e-05, | |
| "loss": 0.0939, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 31084142.0, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 1.1172385620915033, | |
| "grad_norm": 0.45221275091171265, | |
| "learning_rate": 2.7152728623246367e-05, | |
| "loss": 0.0184, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 31139371.0, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 1.119281045751634, | |
| "grad_norm": 56.829654693603516, | |
| "learning_rate": 2.7141084798841102e-05, | |
| "loss": 0.1138, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 31196424.0, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 1.1213235294117647, | |
| "grad_norm": 1.4261711835861206, | |
| "learning_rate": 2.7129419721798726e-05, | |
| "loss": 0.0352, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 31248817.0, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 1.1233660130718954, | |
| "grad_norm": 9.348472595214844, | |
| "learning_rate": 2.7117733412538645e-05, | |
| "loss": 0.0592, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 31307122.0, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.1254084967320261, | |
| "grad_norm": 19.175357818603516, | |
| "learning_rate": 2.7106025891517423e-05, | |
| "loss": 0.0337, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 31366579.0, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 1.1274509803921569, | |
| "grad_norm": 2.8861067295074463, | |
| "learning_rate": 2.709429717922875e-05, | |
| "loss": 0.0854, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 31422939.0, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 1.1294934640522876, | |
| "grad_norm": 0.8002188205718994, | |
| "learning_rate": 2.708254729620342e-05, | |
| "loss": 0.2183, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 31479281.0, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 1.1315359477124183, | |
| "grad_norm": 11.806565284729004, | |
| "learning_rate": 2.7070776263009276e-05, | |
| "loss": 0.0967, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 31538685.0, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 1.133578431372549, | |
| "grad_norm": 7.007813453674316, | |
| "learning_rate": 2.70589841002512e-05, | |
| "loss": 0.0735, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 31593635.0, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 1.1356209150326797, | |
| "grad_norm": 6.60618782043457, | |
| "learning_rate": 2.7047170828571043e-05, | |
| "loss": 0.0449, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 31650413.0, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 1.1376633986928104, | |
| "grad_norm": 27.73697853088379, | |
| "learning_rate": 2.7035336468647616e-05, | |
| "loss": 0.087, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 31704431.0, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 1.1397058823529411, | |
| "grad_norm": 46.30674743652344, | |
| "learning_rate": 2.702348104119664e-05, | |
| "loss": 0.19, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 31761592.0, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 1.1417483660130718, | |
| "grad_norm": 1.0027847290039062, | |
| "learning_rate": 2.7011604566970724e-05, | |
| "loss": 0.1226, | |
| "mean_token_accuracy": 0.9375, | |
| "num_tokens": 31823824.0, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 1.1437908496732025, | |
| "grad_norm": 9.493412971496582, | |
| "learning_rate": 2.6999707066759306e-05, | |
| "loss": 0.072, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 31880251.0, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.1458333333333333, | |
| "grad_norm": 19.38888931274414, | |
| "learning_rate": 2.698778856138864e-05, | |
| "loss": 0.0777, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 31938885.0, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 1.147875816993464, | |
| "grad_norm": 4.605920791625977, | |
| "learning_rate": 2.697584907172174e-05, | |
| "loss": 0.0841, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 31994506.0, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 1.1499183006535947, | |
| "grad_norm": 5.855953693389893, | |
| "learning_rate": 2.696388861865835e-05, | |
| "loss": 0.0663, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 32047010.0, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 1.1519607843137254, | |
| "grad_norm": 10.998538970947266, | |
| "learning_rate": 2.695190722313493e-05, | |
| "loss": 0.0913, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 32104588.0, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 1.1540032679738563, | |
| "grad_norm": 0.5235303640365601, | |
| "learning_rate": 2.6939904906124578e-05, | |
| "loss": 0.0412, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 32162708.0, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 1.1560457516339868, | |
| "grad_norm": 47.070552825927734, | |
| "learning_rate": 2.6927881688637015e-05, | |
| "loss": 0.1056, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 32215570.0, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 1.1580882352941178, | |
| "grad_norm": 0.2211477905511856, | |
| "learning_rate": 2.6915837591718567e-05, | |
| "loss": 0.0836, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 32272951.0, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 1.1601307189542482, | |
| "grad_norm": 3.930335521697998, | |
| "learning_rate": 2.6903772636452095e-05, | |
| "loss": 0.0932, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 32329386.0, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 1.1621732026143792, | |
| "grad_norm": 8.846892356872559, | |
| "learning_rate": 2.689168684395696e-05, | |
| "loss": 0.0411, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 32380952.0, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 1.1642156862745099, | |
| "grad_norm": 0.5302337408065796, | |
| "learning_rate": 2.6879580235389028e-05, | |
| "loss": 0.1016, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 32432891.0, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.1662581699346406, | |
| "grad_norm": 0.2716829776763916, | |
| "learning_rate": 2.6867452831940577e-05, | |
| "loss": 0.062, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 32493441.0, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 1.1683006535947713, | |
| "grad_norm": 1.5299780368804932, | |
| "learning_rate": 2.6855304654840295e-05, | |
| "loss": 0.2147, | |
| "mean_token_accuracy": 0.925, | |
| "num_tokens": 32548623.0, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 1.170343137254902, | |
| "grad_norm": 18.9086971282959, | |
| "learning_rate": 2.6843135725353245e-05, | |
| "loss": 0.0558, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 32607667.0, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 1.1723856209150327, | |
| "grad_norm": 0.5465404391288757, | |
| "learning_rate": 2.683094606478079e-05, | |
| "loss": 0.0717, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 32662635.0, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 1.1744281045751634, | |
| "grad_norm": 13.529513359069824, | |
| "learning_rate": 2.6818735694460606e-05, | |
| "loss": 0.0716, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 32720083.0, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 10.817940711975098, | |
| "learning_rate": 2.6806504635766612e-05, | |
| "loss": 0.0299, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 32779417.0, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 1.1785130718954249, | |
| "grad_norm": 4.209823131561279, | |
| "learning_rate": 2.6794252910108944e-05, | |
| "loss": 0.0597, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 32834578.0, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 1.1805555555555556, | |
| "grad_norm": 5.100384712219238, | |
| "learning_rate": 2.6781980538933905e-05, | |
| "loss": 0.0251, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 32888125.0, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 1.1825980392156863, | |
| "grad_norm": 0.39214545488357544, | |
| "learning_rate": 2.6769687543723954e-05, | |
| "loss": 0.01, | |
| "mean_token_accuracy": 1.0, | |
| "num_tokens": 32945098.0, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 1.184640522875817, | |
| "grad_norm": 0.8744640946388245, | |
| "learning_rate": 2.675737394599764e-05, | |
| "loss": 0.0394, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 33003280.0, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.1866830065359477, | |
| "grad_norm": 0.13359962403774261, | |
| "learning_rate": 2.674503976730958e-05, | |
| "loss": 0.1168, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 33059117.0, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 1.1887254901960784, | |
| "grad_norm": 1.157809853553772, | |
| "learning_rate": 2.673268502925041e-05, | |
| "loss": 0.0695, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 33115168.0, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 1.1907679738562091, | |
| "grad_norm": 0.11052218824625015, | |
| "learning_rate": 2.672030975344677e-05, | |
| "loss": 0.0379, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 33174516.0, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 1.1928104575163399, | |
| "grad_norm": 11.977166175842285, | |
| "learning_rate": 2.6707913961561242e-05, | |
| "loss": 0.0873, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 33233745.0, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 1.1948529411764706, | |
| "grad_norm": 0.7738474011421204, | |
| "learning_rate": 2.6695497675292315e-05, | |
| "loss": 0.2278, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 33292979.0, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 1.1968954248366013, | |
| "grad_norm": 4.716780662536621, | |
| "learning_rate": 2.668306091637436e-05, | |
| "loss": 0.0272, | |
| "mean_token_accuracy": 1.0, | |
| "num_tokens": 33353857.0, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 1.198937908496732, | |
| "grad_norm": 4.672280788421631, | |
| "learning_rate": 2.667060370657759e-05, | |
| "loss": 0.1089, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 33410348.0, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 1.2009803921568627, | |
| "grad_norm": 24.077367782592773, | |
| "learning_rate": 2.6658126067708e-05, | |
| "loss": 0.0807, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 33470174.0, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 1.2030228758169934, | |
| "grad_norm": 27.191696166992188, | |
| "learning_rate": 2.6645628021607364e-05, | |
| "loss": 0.0998, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 33527936.0, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 1.2050653594771241, | |
| "grad_norm": 0.894814133644104, | |
| "learning_rate": 2.663310959015317e-05, | |
| "loss": 0.0683, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 33583538.0, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 1.2071078431372548, | |
| "grad_norm": 3.784269094467163, | |
| "learning_rate": 2.6620570795258585e-05, | |
| "loss": 0.0698, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 33644262.0, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 1.2091503267973855, | |
| "grad_norm": 9.590209007263184, | |
| "learning_rate": 2.660801165887243e-05, | |
| "loss": 0.0742, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 33700913.0, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 1.2111928104575163, | |
| "grad_norm": 18.95368766784668, | |
| "learning_rate": 2.6595432202979127e-05, | |
| "loss": 0.0429, | |
| "mean_token_accuracy": 0.9875, | |
| "num_tokens": 33753913.0, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 1.213235294117647, | |
| "grad_norm": 62.50135803222656, | |
| "learning_rate": 2.6582832449598675e-05, | |
| "loss": 0.1161, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 33807937.0, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 1.2152777777777777, | |
| "grad_norm": 2.0808401107788086, | |
| "learning_rate": 2.6570212420786593e-05, | |
| "loss": 0.0737, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 33866025.0, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 1.2173202614379086, | |
| "grad_norm": 4.220352649688721, | |
| "learning_rate": 2.65575721386339e-05, | |
| "loss": 0.0664, | |
| "mean_token_accuracy": 0.975, | |
| "num_tokens": 33922174.0, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 1.219362745098039, | |
| "grad_norm": 1.307907223701477, | |
| "learning_rate": 2.6544911625267064e-05, | |
| "loss": 0.1023, | |
| "mean_token_accuracy": 0.9625, | |
| "num_tokens": 33976550.0, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 1.22140522875817, | |
| "grad_norm": 42.671051025390625, | |
| "learning_rate": 2.653223090284796e-05, | |
| "loss": 0.0942, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 34037197.0, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 1.2234477124183007, | |
| "grad_norm": 1.9737892150878906, | |
| "learning_rate": 2.651952999357386e-05, | |
| "loss": 0.0879, | |
| "mean_token_accuracy": 0.95, | |
| "num_tokens": 34094442.0, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 1.2254901960784315, | |
| "grad_norm": 0.6595084071159363, | |
| "learning_rate": 2.650680891967735e-05, | |
| "loss": 0.0238, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.2254901960784315, | |
| "eval_loss": 0.10167907178401947, | |
| "eval_mean_token_accuracy": 0.9633899676375405, | |
| "eval_num_tokens": 34150859.0, | |
| "eval_runtime": 810.5733, | |
| "eval_samples_per_second": 6.099, | |
| "eval_steps_per_second": 1.525, | |
| "step": 6000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 24480, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.2618717189581046e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |