| { | |
| "best_metric": 0.9149749926448956, | |
| "best_model_checkpoint": "trillsson3-ft-keyword-spotting-14/checkpoint-23955", | |
| "epoch": 20.0, | |
| "global_step": 31940, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 8.73512836568566e-06, | |
| "loss": 8.0793, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.812773951158422e-05, | |
| "loss": 7.1754, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2.7520350657482777e-05, | |
| "loss": 5.6723, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.691296180338134e-05, | |
| "loss": 4.1468, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.6305572949279896e-05, | |
| "loss": 3.3576, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 5.5698184095178454e-05, | |
| "loss": 2.955, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.509079524107701e-05, | |
| "loss": 2.7689, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 7.448340638697557e-05, | |
| "loss": 2.5858, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.387601753287413e-05, | |
| "loss": 2.3275, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.326862867877268e-05, | |
| "loss": 2.0771, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00010266123982467126, | |
| "loss": 1.8958, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0001120538509705698, | |
| "loss": 1.6778, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00012144646211646837, | |
| "loss": 1.5346, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00013083907326236693, | |
| "loss": 1.4238, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0001402316844082655, | |
| "loss": 1.2824, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6891732862606649, | |
| "eval_loss": 0.7817752957344055, | |
| "eval_runtime": 152.2428, | |
| "eval_samples_per_second": 44.652, | |
| "eval_steps_per_second": 0.703, | |
| "step": 1597 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00014962429555416404, | |
| "loss": 1.2121, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0001590169067000626, | |
| "loss": 1.1391, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00016840951784596116, | |
| "loss": 1.12, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00017780212899185972, | |
| "loss": 1.053, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0001871947401377583, | |
| "loss": 1.0245, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00019658735128365683, | |
| "loss": 0.9887, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0002059799624295554, | |
| "loss": 0.9671, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00021537257357545395, | |
| "loss": 0.8912, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00022476518472135253, | |
| "loss": 0.9015, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0002341577958672511, | |
| "loss": 0.89, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00024355040701314962, | |
| "loss": 0.8173, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0002529430181590482, | |
| "loss": 0.8338, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00026233562930494674, | |
| "loss": 0.8313, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0002717282404508453, | |
| "loss": 0.8395, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00028112085159674385, | |
| "loss": 0.8036, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00029051346274264244, | |
| "loss": 0.8003, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8734922035892909, | |
| "eval_loss": 0.44425612688064575, | |
| "eval_runtime": 147.8186, | |
| "eval_samples_per_second": 45.989, | |
| "eval_steps_per_second": 0.724, | |
| "step": 3194 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00029990607388854097, | |
| "loss": 0.7951, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.0002989668127739511, | |
| "loss": 0.8114, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.00029792318931329574, | |
| "loss": 0.8343, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.00029687956585264035, | |
| "loss": 0.7617, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.00029583594239198497, | |
| "loss": 0.7779, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.0002947923189313295, | |
| "loss": 0.7512, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.00029374869547067414, | |
| "loss": 0.7962, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.00029270507201001875, | |
| "loss": 0.7134, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.00029166144854936337, | |
| "loss": 0.786, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.000290617825088708, | |
| "loss": 0.7808, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.0002895742016280526, | |
| "loss": 0.7379, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.00028853057816739715, | |
| "loss": 0.7545, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.00028748695470674177, | |
| "loss": 0.7557, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 0.0002864433312460864, | |
| "loss": 0.7633, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.000285399707785431, | |
| "loss": 0.7414, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.0002843560843247756, | |
| "loss": 0.7232, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8833480435422183, | |
| "eval_loss": 0.372787207365036, | |
| "eval_runtime": 148.4355, | |
| "eval_samples_per_second": 45.798, | |
| "eval_steps_per_second": 0.721, | |
| "step": 4791 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.00028331246086412017, | |
| "loss": 0.7661, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 0.00028226883740346484, | |
| "loss": 0.7224, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 0.0002812252139428094, | |
| "loss": 0.7186, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 0.0002801920267167606, | |
| "loss": 0.7151, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 0.00027914840325610516, | |
| "loss": 0.7175, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 0.0002781047797954498, | |
| "loss": 0.6871, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 0.0002770611563347944, | |
| "loss": 0.7446, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 0.000276017532874139, | |
| "loss": 0.7128, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 0.0002749739094134836, | |
| "loss": 0.6896, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 0.0002739302859528282, | |
| "loss": 0.714, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 0.0002728866624921728, | |
| "loss": 0.7478, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 0.0002718430390315174, | |
| "loss": 0.6853, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 0.000270799415570862, | |
| "loss": 0.7165, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 0.0002697557921102066, | |
| "loss": 0.704, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 0.00026871216864955125, | |
| "loss": 0.6954, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 0.0002676685451888958, | |
| "loss": 0.73, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8973227419829362, | |
| "eval_loss": 0.346542090177536, | |
| "eval_runtime": 147.4068, | |
| "eval_samples_per_second": 46.117, | |
| "eval_steps_per_second": 0.726, | |
| "step": 6388 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 0.0002666249217282404, | |
| "loss": 0.7149, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 0.00026558129826758503, | |
| "loss": 0.7107, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 0.00026453767480692965, | |
| "loss": 0.6744, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 0.0002634940513462742, | |
| "loss": 0.727, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 0.0002624504278856189, | |
| "loss": 0.7, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 0.00026140680442496343, | |
| "loss": 0.7239, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 0.00026036318096430805, | |
| "loss": 0.6847, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 0.00025931955750365266, | |
| "loss": 0.7151, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 0.0002582759340429973, | |
| "loss": 0.7228, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 0.0002572427468169484, | |
| "loss": 0.6925, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 0.000256199123356293, | |
| "loss": 0.7064, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 0.00025515549989563765, | |
| "loss": 0.6861, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 0.0002541118764349822, | |
| "loss": 0.7057, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 0.0002530682529743269, | |
| "loss": 0.6811, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 0.00025202462951367144, | |
| "loss": 0.6676, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 0.00025098100605301605, | |
| "loss": 0.7015, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.910856134157105, | |
| "eval_loss": 0.3211327791213989, | |
| "eval_runtime": 150.4771, | |
| "eval_samples_per_second": 45.176, | |
| "eval_steps_per_second": 0.711, | |
| "step": 7985 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 0.00024993738259236067, | |
| "loss": 0.708, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 0.0002488937591317053, | |
| "loss": 0.7372, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 0.00024785013567104984, | |
| "loss": 0.7089, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 0.00024680651221039445, | |
| "loss": 0.6962, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 0.00024576288874973907, | |
| "loss": 0.7209, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 0.0002447192652890837, | |
| "loss": 0.7091, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 0.0002436756418284283, | |
| "loss": 0.6898, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 0.00024263201836777288, | |
| "loss": 0.726, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 0.00024158839490711747, | |
| "loss": 0.682, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 0.0002405447714464621, | |
| "loss": 0.6855, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 0.0002395011479858067, | |
| "loss": 0.7108, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 0.00023845752452515128, | |
| "loss": 0.6945, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 0.00023741390106449592, | |
| "loss": 0.6621, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 0.0002363702776038405, | |
| "loss": 0.7176, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 0.00023532665414318512, | |
| "loss": 0.6824, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 0.00023428303068252974, | |
| "loss": 0.6981, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9080611944689615, | |
| "eval_loss": 0.3200249671936035, | |
| "eval_runtime": 148.3702, | |
| "eval_samples_per_second": 45.818, | |
| "eval_steps_per_second": 0.721, | |
| "step": 9582 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 0.00023323940722187433, | |
| "loss": 0.6934, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 0.00023219578376121894, | |
| "loss": 0.7101, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 0.00023115216030056353, | |
| "loss": 0.6922, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 0.00023010853683990814, | |
| "loss": 0.7027, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 0.00022906491337925275, | |
| "loss": 0.6931, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 0.00022802128991859734, | |
| "loss": 0.6782, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 0.00022697766645794195, | |
| "loss": 0.6842, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 0.00022593404299728657, | |
| "loss": 0.7295, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 0.00022489041953663115, | |
| "loss": 0.7145, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 0.00022384679607597577, | |
| "loss": 0.6637, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 0.00022280317261532038, | |
| "loss": 0.6666, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 0.00022175954915466497, | |
| "loss": 0.7068, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 0.00022071592569400955, | |
| "loss": 0.6759, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 0.0002196723022333542, | |
| "loss": 0.6926, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 0.00021862867877269878, | |
| "loss": 0.6825, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 0.00021758505531204342, | |
| "loss": 0.6807, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9058546631362165, | |
| "eval_loss": 0.3208906650543213, | |
| "eval_runtime": 149.169, | |
| "eval_samples_per_second": 45.572, | |
| "eval_steps_per_second": 0.717, | |
| "step": 11179 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 0.000216541431851388, | |
| "loss": 0.677, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 0.00021550824462533916, | |
| "loss": 0.7379, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 0.00021447505739929034, | |
| "loss": 0.7156, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 0.00021343143393863493, | |
| "loss": 0.6406, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 0.0002123878104779795, | |
| "loss": 0.6888, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 0.00021134418701732413, | |
| "loss": 0.6968, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 0.00021030056355666874, | |
| "loss": 0.6989, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 0.00020925694009601333, | |
| "loss": 0.6751, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 0.00020821331663535794, | |
| "loss": 0.6879, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 0.00020716969317470255, | |
| "loss": 0.678, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 0.00020612606971404714, | |
| "loss": 0.6501, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 0.00020508244625339176, | |
| "loss": 0.6679, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 0.00020403882279273637, | |
| "loss": 0.7116, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "learning_rate": 0.00020299519933208098, | |
| "loss": 0.6899, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 0.00020195157587142557, | |
| "loss": 0.6892, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 0.00020090795241077016, | |
| "loss": 0.6873, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.902177110914975, | |
| "eval_loss": 0.3205910921096802, | |
| "eval_runtime": 147.3348, | |
| "eval_samples_per_second": 46.14, | |
| "eval_steps_per_second": 0.726, | |
| "step": 12776 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 0.0001998643289501148, | |
| "loss": 0.6847, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "learning_rate": 0.00019882070548945938, | |
| "loss": 0.6833, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 0.00019777708202880397, | |
| "loss": 0.6737, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 0.0001967334585681486, | |
| "loss": 0.6568, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 0.0001956898351074932, | |
| "loss": 0.7059, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 0.00019464621164683778, | |
| "loss": 0.6831, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 0.00019360258818618243, | |
| "loss": 0.7174, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 0.00019256940096013358, | |
| "loss": 0.6966, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "learning_rate": 0.00019152577749947816, | |
| "loss": 0.699, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 0.00019048215403882278, | |
| "loss": 0.6774, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 0.0001894385305781674, | |
| "loss": 0.6848, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 0.00018839490711751198, | |
| "loss": 0.6901, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 0.00018735128365685656, | |
| "loss": 0.6994, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "learning_rate": 0.0001863076601962012, | |
| "loss": 0.6739, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 0.0001852640367355458, | |
| "loss": 0.6854, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 0.00018422041327489038, | |
| "loss": 0.6416, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9057075610473668, | |
| "eval_loss": 0.31237688660621643, | |
| "eval_runtime": 148.9632, | |
| "eval_samples_per_second": 45.635, | |
| "eval_steps_per_second": 0.718, | |
| "step": 14373 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 0.00018317678981423502, | |
| "loss": 0.6711, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "learning_rate": 0.0001821331663535796, | |
| "loss": 0.6965, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 0.00018108954289292422, | |
| "loss": 0.6896, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 0.00018004591943226883, | |
| "loss": 0.6944, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 0.00017900229597161342, | |
| "loss": 0.6981, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 0.00017795867251095803, | |
| "loss": 0.6819, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "learning_rate": 0.00017691504905030265, | |
| "loss": 0.6869, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 0.00017587142558964723, | |
| "loss": 0.6974, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 0.00017482780212899185, | |
| "loss": 0.6621, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 0.00017378417866833646, | |
| "loss": 0.6732, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 0.00017274055520768105, | |
| "loss": 0.678, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 0.00017169693174702566, | |
| "loss": 0.6494, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 0.00017065330828637025, | |
| "loss": 0.6909, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "learning_rate": 0.00016960968482571486, | |
| "loss": 0.687, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 0.00016856606136505948, | |
| "loss": 0.6705, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "learning_rate": 0.00016752243790440406, | |
| "loss": 0.6698, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8949691085613416, | |
| "eval_loss": 0.3288457989692688, | |
| "eval_runtime": 150.3856, | |
| "eval_samples_per_second": 45.204, | |
| "eval_steps_per_second": 0.712, | |
| "step": 15970 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 0.00016648925067835524, | |
| "loss": 0.6701, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "learning_rate": 0.00016544562721769983, | |
| "loss": 0.6771, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "learning_rate": 0.00016440200375704444, | |
| "loss": 0.6877, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "learning_rate": 0.00016335838029638906, | |
| "loss": 0.6495, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 10.27, | |
| "learning_rate": 0.00016231475683573364, | |
| "loss": 0.6925, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 10.33, | |
| "learning_rate": 0.00016127113337507826, | |
| "loss": 0.647, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 10.39, | |
| "learning_rate": 0.00016022750991442287, | |
| "loss": 0.658, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 10.46, | |
| "learning_rate": 0.00015918388645376746, | |
| "loss": 0.7033, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 10.52, | |
| "learning_rate": 0.00015814026299311207, | |
| "loss": 0.6675, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 10.58, | |
| "learning_rate": 0.00015709663953245666, | |
| "loss": 0.6905, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 10.64, | |
| "learning_rate": 0.0001560530160718013, | |
| "loss": 0.6766, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 0.00015500939261114588, | |
| "loss": 0.684, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 0.00015396576915049047, | |
| "loss": 0.6382, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 0.0001529221456898351, | |
| "loss": 0.6737, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 0.0001518785222291797, | |
| "loss": 0.691, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "learning_rate": 0.00015083489876852429, | |
| "loss": 0.716, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.8998234774933804, | |
| "eval_loss": 0.31469690799713135, | |
| "eval_runtime": 150.5759, | |
| "eval_samples_per_second": 45.147, | |
| "eval_steps_per_second": 0.711, | |
| "step": 17567 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 0.0001497912753078689, | |
| "loss": 0.7326, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 11.08, | |
| "learning_rate": 0.0001487476518472135, | |
| "loss": 0.6747, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 11.15, | |
| "learning_rate": 0.00014770402838655813, | |
| "loss": 0.7075, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 11.21, | |
| "learning_rate": 0.0001466604049259027, | |
| "loss": 0.69, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 11.27, | |
| "learning_rate": 0.00014561678146524733, | |
| "loss": 0.6793, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 11.33, | |
| "learning_rate": 0.00014457315800459194, | |
| "loss": 0.6782, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 0.00014352953454393655, | |
| "loss": 0.6532, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 11.46, | |
| "learning_rate": 0.00014249634731788768, | |
| "loss": 0.7053, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 0.0001414527238572323, | |
| "loss": 0.6476, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 11.58, | |
| "learning_rate": 0.0001404091003965769, | |
| "loss": 0.6308, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 11.65, | |
| "learning_rate": 0.0001393654769359215, | |
| "loss": 0.6886, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 11.71, | |
| "learning_rate": 0.0001383218534752661, | |
| "loss": 0.6631, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 11.77, | |
| "learning_rate": 0.00013727823001461072, | |
| "loss": 0.7056, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 11.83, | |
| "learning_rate": 0.00013623460655395533, | |
| "loss": 0.6602, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 11.9, | |
| "learning_rate": 0.00013519098309329992, | |
| "loss": 0.6728, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 11.96, | |
| "learning_rate": 0.00013414735963264453, | |
| "loss": 0.6514, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9111503383348043, | |
| "eval_loss": 0.3034283220767975, | |
| "eval_runtime": 145.7542, | |
| "eval_samples_per_second": 46.64, | |
| "eval_steps_per_second": 0.734, | |
| "step": 19164 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 0.00013310373617198915, | |
| "loss": 0.6567, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 12.09, | |
| "learning_rate": 0.00013206011271133373, | |
| "loss": 0.6882, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "learning_rate": 0.00013101648925067835, | |
| "loss": 0.6511, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "learning_rate": 0.00012997286579002296, | |
| "loss": 0.6705, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "learning_rate": 0.00012892924232936755, | |
| "loss": 0.6693, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 12.34, | |
| "learning_rate": 0.00012788561886871216, | |
| "loss": 0.68, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "learning_rate": 0.00012684199540805675, | |
| "loss": 0.6767, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 12.46, | |
| "learning_rate": 0.00012579837194740136, | |
| "loss": 0.6768, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 12.52, | |
| "learning_rate": 0.00012475474848674598, | |
| "loss": 0.6662, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 12.59, | |
| "learning_rate": 0.00012371112502609056, | |
| "loss": 0.6511, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 12.65, | |
| "learning_rate": 0.00012266750156543518, | |
| "loss": 0.7057, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 12.71, | |
| "learning_rate": 0.00012163431433938634, | |
| "loss": 0.6699, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 12.77, | |
| "learning_rate": 0.00012059069087873094, | |
| "loss": 0.6541, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 12.84, | |
| "learning_rate": 0.00011954706741807554, | |
| "loss": 0.6741, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 0.00011850344395742016, | |
| "loss": 0.658, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 0.00011745982049676476, | |
| "loss": 0.6513, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9092380111797588, | |
| "eval_loss": 0.30905914306640625, | |
| "eval_runtime": 146.3169, | |
| "eval_samples_per_second": 46.461, | |
| "eval_steps_per_second": 0.731, | |
| "step": 20761 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 0.00011641619703610936, | |
| "loss": 0.6568, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 13.09, | |
| "learning_rate": 0.00011537257357545397, | |
| "loss": 0.6853, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 13.15, | |
| "learning_rate": 0.00011432895011479858, | |
| "loss": 0.6699, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 13.21, | |
| "learning_rate": 0.00011328532665414317, | |
| "loss": 0.6494, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 13.27, | |
| "learning_rate": 0.00011224170319348778, | |
| "loss": 0.7118, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 13.34, | |
| "learning_rate": 0.00011119807973283239, | |
| "loss": 0.6649, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "learning_rate": 0.00011015445627217699, | |
| "loss": 0.6646, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 13.46, | |
| "learning_rate": 0.0001091108328115216, | |
| "loss": 0.6436, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "learning_rate": 0.0001080672093508662, | |
| "loss": 0.6258, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 13.59, | |
| "learning_rate": 0.0001070235858902108, | |
| "loss": 0.6754, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 13.65, | |
| "learning_rate": 0.0001059799624295554, | |
| "loss": 0.6737, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "learning_rate": 0.00010493633896890001, | |
| "loss": 0.6511, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 13.78, | |
| "learning_rate": 0.00010389271550824463, | |
| "loss": 0.6472, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 13.84, | |
| "learning_rate": 0.00010284909204758921, | |
| "loss": 0.6571, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 13.9, | |
| "learning_rate": 0.00010180546858693383, | |
| "loss": 0.693, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 13.96, | |
| "learning_rate": 0.00010076184512627843, | |
| "loss": 0.652, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.909973521624007, | |
| "eval_loss": 0.30560359358787537, | |
| "eval_runtime": 146.3619, | |
| "eval_samples_per_second": 46.447, | |
| "eval_steps_per_second": 0.731, | |
| "step": 22358 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 9.971822166562303e-05, | |
| "loss": 0.6286, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 14.09, | |
| "learning_rate": 9.867459820496764e-05, | |
| "loss": 0.6503, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 14.15, | |
| "learning_rate": 9.763097474431224e-05, | |
| "loss": 0.6514, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "learning_rate": 9.659778751826341e-05, | |
| "loss": 0.6728, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 14.28, | |
| "learning_rate": 9.555416405760801e-05, | |
| "loss": 0.6621, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 14.34, | |
| "learning_rate": 9.451054059695261e-05, | |
| "loss": 0.6771, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 9.346691713629722e-05, | |
| "loss": 0.6689, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 14.46, | |
| "learning_rate": 9.242329367564181e-05, | |
| "loss": 0.6712, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 14.53, | |
| "learning_rate": 9.137967021498642e-05, | |
| "loss": 0.6761, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 14.59, | |
| "learning_rate": 9.033604675433104e-05, | |
| "loss": 0.6327, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 14.65, | |
| "learning_rate": 8.929242329367564e-05, | |
| "loss": 0.6671, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 8.824879983302024e-05, | |
| "loss": 0.6598, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 14.78, | |
| "learning_rate": 8.720517637236485e-05, | |
| "loss": 0.6317, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 8.616155291170945e-05, | |
| "loss": 0.6615, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 14.9, | |
| "learning_rate": 8.511792945105405e-05, | |
| "loss": 0.6087, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 14.97, | |
| "learning_rate": 8.407430599039865e-05, | |
| "loss": 0.7105, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9149749926448956, | |
| "eval_loss": 0.30149412155151367, | |
| "eval_runtime": 145.6909, | |
| "eval_samples_per_second": 46.66, | |
| "eval_steps_per_second": 0.734, | |
| "step": 23955 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 8.303068252974326e-05, | |
| "loss": 0.6911, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 15.09, | |
| "learning_rate": 8.198705906908788e-05, | |
| "loss": 0.6717, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 15.15, | |
| "learning_rate": 8.094343560843246e-05, | |
| "loss": 0.6564, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "learning_rate": 7.989981214777708e-05, | |
| "loss": 0.6446, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 15.28, | |
| "learning_rate": 7.885618868712169e-05, | |
| "loss": 0.6431, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 15.34, | |
| "learning_rate": 7.781256522646628e-05, | |
| "loss": 0.6762, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 15.4, | |
| "learning_rate": 7.676894176581089e-05, | |
| "loss": 0.6656, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 15.47, | |
| "learning_rate": 7.572531830515549e-05, | |
| "loss": 0.6337, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 15.53, | |
| "learning_rate": 7.468169484450009e-05, | |
| "loss": 0.6541, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 15.59, | |
| "learning_rate": 7.363807138384469e-05, | |
| "loss": 0.6772, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 15.65, | |
| "learning_rate": 7.260488415779586e-05, | |
| "loss": 0.629, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 15.72, | |
| "learning_rate": 7.156126069714046e-05, | |
| "loss": 0.6998, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 15.78, | |
| "learning_rate": 7.051763723648507e-05, | |
| "loss": 0.6686, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 15.84, | |
| "learning_rate": 6.947401377582967e-05, | |
| "loss": 0.6822, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "learning_rate": 6.843039031517429e-05, | |
| "loss": 0.6143, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 6.738676685451889e-05, | |
| "loss": 0.6337, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.30700910091400146, | |
| "eval_runtime": 146.384, | |
| "eval_samples_per_second": 46.44, | |
| "eval_steps_per_second": 0.731, | |
| "step": 25552 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 6.634314339386349e-05, | |
| "loss": 0.6502, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 16.09, | |
| "learning_rate": 6.52995199332081e-05, | |
| "loss": 0.6448, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 16.16, | |
| "learning_rate": 6.42558964725527e-05, | |
| "loss": 0.6272, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 16.22, | |
| "learning_rate": 6.32122730118973e-05, | |
| "loss": 0.6316, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 16.28, | |
| "learning_rate": 6.21686495512419e-05, | |
| "loss": 0.6442, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 16.34, | |
| "learning_rate": 6.11250260905865e-05, | |
| "loss": 0.6489, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 16.41, | |
| "learning_rate": 6.0081402629931114e-05, | |
| "loss": 0.6603, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 16.47, | |
| "learning_rate": 5.9037779169275714e-05, | |
| "loss": 0.6449, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 16.53, | |
| "learning_rate": 5.799415570862033e-05, | |
| "loss": 0.661, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 16.59, | |
| "learning_rate": 5.695053224796493e-05, | |
| "loss": 0.642, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 16.66, | |
| "learning_rate": 5.5906908787309535e-05, | |
| "loss": 0.6498, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 16.72, | |
| "learning_rate": 5.4863285326654135e-05, | |
| "loss": 0.6902, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 16.78, | |
| "learning_rate": 5.381966186599874e-05, | |
| "loss": 0.6336, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 16.84, | |
| "learning_rate": 5.277603840534335e-05, | |
| "loss": 0.6393, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 16.91, | |
| "learning_rate": 5.173241494468795e-05, | |
| "loss": 0.6496, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 16.97, | |
| "learning_rate": 5.0688791484032557e-05, | |
| "loss": 0.63, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.913503971756399, | |
| "eval_loss": 0.30175167322158813, | |
| "eval_runtime": 149.8031, | |
| "eval_samples_per_second": 45.38, | |
| "eval_steps_per_second": 0.714, | |
| "step": 27149 | |
| }, | |
| { | |
| "epoch": 17.03, | |
| "learning_rate": 4.9645168023377163e-05, | |
| "loss": 0.6195, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 17.09, | |
| "learning_rate": 4.861198079732832e-05, | |
| "loss": 0.6299, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 17.16, | |
| "learning_rate": 4.756835733667292e-05, | |
| "loss": 0.6939, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 17.22, | |
| "learning_rate": 4.652473387601752e-05, | |
| "loss": 0.6416, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 4.5481110415362136e-05, | |
| "loss": 0.6626, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 17.35, | |
| "learning_rate": 4.4437486954706736e-05, | |
| "loss": 0.6444, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 17.41, | |
| "learning_rate": 4.339386349405134e-05, | |
| "loss": 0.6238, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 17.47, | |
| "learning_rate": 4.2350240033395944e-05, | |
| "loss": 0.6505, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 17.53, | |
| "learning_rate": 4.130661657274056e-05, | |
| "loss": 0.6346, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 4.026299311208516e-05, | |
| "loss": 0.6319, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 17.66, | |
| "learning_rate": 3.921936965142976e-05, | |
| "loss": 0.6811, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 17.72, | |
| "learning_rate": 3.8175746190774365e-05, | |
| "loss": 0.6645, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 17.78, | |
| "learning_rate": 3.713212273011897e-05, | |
| "loss": 0.6512, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 17.85, | |
| "learning_rate": 3.608849926946357e-05, | |
| "loss": 0.6578, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 17.91, | |
| "learning_rate": 3.504487580880818e-05, | |
| "loss": 0.6358, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 17.97, | |
| "learning_rate": 3.4001252348152786e-05, | |
| "loss": 0.6672, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9087967049132097, | |
| "eval_loss": 0.30836355686187744, | |
| "eval_runtime": 148.2197, | |
| "eval_samples_per_second": 45.864, | |
| "eval_steps_per_second": 0.722, | |
| "step": 28746 | |
| }, | |
| { | |
| "epoch": 18.03, | |
| "learning_rate": 3.295762888749739e-05, | |
| "loss": 0.65, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 18.1, | |
| "learning_rate": 3.191400542684199e-05, | |
| "loss": 0.6293, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 18.16, | |
| "learning_rate": 3.087038196618659e-05, | |
| "loss": 0.6059, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 18.22, | |
| "learning_rate": 2.98267585055312e-05, | |
| "loss": 0.5975, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 18.28, | |
| "learning_rate": 2.8783135044875807e-05, | |
| "loss": 0.6759, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 18.35, | |
| "learning_rate": 2.773951158422041e-05, | |
| "loss": 0.6457, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 18.41, | |
| "learning_rate": 2.6695888123565017e-05, | |
| "loss": 0.6715, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 18.47, | |
| "learning_rate": 2.565226466290962e-05, | |
| "loss": 0.6642, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 18.53, | |
| "learning_rate": 2.460864120225422e-05, | |
| "loss": 0.6432, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 18.6, | |
| "learning_rate": 2.3565017741598828e-05, | |
| "loss": 0.6441, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "learning_rate": 2.2521394280943432e-05, | |
| "loss": 0.6843, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "learning_rate": 2.147777082028804e-05, | |
| "loss": 0.6459, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 18.79, | |
| "learning_rate": 2.0434147359632642e-05, | |
| "loss": 0.6233, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 18.85, | |
| "learning_rate": 1.939052389897725e-05, | |
| "loss": 0.6634, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 18.91, | |
| "learning_rate": 1.8346900438321853e-05, | |
| "loss": 0.6701, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 18.97, | |
| "learning_rate": 1.7303276977666456e-05, | |
| "loss": 0.6479, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.9101206237128567, | |
| "eval_loss": 0.3060016632080078, | |
| "eval_runtime": 149.555, | |
| "eval_samples_per_second": 45.455, | |
| "eval_steps_per_second": 0.715, | |
| "step": 30343 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 1.625965351701106e-05, | |
| "loss": 0.6155, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 19.1, | |
| "learning_rate": 1.5216030056355665e-05, | |
| "loss": 0.6079, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 19.16, | |
| "learning_rate": 1.417240659570027e-05, | |
| "loss": 0.6709, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 19.22, | |
| "learning_rate": 1.3128783135044874e-05, | |
| "loss": 0.6604, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 19.29, | |
| "learning_rate": 1.208515967438948e-05, | |
| "loss": 0.6222, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 19.35, | |
| "learning_rate": 1.1041536213734085e-05, | |
| "loss": 0.6428, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 19.41, | |
| "learning_rate": 9.997912753078688e-06, | |
| "loss": 0.6664, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 19.47, | |
| "learning_rate": 8.954289292423293e-06, | |
| "loss": 0.6489, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 19.54, | |
| "learning_rate": 7.910665831767897e-06, | |
| "loss": 0.6414, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 19.6, | |
| "learning_rate": 6.877478605719056e-06, | |
| "loss": 0.6599, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 19.66, | |
| "learning_rate": 5.83385514506366e-06, | |
| "loss": 0.6433, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 19.72, | |
| "learning_rate": 4.790231684408265e-06, | |
| "loss": 0.6325, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 19.79, | |
| "learning_rate": 3.7466082237528697e-06, | |
| "loss": 0.6363, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 19.85, | |
| "learning_rate": 2.7029847630974745e-06, | |
| "loss": 0.6408, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 19.91, | |
| "learning_rate": 1.6593613024420787e-06, | |
| "loss": 0.645, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 19.97, | |
| "learning_rate": 6.157378417866834e-07, | |
| "loss": 0.6658, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9089438070020595, | |
| "eval_loss": 0.3071773946285248, | |
| "eval_runtime": 150.0563, | |
| "eval_samples_per_second": 45.303, | |
| "eval_steps_per_second": 0.713, | |
| "step": 31940 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 31940, | |
| "total_flos": 0.0, | |
| "train_loss": 0.8136612295581911, | |
| "train_runtime": 27726.7705, | |
| "train_samples_per_second": 36.855, | |
| "train_steps_per_second": 1.152 | |
| } | |
| ], | |
| "max_steps": 31940, | |
| "num_train_epochs": 20, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |