| { | |
| "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": 0.5054151624548736, | |
| "eval_loss": 0.3735279142856598, | |
| "eval_runtime": 9.0462, | |
| "eval_samples_per_second": 30.621, | |
| "eval_steps_per_second": 3.869, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5054151624548736, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.002919871794871795, | |
| "loss": 0.5142, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5415162454873647, | |
| "eval_loss": 0.4847595989704132, | |
| "eval_runtime": 9.0779, | |
| "eval_samples_per_second": 30.514, | |
| "eval_steps_per_second": 3.856, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5415162454873647, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5379061371841155, | |
| "eval_loss": 0.3801901936531067, | |
| "eval_runtime": 9.1102, | |
| "eval_samples_per_second": 30.405, | |
| "eval_steps_per_second": 3.842, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5415162454873647, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.0028397435897435895, | |
| "loss": 0.4859, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.4823205769062042, | |
| "eval_runtime": 9.1679, | |
| "eval_samples_per_second": 30.214, | |
| "eval_steps_per_second": 3.818, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5415162454873647, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.0027596153846153847, | |
| "loss": 0.4412, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5379061371841155, | |
| "eval_loss": 0.39017239212989807, | |
| "eval_runtime": 9.088, | |
| "eval_samples_per_second": 30.48, | |
| "eval_steps_per_second": 3.851, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5415162454873647, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5595667870036101, | |
| "eval_loss": 0.3743537962436676, | |
| "eval_runtime": 9.2011, | |
| "eval_samples_per_second": 30.105, | |
| "eval_steps_per_second": 3.804, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.00267948717948718, | |
| "loss": 0.4418, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5487364620938628, | |
| "eval_loss": 0.4612128734588623, | |
| "eval_runtime": 9.1118, | |
| "eval_samples_per_second": 30.4, | |
| "eval_steps_per_second": 3.841, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.45901069045066833, | |
| "eval_runtime": 8.9276, | |
| "eval_samples_per_second": 31.027, | |
| "eval_steps_per_second": 3.92, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.0025993589743589745, | |
| "loss": 0.4467, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.47772425413131714, | |
| "eval_runtime": 8.8284, | |
| "eval_samples_per_second": 31.376, | |
| "eval_steps_per_second": 3.964, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.0025192307692307693, | |
| "loss": 0.4177, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.48375451263537905, | |
| "eval_loss": 0.3615993857383728, | |
| "eval_runtime": 8.8201, | |
| "eval_samples_per_second": 31.405, | |
| "eval_steps_per_second": 3.968, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6245487364620939, | |
| "eval_loss": 0.37356361746788025, | |
| "eval_runtime": 9.032, | |
| "eval_samples_per_second": 30.669, | |
| "eval_steps_per_second": 3.875, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 10, | |
| "best_eval_accuracy": 0.6245487364620939, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 0.002439102564102564, | |
| "loss": 0.3988, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5992779783393501, | |
| "eval_loss": 0.3464394211769104, | |
| "eval_runtime": 9.0159, | |
| "eval_samples_per_second": 30.724, | |
| "eval_steps_per_second": 3.882, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 10, | |
| "best_eval_accuracy": 0.6245487364620939, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.002358974358974359, | |
| "loss": 0.3911, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.628158844765343, | |
| "eval_loss": 0.3522431254386902, | |
| "eval_runtime": 9.0184, | |
| "eval_samples_per_second": 30.715, | |
| "eval_steps_per_second": 3.881, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 12, | |
| "best_eval_accuracy": 0.628158844765343, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6859205776173285, | |
| "eval_loss": 0.3406241238117218, | |
| "eval_runtime": 9.0292, | |
| "eval_samples_per_second": 30.678, | |
| "eval_steps_per_second": 3.876, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 0.002278846153846154, | |
| "loss": 0.3893, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.6570397111913358, | |
| "eval_loss": 0.42231810092926025, | |
| "eval_runtime": 9.1033, | |
| "eval_samples_per_second": 30.429, | |
| "eval_steps_per_second": 3.845, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5415162454873647, | |
| "eval_loss": 0.6759101748466492, | |
| "eval_runtime": 9.0957, | |
| "eval_samples_per_second": 30.454, | |
| "eval_steps_per_second": 3.848, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.0021987179487179486, | |
| "loss": 0.38, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.6823104693140795, | |
| "eval_loss": 0.36305832862854004, | |
| "eval_runtime": 9.0737, | |
| "eval_samples_per_second": 30.528, | |
| "eval_steps_per_second": 3.857, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.0021185897435897437, | |
| "loss": 0.3772, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.6931407942238267, | |
| "eval_loss": 0.343391090631485, | |
| "eval_runtime": 9.1219, | |
| "eval_samples_per_second": 30.367, | |
| "eval_steps_per_second": 3.837, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 17, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.6137184115523465, | |
| "eval_loss": 0.33444103598594666, | |
| "eval_runtime": 9.129, | |
| "eval_samples_per_second": 30.343, | |
| "eval_steps_per_second": 3.834, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 17, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.0020384615384615385, | |
| "loss": 0.3639, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6967509025270758, | |
| "eval_loss": 0.3670320212841034, | |
| "eval_runtime": 9.0881, | |
| "eval_samples_per_second": 30.479, | |
| "eval_steps_per_second": 3.851, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 19, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 0.0019583333333333336, | |
| "loss": 0.336, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.6895306859205776, | |
| "eval_loss": 0.3482595980167389, | |
| "eval_runtime": 8.9775, | |
| "eval_samples_per_second": 30.855, | |
| "eval_steps_per_second": 3.899, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 19, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.34846988320350647, | |
| "eval_runtime": 6.7951, | |
| "eval_samples_per_second": 40.765, | |
| "eval_steps_per_second": 5.151, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 21, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.0018782051282051281, | |
| "loss": 0.3369, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.7184115523465704, | |
| "eval_loss": 0.3540826141834259, | |
| "eval_runtime": 9.1597, | |
| "eval_samples_per_second": 30.241, | |
| "eval_steps_per_second": 3.821, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7111913357400722, | |
| "eval_loss": 0.3346291184425354, | |
| "eval_runtime": 9.1464, | |
| "eval_samples_per_second": 30.285, | |
| "eval_steps_per_second": 3.827, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 0.001798076923076923, | |
| "loss": 0.3291, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.3387109339237213, | |
| "eval_runtime": 9.16, | |
| "eval_samples_per_second": 30.24, | |
| "eval_steps_per_second": 3.821, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.0017179487179487178, | |
| "loss": 0.3228, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7220216606498195, | |
| "eval_loss": 0.3492320775985718, | |
| "eval_runtime": 9.1667, | |
| "eval_samples_per_second": 30.218, | |
| "eval_steps_per_second": 3.818, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.333434522151947, | |
| "eval_runtime": 9.1342, | |
| "eval_samples_per_second": 30.326, | |
| "eval_steps_per_second": 3.832, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 0.0016378205128205127, | |
| "loss": 0.3206, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.33880335092544556, | |
| "eval_runtime": 9.1365, | |
| "eval_samples_per_second": 30.318, | |
| "eval_steps_per_second": 3.831, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 27, | |
| "best_eval_accuracy": 0.740072202166065, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.0015576923076923079, | |
| "loss": 0.3189, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.33039894700050354, | |
| "eval_runtime": 9.1312, | |
| "eval_samples_per_second": 30.335, | |
| "eval_steps_per_second": 3.833, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 27, | |
| "best_eval_accuracy": 0.740072202166065, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.3566158413887024, | |
| "eval_runtime": 9.115, | |
| "eval_samples_per_second": 30.389, | |
| "eval_steps_per_second": 3.84, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 27, | |
| "best_eval_accuracy": 0.740072202166065, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 0.0014775641025641026, | |
| "loss": 0.3148, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.33697280287742615, | |
| "eval_runtime": 9.1237, | |
| "eval_samples_per_second": 30.361, | |
| "eval_steps_per_second": 3.836, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 27, | |
| "best_eval_accuracy": 0.740072202166065, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.33278366923332214, | |
| "eval_runtime": 9.1556, | |
| "eval_samples_per_second": 30.255, | |
| "eval_steps_per_second": 3.823, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 27, | |
| "best_eval_accuracy": 0.740072202166065, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.0013974358974358976, | |
| "loss": 0.31, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.3422046899795532, | |
| "eval_runtime": 9.1388, | |
| "eval_samples_per_second": 30.31, | |
| "eval_steps_per_second": 3.83, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 0.0013173076923076923, | |
| "loss": 0.306, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.3339076340198517, | |
| "eval_runtime": 9.1306, | |
| "eval_samples_per_second": 30.338, | |
| "eval_steps_per_second": 3.833, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.3253796398639679, | |
| "eval_runtime": 9.1502, | |
| "eval_samples_per_second": 30.272, | |
| "eval_steps_per_second": 3.825, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.0012371794871794872, | |
| "loss": 0.3032, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.3329690992832184, | |
| "eval_runtime": 9.1346, | |
| "eval_samples_per_second": 30.324, | |
| "eval_steps_per_second": 3.832, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 0.0011570512820512822, | |
| "loss": 0.3028, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7184115523465704, | |
| "eval_loss": 0.3718496859073639, | |
| "eval_runtime": 9.1526, | |
| "eval_samples_per_second": 30.265, | |
| "eval_steps_per_second": 3.824, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.32942327857017517, | |
| "eval_runtime": 9.1344, | |
| "eval_samples_per_second": 30.325, | |
| "eval_steps_per_second": 3.832, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.0010769230769230769, | |
| "loss": 0.3005, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.3465494215488434, | |
| "eval_runtime": 9.149, | |
| "eval_samples_per_second": 30.277, | |
| "eval_steps_per_second": 3.826, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.33344584703445435, | |
| "eval_runtime": 9.134, | |
| "eval_samples_per_second": 30.326, | |
| "eval_steps_per_second": 3.832, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 0.0009967948717948718, | |
| "loss": 0.2965, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.32391032576560974, | |
| "eval_runtime": 9.1543, | |
| "eval_samples_per_second": 30.259, | |
| "eval_steps_per_second": 3.823, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0009166666666666668, | |
| "loss": 0.2947, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.33224305510520935, | |
| "eval_runtime": 9.1316, | |
| "eval_samples_per_second": 30.334, | |
| "eval_steps_per_second": 3.833, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.3370007574558258, | |
| "eval_runtime": 9.1457, | |
| "eval_samples_per_second": 30.288, | |
| "eval_steps_per_second": 3.827, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 0.0008365384615384616, | |
| "loss": 0.2909, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.3385498523712158, | |
| "eval_runtime": 9.1809, | |
| "eval_samples_per_second": 30.171, | |
| "eval_steps_per_second": 3.812, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.0007564102564102564, | |
| "loss": 0.2915, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.3364669382572174, | |
| "eval_runtime": 9.1472, | |
| "eval_samples_per_second": 30.283, | |
| "eval_steps_per_second": 3.826, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.3435125946998596, | |
| "eval_runtime": 9.1788, | |
| "eval_samples_per_second": 30.178, | |
| "eval_steps_per_second": 3.813, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 0.0006762820512820514, | |
| "loss": 0.29, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.3300550878047943, | |
| "eval_runtime": 9.1805, | |
| "eval_samples_per_second": 30.173, | |
| "eval_steps_per_second": 3.812, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.34428879618644714, | |
| "eval_runtime": 9.1365, | |
| "eval_samples_per_second": 30.318, | |
| "eval_steps_per_second": 3.831, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 0.0005961538461538461, | |
| "loss": 0.2872, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.3392505347728729, | |
| "eval_runtime": 9.1185, | |
| "eval_samples_per_second": 30.378, | |
| "eval_steps_per_second": 3.838, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 0.000516025641025641, | |
| "loss": 0.2838, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.3291374742984772, | |
| "eval_runtime": 9.1502, | |
| "eval_samples_per_second": 30.273, | |
| "eval_steps_per_second": 3.825, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.33556076884269714, | |
| "eval_runtime": 9.1546, | |
| "eval_samples_per_second": 30.258, | |
| "eval_steps_per_second": 3.823, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 0.00043589743589743596, | |
| "loss": 0.2865, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.3306904137134552, | |
| "eval_runtime": 9.1381, | |
| "eval_samples_per_second": 30.313, | |
| "eval_steps_per_second": 3.83, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 0.00035576923076923074, | |
| "loss": 0.2823, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.34133222699165344, | |
| "eval_runtime": 9.1664, | |
| "eval_samples_per_second": 30.219, | |
| "eval_steps_per_second": 3.818, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.3353198766708374, | |
| "eval_runtime": 9.1849, | |
| "eval_samples_per_second": 30.158, | |
| "eval_steps_per_second": 3.811, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 0.0002756410256410257, | |
| "loss": 0.28, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.33145207166671753, | |
| "eval_runtime": 9.1935, | |
| "eval_samples_per_second": 30.13, | |
| "eval_steps_per_second": 3.807, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.34334462881088257, | |
| "eval_runtime": 9.1494, | |
| "eval_samples_per_second": 30.275, | |
| "eval_steps_per_second": 3.825, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 0.00019551282051282054, | |
| "loss": 0.2832, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.33375221490859985, | |
| "eval_runtime": 9.1538, | |
| "eval_samples_per_second": 30.261, | |
| "eval_steps_per_second": 3.824, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 0.0001153846153846154, | |
| "loss": 0.2794, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.3367079198360443, | |
| "eval_runtime": 9.1809, | |
| "eval_samples_per_second": 30.171, | |
| "eval_steps_per_second": 3.812, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.3371344208717346, | |
| "eval_runtime": 3.5086, | |
| "eval_samples_per_second": 78.948, | |
| "eval_steps_per_second": 9.975, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 3.5256410256410254e-05, | |
| "loss": 0.2785, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.33732497692108154, | |
| "eval_runtime": 9.129, | |
| "eval_samples_per_second": 30.343, | |
| "eval_steps_per_second": 3.834, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 0.33913088435800665, | |
| "train_runtime": 8207.561, | |
| "train_samples_per_second": 18.203, | |
| "train_steps_per_second": 2.281 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |