| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 60.0, | |
| "global_step": 18720, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5306859205776173, | |
| "eval_loss": 0.3733972907066345, | |
| "eval_runtime": 4.2135, | |
| "eval_samples_per_second": 65.74, | |
| "eval_steps_per_second": 8.307, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0009732905982905983, | |
| "loss": 0.4216, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.38019850850105286, | |
| "eval_runtime": 4.2887, | |
| "eval_samples_per_second": 64.589, | |
| "eval_steps_per_second": 8.161, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 0.4298796057701111, | |
| "eval_runtime": 4.2965, | |
| "eval_samples_per_second": 64.471, | |
| "eval_steps_per_second": 8.146, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.0009465811965811966, | |
| "loss": 0.3883, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5451263537906137, | |
| "eval_loss": 0.34903544187545776, | |
| "eval_runtime": 4.308, | |
| "eval_samples_per_second": 64.299, | |
| "eval_steps_per_second": 8.124, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 3, | |
| "best_eval_accuracy": 0.5451263537906137, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.0009198717948717949, | |
| "loss": 0.3918, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5884476534296029, | |
| "eval_loss": 0.3460931181907654, | |
| "eval_runtime": 4.301, | |
| "eval_samples_per_second": 64.404, | |
| "eval_steps_per_second": 8.138, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5884476534296029, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5523465703971119, | |
| "eval_loss": 0.3598935902118683, | |
| "eval_runtime": 4.2993, | |
| "eval_samples_per_second": 64.429, | |
| "eval_steps_per_second": 8.141, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5884476534296029, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.0008931623931623932, | |
| "loss": 0.3764, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5451263537906137, | |
| "eval_loss": 0.356489896774292, | |
| "eval_runtime": 4.3043, | |
| "eval_samples_per_second": 64.355, | |
| "eval_steps_per_second": 8.131, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5884476534296029, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5018050541516246, | |
| "eval_loss": 0.3611055910587311, | |
| "eval_runtime": 4.3049, | |
| "eval_samples_per_second": 64.345, | |
| "eval_steps_per_second": 8.13, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5884476534296029, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.0008664529914529915, | |
| "loss": 0.3794, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5415162454873647, | |
| "eval_loss": 0.40397846698760986, | |
| "eval_runtime": 4.3052, | |
| "eval_samples_per_second": 64.341, | |
| "eval_steps_per_second": 8.13, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5884476534296029, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.0008397435897435898, | |
| "loss": 0.3778, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.3622380495071411, | |
| "eval_runtime": 4.3031, | |
| "eval_samples_per_second": 64.372, | |
| "eval_steps_per_second": 8.134, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5884476534296029, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.4693140794223827, | |
| "eval_loss": 0.4954076111316681, | |
| "eval_runtime": 4.3057, | |
| "eval_samples_per_second": 64.333, | |
| "eval_steps_per_second": 8.129, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5884476534296029, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 0.0008130341880341881, | |
| "loss": 0.3813, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 0.3602141737937927, | |
| "eval_runtime": 4.3078, | |
| "eval_samples_per_second": 64.302, | |
| "eval_steps_per_second": 8.125, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5884476534296029, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.0007863247863247863, | |
| "loss": 0.3718, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.5415162454873647, | |
| "eval_loss": 0.345300555229187, | |
| "eval_runtime": 4.2997, | |
| "eval_samples_per_second": 64.422, | |
| "eval_steps_per_second": 8.14, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5884476534296029, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.5342960288808665, | |
| "eval_loss": 0.36396491527557373, | |
| "eval_runtime": 4.3002, | |
| "eval_samples_per_second": 64.415, | |
| "eval_steps_per_second": 8.139, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5884476534296029, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 0.0007596153846153846, | |
| "loss": 0.3701, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.48375451263537905, | |
| "eval_loss": 0.358859658241272, | |
| "eval_runtime": 4.3059, | |
| "eval_samples_per_second": 64.33, | |
| "eval_steps_per_second": 8.128, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5884476534296029, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5631768953068592, | |
| "eval_loss": 0.36997947096824646, | |
| "eval_runtime": 4.3027, | |
| "eval_samples_per_second": 64.378, | |
| "eval_steps_per_second": 8.134, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5884476534296029, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.0007329059829059829, | |
| "loss": 0.371, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5342960288808665, | |
| "eval_loss": 0.4146815538406372, | |
| "eval_runtime": 4.3009, | |
| "eval_samples_per_second": 64.405, | |
| "eval_steps_per_second": 8.138, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5884476534296029, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.0007061965811965813, | |
| "loss": 0.3644, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.5740072202166066, | |
| "eval_loss": 0.3504742681980133, | |
| "eval_runtime": 4.3002, | |
| "eval_samples_per_second": 64.416, | |
| "eval_steps_per_second": 8.139, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5884476534296029, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.48736462093862815, | |
| "eval_loss": 0.37356558442115784, | |
| "eval_runtime": 4.2986, | |
| "eval_samples_per_second": 64.439, | |
| "eval_steps_per_second": 8.142, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5884476534296029, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.0006794871794871796, | |
| "loss": 0.3667, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5703971119133574, | |
| "eval_loss": 0.3636634945869446, | |
| "eval_runtime": 4.2999, | |
| "eval_samples_per_second": 64.42, | |
| "eval_steps_per_second": 8.14, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5884476534296029, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 0.0006527777777777778, | |
| "loss": 0.3629, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.6209386281588448, | |
| "eval_loss": 0.3412002921104431, | |
| "eval_runtime": 4.2976, | |
| "eval_samples_per_second": 64.455, | |
| "eval_steps_per_second": 8.144, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.6209386281588448, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.628158844765343, | |
| "eval_loss": 0.34508734941482544, | |
| "eval_runtime": 4.3013, | |
| "eval_samples_per_second": 64.399, | |
| "eval_steps_per_second": 8.137, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 21, | |
| "best_eval_accuracy": 0.628158844765343, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.0006260683760683761, | |
| "loss": 0.3574, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.6064981949458483, | |
| "eval_loss": 0.3625960350036621, | |
| "eval_runtime": 4.301, | |
| "eval_samples_per_second": 64.404, | |
| "eval_steps_per_second": 8.138, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 21, | |
| "best_eval_accuracy": 0.628158844765343, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.48736462093862815, | |
| "eval_loss": 0.3732198178768158, | |
| "eval_runtime": 4.2992, | |
| "eval_samples_per_second": 64.431, | |
| "eval_steps_per_second": 8.141, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 21, | |
| "best_eval_accuracy": 0.628158844765343, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 0.0005993589743589744, | |
| "loss": 0.3565, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.6173285198555957, | |
| "eval_loss": 0.342726469039917, | |
| "eval_runtime": 4.3024, | |
| "eval_samples_per_second": 64.382, | |
| "eval_steps_per_second": 8.135, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 21, | |
| "best_eval_accuracy": 0.628158844765343, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.0005726495726495727, | |
| "loss": 0.3525, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.5812274368231047, | |
| "eval_loss": 0.38550591468811035, | |
| "eval_runtime": 4.3005, | |
| "eval_samples_per_second": 64.41, | |
| "eval_steps_per_second": 8.139, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 21, | |
| "best_eval_accuracy": 0.628158844765343, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.6498194945848376, | |
| "eval_loss": 0.3384442925453186, | |
| "eval_runtime": 4.2994, | |
| "eval_samples_per_second": 64.428, | |
| "eval_steps_per_second": 8.141, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.6498194945848376, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 0.000545940170940171, | |
| "loss": 0.3523, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.628158844765343, | |
| "eval_loss": 0.3408096730709076, | |
| "eval_runtime": 4.3005, | |
| "eval_samples_per_second": 64.412, | |
| "eval_steps_per_second": 8.139, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.6498194945848376, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.0005192307692307693, | |
| "loss": 0.3505, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.6101083032490975, | |
| "eval_loss": 0.354794442653656, | |
| "eval_runtime": 4.3016, | |
| "eval_samples_per_second": 64.395, | |
| "eval_steps_per_second": 8.137, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.6498194945848376, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.592057761732852, | |
| "eval_loss": 0.3860756754875183, | |
| "eval_runtime": 4.2988, | |
| "eval_samples_per_second": 64.436, | |
| "eval_steps_per_second": 8.142, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.6498194945848376, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 0.0004925213675213676, | |
| "loss": 0.3509, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.5992779783393501, | |
| "eval_loss": 0.370971143245697, | |
| "eval_runtime": 4.2976, | |
| "eval_samples_per_second": 64.454, | |
| "eval_steps_per_second": 8.144, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.6498194945848376, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.5992779783393501, | |
| "eval_loss": 0.38974320888519287, | |
| "eval_runtime": 4.303, | |
| "eval_samples_per_second": 64.374, | |
| "eval_steps_per_second": 8.134, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.6498194945848376, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.00046581196581196583, | |
| "loss": 0.3494, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.6353790613718412, | |
| "eval_loss": 0.3535420596599579, | |
| "eval_runtime": 4.299, | |
| "eval_samples_per_second": 64.433, | |
| "eval_steps_per_second": 8.141, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.6498194945848376, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 0.0004391025641025641, | |
| "loss": 0.3459, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.628158844765343, | |
| "eval_loss": 0.33893653750419617, | |
| "eval_runtime": 4.3011, | |
| "eval_samples_per_second": 64.401, | |
| "eval_steps_per_second": 8.137, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.6498194945848376, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.6209386281588448, | |
| "eval_loss": 0.3396986126899719, | |
| "eval_runtime": 4.2983, | |
| "eval_samples_per_second": 64.445, | |
| "eval_steps_per_second": 8.143, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.6498194945848376, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.0004123931623931624, | |
| "loss": 0.3429, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.6101083032490975, | |
| "eval_loss": 0.34503623843193054, | |
| "eval_runtime": 4.2992, | |
| "eval_samples_per_second": 64.431, | |
| "eval_steps_per_second": 8.141, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.6498194945848376, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 0.0003856837606837607, | |
| "loss": 0.3432, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.6064981949458483, | |
| "eval_loss": 0.392516553401947, | |
| "eval_runtime": 4.2992, | |
| "eval_samples_per_second": 64.431, | |
| "eval_steps_per_second": 8.141, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.6498194945848376, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.6714801444043321, | |
| "eval_loss": 0.32944434881210327, | |
| "eval_runtime": 4.2991, | |
| "eval_samples_per_second": 64.432, | |
| "eval_steps_per_second": 8.141, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 37, | |
| "best_eval_accuracy": 0.6714801444043321, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.000358974358974359, | |
| "loss": 0.341, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.6389891696750902, | |
| "eval_loss": 0.34416595101356506, | |
| "eval_runtime": 4.2999, | |
| "eval_samples_per_second": 64.419, | |
| "eval_steps_per_second": 8.14, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 37, | |
| "best_eval_accuracy": 0.6714801444043321, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.6462093862815884, | |
| "eval_loss": 0.342062771320343, | |
| "eval_runtime": 4.3022, | |
| "eval_samples_per_second": 64.386, | |
| "eval_steps_per_second": 8.135, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 37, | |
| "best_eval_accuracy": 0.6714801444043321, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 0.00033226495726495727, | |
| "loss": 0.3392, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.6389891696750902, | |
| "eval_loss": 0.33708664774894714, | |
| "eval_runtime": 4.2992, | |
| "eval_samples_per_second": 64.431, | |
| "eval_steps_per_second": 8.141, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 37, | |
| "best_eval_accuracy": 0.6714801444043321, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0003055555555555556, | |
| "loss": 0.3392, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.6534296028880866, | |
| "eval_loss": 0.33264684677124023, | |
| "eval_runtime": 4.3016, | |
| "eval_samples_per_second": 64.395, | |
| "eval_steps_per_second": 8.136, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 37, | |
| "best_eval_accuracy": 0.6714801444043321, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.628158844765343, | |
| "eval_loss": 0.3713812530040741, | |
| "eval_runtime": 4.2963, | |
| "eval_samples_per_second": 64.474, | |
| "eval_steps_per_second": 8.146, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 37, | |
| "best_eval_accuracy": 0.6714801444043321, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 0.0002788461538461539, | |
| "loss": 0.337, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.6245487364620939, | |
| "eval_loss": 0.3535134494304657, | |
| "eval_runtime": 4.2972, | |
| "eval_samples_per_second": 64.461, | |
| "eval_steps_per_second": 8.145, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 37, | |
| "best_eval_accuracy": 0.6714801444043321, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.00025213675213675216, | |
| "loss": 0.3352, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.6245487364620939, | |
| "eval_loss": 0.35477742552757263, | |
| "eval_runtime": 4.2996, | |
| "eval_samples_per_second": 64.424, | |
| "eval_steps_per_second": 8.14, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 37, | |
| "best_eval_accuracy": 0.6714801444043321, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.6570397111913358, | |
| "eval_loss": 0.33611994981765747, | |
| "eval_runtime": 4.2993, | |
| "eval_samples_per_second": 64.429, | |
| "eval_steps_per_second": 8.141, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 37, | |
| "best_eval_accuracy": 0.6714801444043321, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 0.00022542735042735044, | |
| "loss": 0.3335, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.6859205776173285, | |
| "eval_loss": 0.33294087648391724, | |
| "eval_runtime": 4.3015, | |
| "eval_samples_per_second": 64.396, | |
| "eval_steps_per_second": 8.137, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.6462093862815884, | |
| "eval_loss": 0.3423037827014923, | |
| "eval_runtime": 4.297, | |
| "eval_samples_per_second": 64.464, | |
| "eval_steps_per_second": 8.145, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 0.0001987179487179487, | |
| "loss": 0.3329, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.6534296028880866, | |
| "eval_loss": 0.33556535840034485, | |
| "eval_runtime": 4.2948, | |
| "eval_samples_per_second": 64.497, | |
| "eval_steps_per_second": 8.149, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 0.00017200854700854702, | |
| "loss": 0.3308, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.6642599277978339, | |
| "eval_loss": 0.33979371190071106, | |
| "eval_runtime": 4.2975, | |
| "eval_samples_per_second": 64.456, | |
| "eval_steps_per_second": 8.144, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.6678700361010831, | |
| "eval_loss": 0.3374033272266388, | |
| "eval_runtime": 4.2988, | |
| "eval_samples_per_second": 64.437, | |
| "eval_steps_per_second": 8.142, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 0.00014529914529914532, | |
| "loss": 0.3291, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.6787003610108303, | |
| "eval_loss": 0.33146607875823975, | |
| "eval_runtime": 4.3011, | |
| "eval_samples_per_second": 64.402, | |
| "eval_steps_per_second": 8.137, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 0.00011858974358974358, | |
| "loss": 0.3284, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.631768953068592, | |
| "eval_loss": 0.36504465341567993, | |
| "eval_runtime": 4.3007, | |
| "eval_samples_per_second": 64.409, | |
| "eval_steps_per_second": 8.138, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.628158844765343, | |
| "eval_loss": 0.35373085737228394, | |
| "eval_runtime": 4.2986, | |
| "eval_samples_per_second": 64.44, | |
| "eval_steps_per_second": 8.142, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 9.188034188034189e-05, | |
| "loss": 0.3257, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.6425992779783394, | |
| "eval_loss": 0.34801429510116577, | |
| "eval_runtime": 4.3013, | |
| "eval_samples_per_second": 64.399, | |
| "eval_steps_per_second": 8.137, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.6570397111913358, | |
| "eval_loss": 0.34239715337753296, | |
| "eval_runtime": 4.2962, | |
| "eval_samples_per_second": 64.476, | |
| "eval_steps_per_second": 8.147, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 6.517094017094018e-05, | |
| "loss": 0.3274, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.6678700361010831, | |
| "eval_loss": 0.3412990868091583, | |
| "eval_runtime": 4.2933, | |
| "eval_samples_per_second": 64.519, | |
| "eval_steps_per_second": 8.152, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.3265, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.6389891696750902, | |
| "eval_loss": 0.34415990114212036, | |
| "eval_runtime": 4.3058, | |
| "eval_samples_per_second": 64.332, | |
| "eval_steps_per_second": 8.129, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.6534296028880866, | |
| "eval_loss": 0.34172776341438293, | |
| "eval_runtime": 4.2978, | |
| "eval_samples_per_second": 64.452, | |
| "eval_steps_per_second": 8.144, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 1.1752136752136752e-05, | |
| "loss": 0.326, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.6570397111913358, | |
| "eval_loss": 0.3407086431980133, | |
| "eval_runtime": 4.2954, | |
| "eval_samples_per_second": 64.488, | |
| "eval_steps_per_second": 8.148, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 0.3531108416043795, | |
| "train_runtime": 3953.5033, | |
| "train_samples_per_second": 37.789, | |
| "train_steps_per_second": 4.735 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |