| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 371720, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.375e-06, | |
| "loss": 6.8593, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.875e-05, | |
| "loss": 5.3677, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.8125e-05, | |
| "loss": 5.0449, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.75e-05, | |
| "loss": 4.821, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.6874999999999994e-05, | |
| "loss": 4.6456, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5.625e-05, | |
| "loss": 4.5012, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.5625e-05, | |
| "loss": 4.3871, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.5e-05, | |
| "loss": 4.2893, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 8.437499999999999e-05, | |
| "loss": 4.2089, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.374999999999999e-05, | |
| "loss": 4.1406, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00010312499999999999, | |
| "loss": 4.0695, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0001125, | |
| "loss": 4.0107, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00012185624999999998, | |
| "loss": 3.9458, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.000131221875, | |
| "loss": 3.8982, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.000140596875, | |
| "loss": 3.8433, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.000149971875, | |
| "loss": 3.8086, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00015933749999999996, | |
| "loss": 3.7712, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00016871249999999996, | |
| "loss": 3.7431, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.34807019476750434, | |
| "eval_loss": 3.8859505653381348, | |
| "eval_runtime": 152.2662, | |
| "eval_samples_per_second": 380.386, | |
| "eval_steps_per_second": 5.944, | |
| "step": 18586 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.000178078125, | |
| "loss": 3.698, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00018745312499999998, | |
| "loss": 3.6713, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00019681874999999998, | |
| "loss": 3.6498, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00020618437499999995, | |
| "loss": 3.627, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00021555937499999998, | |
| "loss": 3.6114, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00022493437499999998, | |
| "loss": 3.592, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00023430937499999997, | |
| "loss": 3.5844, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00024367499999999997, | |
| "loss": 3.5658, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00025305, | |
| "loss": 3.5562, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.000262425, | |
| "loss": 3.5434, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0002718, | |
| "loss": 3.528, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.000281165625, | |
| "loss": 3.5166, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.000290540625, | |
| "loss": 3.5017, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00029990624999999993, | |
| "loss": 3.4968, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.0002991257506181561, | |
| "loss": 3.4872, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.0002982435535146591, | |
| "loss": 3.4725, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0002973604733309784, | |
| "loss": 3.4562, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00029647739314729777, | |
| "loss": 3.4495, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00029559519604380077, | |
| "loss": 3.4382, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.37586823096932304, | |
| "eval_loss": 3.62882661819458, | |
| "eval_runtime": 152.7372, | |
| "eval_samples_per_second": 379.213, | |
| "eval_steps_per_second": 5.925, | |
| "step": 37172 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0002947129989403037, | |
| "loss": 3.3875, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.00029382991875662304, | |
| "loss": 3.3815, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.0002929468385729424, | |
| "loss": 3.3706, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.0002920637583892617, | |
| "loss": 3.3661, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.00029118067820558104, | |
| "loss": 3.3599, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.00029029848110208404, | |
| "loss": 3.3582, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.00028941540091840335, | |
| "loss": 3.3502, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.00028853320381490636, | |
| "loss": 3.3462, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.00028765012363122567, | |
| "loss": 3.3367, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.00028676880960791236, | |
| "loss": 3.3362, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.0002858857294242317, | |
| "loss": 3.3322, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.00028500264924055104, | |
| "loss": 3.324, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.00028411956905687036, | |
| "loss": 3.3157, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.00028323737195337336, | |
| "loss": 3.3197, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002823542917696927, | |
| "loss": 3.3102, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.000281471211586012, | |
| "loss": 3.3061, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.0002805881314023313, | |
| "loss": 3.3007, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.0002797059342988343, | |
| "loss": 3.2958, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.38913569232753614, | |
| "eval_loss": 3.5019333362579346, | |
| "eval_runtime": 152.7028, | |
| "eval_samples_per_second": 379.299, | |
| "eval_steps_per_second": 5.927, | |
| "step": 55758 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.0002788228541151536, | |
| "loss": 3.2785, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 0.0002779406570116566, | |
| "loss": 3.2343, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.00027705757682797594, | |
| "loss": 3.236, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 0.00027617626280466263, | |
| "loss": 3.2362, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.00027529318262098194, | |
| "loss": 3.2336, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.00027441010243730126, | |
| "loss": 3.2288, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 0.00027352702225362063, | |
| "loss": 3.2309, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 0.00027264394206993995, | |
| "loss": 3.2278, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 0.00027176174496644295, | |
| "loss": 3.2271, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 0.00027087954786294595, | |
| "loss": 3.2284, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 0.00026999646767926526, | |
| "loss": 3.2305, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 0.0002691133874955846, | |
| "loss": 3.2264, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 0.0002682303073119039, | |
| "loss": 3.2214, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 0.0002673472271282232, | |
| "loss": 3.2197, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 0.0002664650300247262, | |
| "loss": 3.2127, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 0.0002655828329212292, | |
| "loss": 3.2139, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 0.00026469975273754853, | |
| "loss": 3.2105, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.00026381667255386785, | |
| "loss": 3.2163, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 0.00026293359237018716, | |
| "loss": 3.2055, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3957415434142357, | |
| "eval_loss": 3.4540581703186035, | |
| "eval_runtime": 152.4456, | |
| "eval_samples_per_second": 379.939, | |
| "eval_steps_per_second": 5.937, | |
| "step": 74344 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 0.0002620505121865065, | |
| "loss": 3.1626, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.00026116831508300953, | |
| "loss": 3.144, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 0.00026028523489932885, | |
| "loss": 3.1517, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 0.00025940215471564816, | |
| "loss": 3.15, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 0.0002585190745319675, | |
| "loss": 3.1589, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 0.0002576368774284705, | |
| "loss": 3.1527, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 0.0002567546803249735, | |
| "loss": 3.1576, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 0.0002558716001412928, | |
| "loss": 3.152, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 0.0002549885199576121, | |
| "loss": 3.1581, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 0.0002541063228541151, | |
| "loss": 3.1541, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 0.0002532232426704345, | |
| "loss": 3.1546, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 0.0002523401624867538, | |
| "loss": 3.1533, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 0.0002514570823030731, | |
| "loss": 3.1549, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 0.00025057576827975975, | |
| "loss": 3.152, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 0.0002496926880960791, | |
| "loss": 3.1516, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 0.00024880960791239844, | |
| "loss": 3.1563, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 0.00024792652772871775, | |
| "loss": 3.1519, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 0.00024704433062522075, | |
| "loss": 3.1533, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.40060643151965947, | |
| "eval_loss": 3.402815103530884, | |
| "eval_runtime": 152.6189, | |
| "eval_samples_per_second": 379.507, | |
| "eval_steps_per_second": 5.93, | |
| "step": 92930 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.00024616125044154007, | |
| "loss": 3.1452, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 0.0002452781702578594, | |
| "loss": 3.0832, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 0.0002443959731543624, | |
| "loss": 3.0868, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 0.00024351289297068173, | |
| "loss": 3.092, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 0.00024262981278700104, | |
| "loss": 3.0954, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 0.00024174761568350402, | |
| "loss": 3.098, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 0.00024086541858000705, | |
| "loss": 3.1, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 0.00023998233839632636, | |
| "loss": 3.1025, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.00023909925821264568, | |
| "loss": 3.0996, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 0.00023821706110914868, | |
| "loss": 3.1028, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 0.00023733398092546802, | |
| "loss": 3.1036, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 0.00023645090074178734, | |
| "loss": 3.1031, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 0.00023556782055810665, | |
| "loss": 3.1023, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 0.00023468474037442597, | |
| "loss": 3.1053, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 0.00023380254327092897, | |
| "loss": 3.1094, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 0.00023291946308724831, | |
| "loss": 3.1036, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 0.00023203638290356763, | |
| "loss": 3.1038, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 0.00023115418580007063, | |
| "loss": 3.1039, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 0.00023027110561638995, | |
| "loss": 3.1056, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.40350113936840293, | |
| "eval_loss": 3.380485773086548, | |
| "eval_runtime": 152.853, | |
| "eval_samples_per_second": 378.926, | |
| "eval_steps_per_second": 5.921, | |
| "step": 111516 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 0.00022938802543270926, | |
| "loss": 3.0752, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 0.0002285058283292123, | |
| "loss": 3.034, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 0.00022762363122571526, | |
| "loss": 3.0444, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 0.00022674055104203458, | |
| "loss": 3.0518, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 0.0002258574708583539, | |
| "loss": 3.0495, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 0.00022497527375485692, | |
| "loss": 3.0551, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 0.00022409219357117624, | |
| "loss": 3.0553, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 0.00022320911338749556, | |
| "loss": 3.054, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 0.00022232603320381487, | |
| "loss": 3.0601, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 0.00022144383610031787, | |
| "loss": 3.0595, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 0.00022056075591663722, | |
| "loss": 3.0641, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 0.00021967767573295653, | |
| "loss": 3.0614, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.00021879547862945953, | |
| "loss": 3.0655, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 0.00021791239844577885, | |
| "loss": 3.0667, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 0.00021703020134228188, | |
| "loss": 3.0629, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 0.0002161471211586012, | |
| "loss": 3.0646, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 0.0002152640409749205, | |
| "loss": 3.0681, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 0.00021438096079123983, | |
| "loss": 3.0668, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 0.00021349876368774283, | |
| "loss": 3.0671, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.40417266805683943, | |
| "eval_loss": 3.38333797454834, | |
| "eval_runtime": 152.8266, | |
| "eval_samples_per_second": 378.992, | |
| "eval_steps_per_second": 5.922, | |
| "step": 130102 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 0.00021261656658424583, | |
| "loss": 3.0056, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 0.00021173348640056514, | |
| "loss": 3.004, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 0.00021085128929706814, | |
| "loss": 3.0074, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 0.00020996820911338746, | |
| "loss": 3.0123, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 0.0002090851289297068, | |
| "loss": 3.0156, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 0.0002082029318262098, | |
| "loss": 3.0192, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 0.00020731985164252912, | |
| "loss": 3.0201, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 0.00020643765453903212, | |
| "loss": 3.0221, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 0.00020555457435535144, | |
| "loss": 3.0277, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 0.00020467149417167078, | |
| "loss": 3.0262, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 0.00020378929706817378, | |
| "loss": 3.0283, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 0.0002029062168844931, | |
| "loss": 3.028, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 0.00020202401978099607, | |
| "loss": 3.0256, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 0.00020114093959731544, | |
| "loss": 3.0298, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 0.00020025874249381841, | |
| "loss": 3.0327, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 0.00019937566231013773, | |
| "loss": 3.0332, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 0.00019849258212645705, | |
| "loss": 3.0385, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 0.00019761038502296007, | |
| "loss": 3.0331, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.40691104864888106, | |
| "eval_loss": 3.366875410079956, | |
| "eval_runtime": 152.6213, | |
| "eval_samples_per_second": 379.501, | |
| "eval_steps_per_second": 5.93, | |
| "step": 148688 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 0.00019672818791946308, | |
| "loss": 3.0125, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 0.0001958451077357824, | |
| "loss": 2.9641, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 0.0001949620275521017, | |
| "loss": 2.9757, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 0.00019407894736842102, | |
| "loss": 2.9761, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 0.00019319586718474037, | |
| "loss": 2.978, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 0.00019231367008124337, | |
| "loss": 2.9905, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 0.00019143058989756268, | |
| "loss": 2.9886, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 0.00019054839279406568, | |
| "loss": 2.9935, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 0.00018966531261038503, | |
| "loss": 2.9913, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 0.00018878223242670434, | |
| "loss": 2.9943, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 0.00018790003532320734, | |
| "loss": 2.9973, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 0.00018701695513952666, | |
| "loss": 2.9986, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 0.00018613475803602963, | |
| "loss": 3.0023, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "learning_rate": 0.00018525167785234898, | |
| "loss": 2.9989, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 0.00018436948074885198, | |
| "loss": 3.0, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 0.0001834864005651713, | |
| "loss": 3.0023, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "learning_rate": 0.0001826033203814906, | |
| "loss": 3.0023, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 0.00018172024019780993, | |
| "loss": 3.0039, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 0.00018083804309431295, | |
| "loss": 3.0072, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.408285882043124, | |
| "eval_loss": 3.3615922927856445, | |
| "eval_runtime": 152.6155, | |
| "eval_samples_per_second": 379.516, | |
| "eval_steps_per_second": 5.93, | |
| "step": 167274 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 0.00017995496291063227, | |
| "loss": 2.9528, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 0.00017907276580713527, | |
| "loss": 2.9442, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 0.0001781896856234546, | |
| "loss": 2.9515, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 0.00017730748851995762, | |
| "loss": 2.9502, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 0.00017642440833627693, | |
| "loss": 2.9558, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 0.00017554132815259625, | |
| "loss": 2.9566, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 0.00017465913104909922, | |
| "loss": 2.9635, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 0.0001737760508654186, | |
| "loss": 2.9669, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 0.0001728929706817379, | |
| "loss": 2.967, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 0.00017201165665842457, | |
| "loss": 2.9745, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 0.00017112857647474388, | |
| "loss": 2.9685, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 0.0001702463793712469, | |
| "loss": 2.9699, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 0.00016936329918756623, | |
| "loss": 2.972, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 0.00016848021900388554, | |
| "loss": 2.9706, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 0.00016759713882020486, | |
| "loss": 2.9777, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 0.00016671494171670786, | |
| "loss": 2.9724, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 0.0001658318615330272, | |
| "loss": 2.9779, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 0.0001649496644295302, | |
| "loss": 2.9771, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.4078330234107961, | |
| "eval_loss": 3.3777239322662354, | |
| "eval_runtime": 152.9968, | |
| "eval_samples_per_second": 378.57, | |
| "eval_steps_per_second": 5.915, | |
| "step": 185860 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 0.00016406658424584952, | |
| "loss": 2.9716, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 10.06, | |
| "learning_rate": 0.0001631843871423525, | |
| "loss": 2.9114, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 10.12, | |
| "learning_rate": 0.0001623013069586718, | |
| "loss": 2.9208, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 10.17, | |
| "learning_rate": 0.00016141822677499118, | |
| "loss": 2.9265, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 0.0001605351465913105, | |
| "loss": 2.9286, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 0.00015965294948781347, | |
| "loss": 2.9316, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 10.33, | |
| "learning_rate": 0.00015876986930413278, | |
| "loss": 2.9347, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 10.38, | |
| "learning_rate": 0.0001578876722006358, | |
| "loss": 2.9384, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 10.44, | |
| "learning_rate": 0.00015700459201695513, | |
| "loss": 2.9406, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "learning_rate": 0.00015612239491345813, | |
| "loss": 2.9389, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 0.00015523931472977745, | |
| "loss": 2.944, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "learning_rate": 0.00015435623454609676, | |
| "loss": 2.9508, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 0.0001534731543624161, | |
| "loss": 2.9459, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 0.00015259007417873542, | |
| "loss": 2.9463, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "learning_rate": 0.00015170699399505474, | |
| "loss": 2.9486, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 10.81, | |
| "learning_rate": 0.00015082479689155774, | |
| "loss": 2.9517, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 10.87, | |
| "learning_rate": 0.00014994171670787705, | |
| "loss": 2.9533, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "learning_rate": 0.00014905951960438005, | |
| "loss": 2.9536, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "learning_rate": 0.0001481764394206994, | |
| "loss": 2.9534, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.4088908356084872, | |
| "eval_loss": 3.374073028564453, | |
| "eval_runtime": 152.6907, | |
| "eval_samples_per_second": 379.329, | |
| "eval_steps_per_second": 5.927, | |
| "step": 204446 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 0.00014729335923701871, | |
| "loss": 2.9188, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 11.08, | |
| "learning_rate": 0.00014641116213352171, | |
| "loss": 2.8961, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 11.14, | |
| "learning_rate": 0.00014552808194984103, | |
| "loss": 2.9004, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 11.19, | |
| "learning_rate": 0.00014464588484634403, | |
| "loss": 2.9005, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "learning_rate": 0.00014376280466266335, | |
| "loss": 2.9037, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "learning_rate": 0.00014287972447898266, | |
| "loss": 2.9129, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 11.35, | |
| "learning_rate": 0.000141996644295302, | |
| "loss": 2.9132, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 11.41, | |
| "learning_rate": 0.000141114447191805, | |
| "loss": 2.9156, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 11.46, | |
| "learning_rate": 0.000140232250088308, | |
| "loss": 2.9192, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 11.51, | |
| "learning_rate": 0.00013934916990462732, | |
| "loss": 2.9185, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 11.57, | |
| "learning_rate": 0.00013846608972094667, | |
| "loss": 2.9243, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 11.62, | |
| "learning_rate": 0.00013758300953726598, | |
| "loss": 2.9236, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 11.68, | |
| "learning_rate": 0.00013670081243376898, | |
| "loss": 2.9244, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 11.73, | |
| "learning_rate": 0.0001358177322500883, | |
| "loss": 2.9289, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 11.78, | |
| "learning_rate": 0.00013493465206640762, | |
| "loss": 2.928, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 0.0001340533380430943, | |
| "loss": 2.9268, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 11.89, | |
| "learning_rate": 0.00013317025785941362, | |
| "loss": 2.9329, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 0.00013228717767573293, | |
| "loss": 2.9315, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 0.00013140498057223594, | |
| "loss": 2.9279, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.40917695412429866, | |
| "eval_loss": 3.384521484375, | |
| "eval_runtime": 152.8405, | |
| "eval_samples_per_second": 378.957, | |
| "eval_steps_per_second": 5.921, | |
| "step": 223032 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "learning_rate": 0.00013052190038855528, | |
| "loss": 2.8706, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 12.11, | |
| "learning_rate": 0.0001296388202048746, | |
| "loss": 2.8764, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 0.0001287557400211939, | |
| "loss": 2.8801, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "learning_rate": 0.00012787265983751323, | |
| "loss": 2.8853, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "learning_rate": 0.00012699046273401623, | |
| "loss": 2.8877, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 0.00012610738255033557, | |
| "loss": 2.8905, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 12.37, | |
| "learning_rate": 0.00012522430236665489, | |
| "loss": 2.8928, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 12.43, | |
| "learning_rate": 0.0001243421052631579, | |
| "loss": 2.898, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 0.0001234590250794772, | |
| "loss": 2.8982, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 12.54, | |
| "learning_rate": 0.0001225768279759802, | |
| "loss": 2.8923, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 12.59, | |
| "learning_rate": 0.00012169374779229953, | |
| "loss": 2.9047, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 0.00012081066760861885, | |
| "loss": 2.9063, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 12.7, | |
| "learning_rate": 0.00011992758742493818, | |
| "loss": 2.9029, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 12.75, | |
| "learning_rate": 0.00011904539032144117, | |
| "loss": 2.9057, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 12.81, | |
| "learning_rate": 0.0001181623101377605, | |
| "loss": 2.9073, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "learning_rate": 0.00011727922995407981, | |
| "loss": 2.9081, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "learning_rate": 0.00011639614977039916, | |
| "loss": 2.9086, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 12.97, | |
| "learning_rate": 0.00011551483574708583, | |
| "loss": 2.9063, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.4105062396543199, | |
| "eval_loss": 3.36887264251709, | |
| "eval_runtime": 152.9632, | |
| "eval_samples_per_second": 378.653, | |
| "eval_steps_per_second": 5.916, | |
| "step": 241618 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 0.00011463175556340516, | |
| "loss": 2.8865, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 13.07, | |
| "learning_rate": 0.00011374867537972447, | |
| "loss": 2.8543, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 13.13, | |
| "learning_rate": 0.00011286647827622747, | |
| "loss": 2.8563, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 13.18, | |
| "learning_rate": 0.00011198339809254679, | |
| "loss": 2.8637, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 13.24, | |
| "learning_rate": 0.0001111003179088661, | |
| "loss": 2.866, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 13.29, | |
| "learning_rate": 0.00011021812080536912, | |
| "loss": 2.8713, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 13.34, | |
| "learning_rate": 0.00010933504062168844, | |
| "loss": 2.8737, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "learning_rate": 0.00010845196043800777, | |
| "loss": 2.8684, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 13.45, | |
| "learning_rate": 0.00010756888025432708, | |
| "loss": 2.8772, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "learning_rate": 0.00010668756623101377, | |
| "loss": 2.8758, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 13.56, | |
| "learning_rate": 0.00010580448604733308, | |
| "loss": 2.8799, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 13.61, | |
| "learning_rate": 0.0001049214058636524, | |
| "loss": 2.8829, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 13.67, | |
| "learning_rate": 0.00010403920876015541, | |
| "loss": 2.8794, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 13.72, | |
| "learning_rate": 0.00010315612857647473, | |
| "loss": 2.8887, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 13.77, | |
| "learning_rate": 0.00010227393147297774, | |
| "loss": 2.8846, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 13.83, | |
| "learning_rate": 0.00010139085128929706, | |
| "loss": 2.8851, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 13.88, | |
| "learning_rate": 0.00010050777110561639, | |
| "loss": 2.8858, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 13.94, | |
| "learning_rate": 9.962557400211938e-05, | |
| "loss": 2.8897, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "learning_rate": 9.874249381843871e-05, | |
| "loss": 2.8913, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.4104661333490982, | |
| "eval_loss": 3.371145486831665, | |
| "eval_runtime": 152.7732, | |
| "eval_samples_per_second": 379.124, | |
| "eval_steps_per_second": 5.924, | |
| "step": 260204 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "learning_rate": 9.786029671494171e-05, | |
| "loss": 2.839, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "learning_rate": 9.697721653126104e-05, | |
| "loss": 2.8365, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 14.15, | |
| "learning_rate": 9.609501942776402e-05, | |
| "loss": 2.8441, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 14.2, | |
| "learning_rate": 9.521282232426704e-05, | |
| "loss": 2.8514, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 14.26, | |
| "learning_rate": 9.432974214058636e-05, | |
| "loss": 2.8488, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 14.31, | |
| "learning_rate": 9.344666195690567e-05, | |
| "loss": 2.8537, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 14.37, | |
| "learning_rate": 9.2563581773225e-05, | |
| "loss": 2.8525, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 9.168050158954432e-05, | |
| "loss": 2.8573, | |
| "step": 268000 | |
| }, | |
| { | |
| "epoch": 14.47, | |
| "learning_rate": 9.079830448604733e-05, | |
| "loss": 2.8588, | |
| "step": 269000 | |
| }, | |
| { | |
| "epoch": 14.53, | |
| "learning_rate": 8.991522430236665e-05, | |
| "loss": 2.8604, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 14.58, | |
| "learning_rate": 8.903302719886966e-05, | |
| "loss": 2.8599, | |
| "step": 271000 | |
| }, | |
| { | |
| "epoch": 14.63, | |
| "learning_rate": 8.814994701518898e-05, | |
| "loss": 2.8603, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 14.69, | |
| "learning_rate": 8.726686683150828e-05, | |
| "loss": 2.8633, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 14.74, | |
| "learning_rate": 8.638378664782762e-05, | |
| "loss": 2.8652, | |
| "step": 274000 | |
| }, | |
| { | |
| "epoch": 14.8, | |
| "learning_rate": 8.550247262451431e-05, | |
| "loss": 2.865, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 14.85, | |
| "learning_rate": 8.461939244083362e-05, | |
| "loss": 2.865, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 14.9, | |
| "learning_rate": 8.373719533733661e-05, | |
| "loss": 2.8662, | |
| "step": 277000 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "learning_rate": 8.285411515365594e-05, | |
| "loss": 2.8704, | |
| "step": 278000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.4098972553045123, | |
| "eval_loss": 3.3779125213623047, | |
| "eval_runtime": 152.7549, | |
| "eval_samples_per_second": 379.169, | |
| "eval_steps_per_second": 5.925, | |
| "step": 278790 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 8.197103496997526e-05, | |
| "loss": 2.8583, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 15.07, | |
| "learning_rate": 8.10879547862946e-05, | |
| "loss": 2.8214, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 15.12, | |
| "learning_rate": 8.020575768279759e-05, | |
| "loss": 2.8237, | |
| "step": 281000 | |
| }, | |
| { | |
| "epoch": 15.17, | |
| "learning_rate": 7.932267749911692e-05, | |
| "loss": 2.8222, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 15.23, | |
| "learning_rate": 7.844048039561992e-05, | |
| "loss": 2.8321, | |
| "step": 283000 | |
| }, | |
| { | |
| "epoch": 15.28, | |
| "learning_rate": 7.755740021193923e-05, | |
| "loss": 2.8329, | |
| "step": 284000 | |
| }, | |
| { | |
| "epoch": 15.33, | |
| "learning_rate": 7.667432002825856e-05, | |
| "loss": 2.8337, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 15.39, | |
| "learning_rate": 7.579212292476155e-05, | |
| "loss": 2.8375, | |
| "step": 286000 | |
| }, | |
| { | |
| "epoch": 15.44, | |
| "learning_rate": 7.490992582126457e-05, | |
| "loss": 2.8415, | |
| "step": 287000 | |
| }, | |
| { | |
| "epoch": 15.5, | |
| "learning_rate": 7.40268456375839e-05, | |
| "loss": 2.8366, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 15.55, | |
| "learning_rate": 7.314376545390321e-05, | |
| "loss": 2.8427, | |
| "step": 289000 | |
| }, | |
| { | |
| "epoch": 15.6, | |
| "learning_rate": 7.226068527022253e-05, | |
| "loss": 2.8424, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 15.66, | |
| "learning_rate": 7.137848816672553e-05, | |
| "loss": 2.8453, | |
| "step": 291000 | |
| }, | |
| { | |
| "epoch": 15.71, | |
| "learning_rate": 7.049540798304486e-05, | |
| "loss": 2.8451, | |
| "step": 292000 | |
| }, | |
| { | |
| "epoch": 15.76, | |
| "learning_rate": 6.961321087954786e-05, | |
| "loss": 2.8489, | |
| "step": 293000 | |
| }, | |
| { | |
| "epoch": 15.82, | |
| "learning_rate": 6.873101377605086e-05, | |
| "loss": 2.8442, | |
| "step": 294000 | |
| }, | |
| { | |
| "epoch": 15.87, | |
| "learning_rate": 6.784793359237018e-05, | |
| "loss": 2.844, | |
| "step": 295000 | |
| }, | |
| { | |
| "epoch": 15.93, | |
| "learning_rate": 6.69648534086895e-05, | |
| "loss": 2.8475, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 15.98, | |
| "learning_rate": 6.608177322500882e-05, | |
| "loss": 2.8491, | |
| "step": 297000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.4111809257905712, | |
| "eval_loss": 3.376009464263916, | |
| "eval_runtime": 153.0344, | |
| "eval_samples_per_second": 378.477, | |
| "eval_steps_per_second": 5.914, | |
| "step": 297376 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 6.519957612151182e-05, | |
| "loss": 2.8234, | |
| "step": 298000 | |
| }, | |
| { | |
| "epoch": 16.09, | |
| "learning_rate": 6.431649593783115e-05, | |
| "loss": 2.804, | |
| "step": 299000 | |
| }, | |
| { | |
| "epoch": 16.14, | |
| "learning_rate": 6.343429883433415e-05, | |
| "loss": 2.8093, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 16.19, | |
| "learning_rate": 6.255121865065347e-05, | |
| "loss": 2.8146, | |
| "step": 301000 | |
| }, | |
| { | |
| "epoch": 16.25, | |
| "learning_rate": 6.16681384669728e-05, | |
| "loss": 2.8127, | |
| "step": 302000 | |
| }, | |
| { | |
| "epoch": 16.3, | |
| "learning_rate": 6.07859413634758e-05, | |
| "loss": 2.8193, | |
| "step": 303000 | |
| }, | |
| { | |
| "epoch": 16.36, | |
| "learning_rate": 5.990286117979512e-05, | |
| "loss": 2.8189, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 16.41, | |
| "learning_rate": 5.901978099611444e-05, | |
| "loss": 2.8211, | |
| "step": 305000 | |
| }, | |
| { | |
| "epoch": 16.46, | |
| "learning_rate": 5.813670081243376e-05, | |
| "loss": 2.817, | |
| "step": 306000 | |
| }, | |
| { | |
| "epoch": 16.52, | |
| "learning_rate": 5.725450370893676e-05, | |
| "loss": 2.8202, | |
| "step": 307000 | |
| }, | |
| { | |
| "epoch": 16.57, | |
| "learning_rate": 5.6371423525256084e-05, | |
| "loss": 2.8212, | |
| "step": 308000 | |
| }, | |
| { | |
| "epoch": 16.63, | |
| "learning_rate": 5.5488343341575414e-05, | |
| "loss": 2.8274, | |
| "step": 309000 | |
| }, | |
| { | |
| "epoch": 16.68, | |
| "learning_rate": 5.4606146238078415e-05, | |
| "loss": 2.8263, | |
| "step": 310000 | |
| }, | |
| { | |
| "epoch": 16.73, | |
| "learning_rate": 5.372306605439774e-05, | |
| "loss": 2.8244, | |
| "step": 311000 | |
| }, | |
| { | |
| "epoch": 16.79, | |
| "learning_rate": 5.2839985870717054e-05, | |
| "loss": 2.8305, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 16.84, | |
| "learning_rate": 5.195778876722006e-05, | |
| "loss": 2.8253, | |
| "step": 313000 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "learning_rate": 5.107470858353938e-05, | |
| "loss": 2.831, | |
| "step": 314000 | |
| }, | |
| { | |
| "epoch": 16.95, | |
| "learning_rate": 5.019251148004238e-05, | |
| "loss": 2.83, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.4115711057247888, | |
| "eval_loss": 3.375187397003174, | |
| "eval_runtime": 152.7823, | |
| "eval_samples_per_second": 379.101, | |
| "eval_steps_per_second": 5.923, | |
| "step": 315962 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 4.93094312963617e-05, | |
| "loss": 2.8325, | |
| "step": 316000 | |
| }, | |
| { | |
| "epoch": 17.06, | |
| "learning_rate": 4.842635111268103e-05, | |
| "loss": 2.7924, | |
| "step": 317000 | |
| }, | |
| { | |
| "epoch": 17.11, | |
| "learning_rate": 4.754415400918403e-05, | |
| "loss": 2.793, | |
| "step": 318000 | |
| }, | |
| { | |
| "epoch": 17.16, | |
| "learning_rate": 4.6661073825503354e-05, | |
| "loss": 2.7973, | |
| "step": 319000 | |
| }, | |
| { | |
| "epoch": 17.22, | |
| "learning_rate": 4.5778876722006355e-05, | |
| "loss": 2.7998, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 17.27, | |
| "learning_rate": 4.489579653832568e-05, | |
| "loss": 2.803, | |
| "step": 321000 | |
| }, | |
| { | |
| "epoch": 17.32, | |
| "learning_rate": 4.4012716354644994e-05, | |
| "loss": 2.8033, | |
| "step": 322000 | |
| }, | |
| { | |
| "epoch": 17.38, | |
| "learning_rate": 4.3130519251147995e-05, | |
| "loss": 2.8002, | |
| "step": 323000 | |
| }, | |
| { | |
| "epoch": 17.43, | |
| "learning_rate": 4.224743906746732e-05, | |
| "loss": 2.8042, | |
| "step": 324000 | |
| }, | |
| { | |
| "epoch": 17.49, | |
| "learning_rate": 4.1365241963970325e-05, | |
| "loss": 2.8048, | |
| "step": 325000 | |
| }, | |
| { | |
| "epoch": 17.54, | |
| "learning_rate": 4.048216178028965e-05, | |
| "loss": 2.806, | |
| "step": 326000 | |
| }, | |
| { | |
| "epoch": 17.59, | |
| "learning_rate": 3.959908159660897e-05, | |
| "loss": 2.8035, | |
| "step": 327000 | |
| }, | |
| { | |
| "epoch": 17.65, | |
| "learning_rate": 3.871688449311197e-05, | |
| "loss": 2.8083, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 17.7, | |
| "learning_rate": 3.7833804309431294e-05, | |
| "loss": 2.8089, | |
| "step": 329000 | |
| }, | |
| { | |
| "epoch": 17.76, | |
| "learning_rate": 3.6951607205934295e-05, | |
| "loss": 2.8063, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 17.81, | |
| "learning_rate": 3.6069410102437296e-05, | |
| "loss": 2.8133, | |
| "step": 331000 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "learning_rate": 3.518632991875662e-05, | |
| "loss": 2.807, | |
| "step": 332000 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 3.430324973507594e-05, | |
| "loss": 2.8097, | |
| "step": 333000 | |
| }, | |
| { | |
| "epoch": 17.97, | |
| "learning_rate": 3.3420169551395265e-05, | |
| "loss": 2.8136, | |
| "step": 334000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.41081936442590883, | |
| "eval_loss": 3.3912463188171387, | |
| "eval_runtime": 153.0224, | |
| "eval_samples_per_second": 378.507, | |
| "eval_steps_per_second": 5.914, | |
| "step": 334548 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 3.2537972447898265e-05, | |
| "loss": 2.7965, | |
| "step": 335000 | |
| }, | |
| { | |
| "epoch": 18.08, | |
| "learning_rate": 3.165489226421759e-05, | |
| "loss": 2.7795, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 18.13, | |
| "learning_rate": 3.077181208053691e-05, | |
| "loss": 2.7846, | |
| "step": 337000 | |
| }, | |
| { | |
| "epoch": 18.19, | |
| "learning_rate": 2.9889614977039912e-05, | |
| "loss": 2.7852, | |
| "step": 338000 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 2.9006534793359235e-05, | |
| "loss": 2.7818, | |
| "step": 339000 | |
| }, | |
| { | |
| "epoch": 18.29, | |
| "learning_rate": 2.8123454609678557e-05, | |
| "loss": 2.7855, | |
| "step": 340000 | |
| }, | |
| { | |
| "epoch": 18.35, | |
| "learning_rate": 2.724125750618156e-05, | |
| "loss": 2.7881, | |
| "step": 341000 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 2.635817732250088e-05, | |
| "loss": 2.7901, | |
| "step": 342000 | |
| }, | |
| { | |
| "epoch": 18.45, | |
| "learning_rate": 2.5475097138820204e-05, | |
| "loss": 2.7895, | |
| "step": 343000 | |
| }, | |
| { | |
| "epoch": 18.51, | |
| "learning_rate": 2.4592016955139527e-05, | |
| "loss": 2.787, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 2.3709819851642528e-05, | |
| "loss": 2.7907, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 18.62, | |
| "learning_rate": 2.282762274814553e-05, | |
| "loss": 2.7957, | |
| "step": 346000 | |
| }, | |
| { | |
| "epoch": 18.67, | |
| "learning_rate": 2.194454256446485e-05, | |
| "loss": 2.7935, | |
| "step": 347000 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "learning_rate": 2.1061462380784174e-05, | |
| "loss": 2.794, | |
| "step": 348000 | |
| }, | |
| { | |
| "epoch": 18.78, | |
| "learning_rate": 2.0179265277287175e-05, | |
| "loss": 2.7885, | |
| "step": 349000 | |
| }, | |
| { | |
| "epoch": 18.83, | |
| "learning_rate": 1.9296185093606498e-05, | |
| "loss": 2.7946, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 18.89, | |
| "learning_rate": 1.8413987990109502e-05, | |
| "loss": 2.7905, | |
| "step": 351000 | |
| }, | |
| { | |
| "epoch": 18.94, | |
| "learning_rate": 1.7531790886612503e-05, | |
| "loss": 2.7904, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "learning_rate": 1.6648710702931826e-05, | |
| "loss": 2.7924, | |
| "step": 353000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.41071033170668786, | |
| "eval_loss": 3.3984034061431885, | |
| "eval_runtime": 153.8265, | |
| "eval_samples_per_second": 376.528, | |
| "eval_steps_per_second": 5.883, | |
| "step": 353134 | |
| }, | |
| { | |
| "epoch": 19.05, | |
| "learning_rate": 1.5765630519251145e-05, | |
| "loss": 2.7766, | |
| "step": 354000 | |
| }, | |
| { | |
| "epoch": 19.1, | |
| "learning_rate": 1.4882550335570468e-05, | |
| "loss": 2.7713, | |
| "step": 355000 | |
| }, | |
| { | |
| "epoch": 19.15, | |
| "learning_rate": 1.4000353232073472e-05, | |
| "loss": 2.7724, | |
| "step": 356000 | |
| }, | |
| { | |
| "epoch": 19.21, | |
| "learning_rate": 1.3117273048392793e-05, | |
| "loss": 2.7711, | |
| "step": 357000 | |
| }, | |
| { | |
| "epoch": 19.26, | |
| "learning_rate": 1.2234192864712116e-05, | |
| "loss": 2.7774, | |
| "step": 358000 | |
| }, | |
| { | |
| "epoch": 19.32, | |
| "learning_rate": 1.1351995761215117e-05, | |
| "loss": 2.777, | |
| "step": 359000 | |
| }, | |
| { | |
| "epoch": 19.37, | |
| "learning_rate": 1.046891557753444e-05, | |
| "loss": 2.778, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 19.42, | |
| "learning_rate": 9.58583539385376e-06, | |
| "loss": 2.7765, | |
| "step": 361000 | |
| }, | |
| { | |
| "epoch": 19.48, | |
| "learning_rate": 8.703638290356763e-06, | |
| "loss": 2.7765, | |
| "step": 362000 | |
| }, | |
| { | |
| "epoch": 19.53, | |
| "learning_rate": 7.820558106676086e-06, | |
| "loss": 2.7713, | |
| "step": 363000 | |
| }, | |
| { | |
| "epoch": 19.58, | |
| "learning_rate": 6.938361003179088e-06, | |
| "loss": 2.7701, | |
| "step": 364000 | |
| }, | |
| { | |
| "epoch": 19.64, | |
| "learning_rate": 6.05528081949841e-06, | |
| "loss": 2.7758, | |
| "step": 365000 | |
| }, | |
| { | |
| "epoch": 19.69, | |
| "learning_rate": 5.172200635817732e-06, | |
| "loss": 2.7754, | |
| "step": 366000 | |
| }, | |
| { | |
| "epoch": 19.75, | |
| "learning_rate": 4.290003532320734e-06, | |
| "loss": 2.7755, | |
| "step": 367000 | |
| }, | |
| { | |
| "epoch": 19.8, | |
| "learning_rate": 3.406923348640056e-06, | |
| "loss": 2.7752, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 19.85, | |
| "learning_rate": 2.523843164959378e-06, | |
| "loss": 2.7719, | |
| "step": 369000 | |
| }, | |
| { | |
| "epoch": 19.91, | |
| "learning_rate": 1.6407629812787e-06, | |
| "loss": 2.7787, | |
| "step": 370000 | |
| }, | |
| { | |
| "epoch": 19.96, | |
| "learning_rate": 7.576827975980219e-07, | |
| "loss": 2.7792, | |
| "step": 371000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.4106218559881334, | |
| "eval_loss": 3.404461622238159, | |
| "eval_runtime": 153.6422, | |
| "eval_samples_per_second": 376.98, | |
| "eval_steps_per_second": 5.89, | |
| "step": 371720 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 371720, | |
| "total_flos": 1.56614628708864e+18, | |
| "train_loss": 3.0647617085172687, | |
| "train_runtime": 80733.64, | |
| "train_samples_per_second": 147.334, | |
| "train_steps_per_second": 4.604 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 371720, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 5000, | |
| "total_flos": 1.56614628708864e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |