| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 60.0, | |
| "global_step": 9360, | |
| "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": 0.4740632474422455, | |
| "eval_runtime": 9.255, | |
| "eval_samples_per_second": 29.93, | |
| "eval_steps_per_second": 3.782, | |
| "step": 156 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 1.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5090252707581228, | |
| "eval_loss": 0.3849472999572754, | |
| "eval_runtime": 9.2931, | |
| "eval_samples_per_second": 29.807, | |
| "eval_steps_per_second": 3.766, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 2.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.434469997882843, | |
| "eval_runtime": 9.1899, | |
| "eval_samples_per_second": 30.142, | |
| "eval_steps_per_second": 3.809, | |
| "step": 468 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 3.0, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.0037863247863247863, | |
| "loss": 0.5496, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5234657039711191, | |
| "eval_loss": 0.4748525321483612, | |
| "eval_runtime": 9.2109, | |
| "eval_samples_per_second": 30.073, | |
| "eval_steps_per_second": 3.8, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 4.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5342960288808665, | |
| "eval_loss": 0.41381731629371643, | |
| "eval_runtime": 9.2454, | |
| "eval_samples_per_second": 29.961, | |
| "eval_steps_per_second": 3.786, | |
| "step": 780 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 5.0, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5631768953068592, | |
| "eval_loss": 0.3598599135875702, | |
| "eval_runtime": 3.6132, | |
| "eval_samples_per_second": 76.664, | |
| "eval_steps_per_second": 9.687, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5631768953068592, | |
| "epoch": 6.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.003572649572649573, | |
| "loss": 0.4365, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5631768953068592, | |
| "eval_loss": 0.395423024892807, | |
| "eval_runtime": 9.3371, | |
| "eval_samples_per_second": 29.666, | |
| "eval_steps_per_second": 3.748, | |
| "step": 1092 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5631768953068592, | |
| "epoch": 7.0, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5018050541516246, | |
| "eval_loss": 0.34552210569381714, | |
| "eval_runtime": 9.3479, | |
| "eval_samples_per_second": 29.632, | |
| "eval_steps_per_second": 3.744, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5631768953068592, | |
| "epoch": 8.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5776173285198556, | |
| "eval_loss": 0.39849764108657837, | |
| "eval_runtime": 9.338, | |
| "eval_samples_per_second": 29.664, | |
| "eval_steps_per_second": 3.748, | |
| "step": 1404 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5776173285198556, | |
| "epoch": 9.0, | |
| "step": 1404 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.003358974358974359, | |
| "loss": 0.4109, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5992779783393501, | |
| "eval_loss": 0.3827930986881256, | |
| "eval_runtime": 9.2193, | |
| "eval_samples_per_second": 30.046, | |
| "eval_steps_per_second": 3.796, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 9, | |
| "best_eval_accuracy": 0.5992779783393501, | |
| "epoch": 10.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.4339348375797272, | |
| "eval_runtime": 9.1599, | |
| "eval_samples_per_second": 30.24, | |
| "eval_steps_per_second": 3.821, | |
| "step": 1716 | |
| }, | |
| { | |
| "best_epoch": 9, | |
| "best_eval_accuracy": 0.5992779783393501, | |
| "epoch": 11.0, | |
| "step": 1716 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5379061371841155, | |
| "eval_loss": 0.34316927194595337, | |
| "eval_runtime": 8.9867, | |
| "eval_samples_per_second": 30.823, | |
| "eval_steps_per_second": 3.895, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 9, | |
| "best_eval_accuracy": 0.5992779783393501, | |
| "epoch": 12.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.0031452991452991454, | |
| "loss": 0.3611, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.6137184115523465, | |
| "eval_loss": 0.33951735496520996, | |
| "eval_runtime": 9.3311, | |
| "eval_samples_per_second": 29.686, | |
| "eval_steps_per_second": 3.751, | |
| "step": 2028 | |
| }, | |
| { | |
| "best_epoch": 12, | |
| "best_eval_accuracy": 0.6137184115523465, | |
| "epoch": 13.0, | |
| "step": 2028 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6714801444043321, | |
| "eval_loss": 0.3404270112514496, | |
| "eval_runtime": 9.3325, | |
| "eval_samples_per_second": 29.681, | |
| "eval_steps_per_second": 3.75, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.6714801444043321, | |
| "epoch": 14.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.6570397111913358, | |
| "eval_loss": 0.3395780026912689, | |
| "eval_runtime": 9.3018, | |
| "eval_samples_per_second": 29.779, | |
| "eval_steps_per_second": 3.763, | |
| "step": 2340 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.6714801444043321, | |
| "epoch": 15.0, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6353790613718412, | |
| "eval_loss": 0.3856579065322876, | |
| "eval_runtime": 9.3146, | |
| "eval_samples_per_second": 29.738, | |
| "eval_steps_per_second": 3.758, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.6714801444043321, | |
| "epoch": 16.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.0029316239316239316, | |
| "loss": 0.3456, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.6895306859205776, | |
| "eval_loss": 0.348003625869751, | |
| "eval_runtime": 9.3161, | |
| "eval_samples_per_second": 29.734, | |
| "eval_steps_per_second": 3.757, | |
| "step": 2652 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.6895306859205776, | |
| "epoch": 17.0, | |
| "step": 2652 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.33484789729118347, | |
| "eval_runtime": 9.253, | |
| "eval_samples_per_second": 29.936, | |
| "eval_steps_per_second": 3.783, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 17, | |
| "best_eval_accuracy": 0.703971119133574, | |
| "epoch": 18.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.6425992779783394, | |
| "eval_loss": 0.33233121037483215, | |
| "eval_runtime": 9.3192, | |
| "eval_samples_per_second": 29.724, | |
| "eval_steps_per_second": 3.756, | |
| "step": 2964 | |
| }, | |
| { | |
| "best_epoch": 17, | |
| "best_eval_accuracy": 0.703971119133574, | |
| "epoch": 19.0, | |
| "step": 2964 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.0027179487179487182, | |
| "loss": 0.3391, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6714801444043321, | |
| "eval_loss": 0.359100878238678, | |
| "eval_runtime": 9.2605, | |
| "eval_samples_per_second": 29.912, | |
| "eval_steps_per_second": 3.78, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 17, | |
| "best_eval_accuracy": 0.703971119133574, | |
| "epoch": 20.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.33779582381248474, | |
| "eval_runtime": 9.5614, | |
| "eval_samples_per_second": 28.971, | |
| "eval_steps_per_second": 3.661, | |
| "step": 3276 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 21.0, | |
| "step": 3276 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7003610108303249, | |
| "eval_loss": 0.3452521562576294, | |
| "eval_runtime": 9.6177, | |
| "eval_samples_per_second": 28.801, | |
| "eval_steps_per_second": 3.639, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 22.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.0025042735042735045, | |
| "loss": 0.3319, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.6678700361010831, | |
| "eval_loss": 0.34050798416137695, | |
| "eval_runtime": 9.2679, | |
| "eval_samples_per_second": 29.888, | |
| "eval_steps_per_second": 3.776, | |
| "step": 3588 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 23.0, | |
| "step": 3588 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6389891696750902, | |
| "eval_loss": 0.34506645798683167, | |
| "eval_runtime": 9.2745, | |
| "eval_samples_per_second": 29.867, | |
| "eval_steps_per_second": 3.774, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 24.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.6895306859205776, | |
| "eval_loss": 0.36652639508247375, | |
| "eval_runtime": 9.4067, | |
| "eval_samples_per_second": 29.447, | |
| "eval_steps_per_second": 3.721, | |
| "step": 3900 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 25.0, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.0022905982905982907, | |
| "loss": 0.3274, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7111913357400722, | |
| "eval_loss": 0.32902663946151733, | |
| "eval_runtime": 9.2506, | |
| "eval_samples_per_second": 29.944, | |
| "eval_steps_per_second": 3.784, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 26.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.3251630365848541, | |
| "eval_runtime": 9.2957, | |
| "eval_samples_per_second": 29.799, | |
| "eval_steps_per_second": 3.765, | |
| "step": 4212 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 27.0, | |
| "step": 4212 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7184115523465704, | |
| "eval_loss": 0.3264797031879425, | |
| "eval_runtime": 9.1811, | |
| "eval_samples_per_second": 30.171, | |
| "eval_steps_per_second": 3.812, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 27, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 28.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.0020769230769230773, | |
| "loss": 0.3214, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.32835328578948975, | |
| "eval_runtime": 9.1497, | |
| "eval_samples_per_second": 30.274, | |
| "eval_steps_per_second": 3.825, | |
| "step": 4524 | |
| }, | |
| { | |
| "best_epoch": 28, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 29.0, | |
| "step": 4524 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.3290432393550873, | |
| "eval_runtime": 8.9091, | |
| "eval_samples_per_second": 31.092, | |
| "eval_steps_per_second": 3.929, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 30.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.3327571749687195, | |
| "eval_runtime": 8.8998, | |
| "eval_samples_per_second": 31.124, | |
| "eval_steps_per_second": 3.933, | |
| "step": 4836 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 31.0, | |
| "step": 4836 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7220216606498195, | |
| "eval_loss": 0.3268325626850128, | |
| "eval_runtime": 8.9031, | |
| "eval_samples_per_second": 31.113, | |
| "eval_steps_per_second": 3.931, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 32.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.0018632478632478633, | |
| "loss": 0.3167, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7220216606498195, | |
| "eval_loss": 0.3372153341770172, | |
| "eval_runtime": 8.8917, | |
| "eval_samples_per_second": 31.153, | |
| "eval_steps_per_second": 3.936, | |
| "step": 5148 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 33.0, | |
| "step": 5148 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.32633286714553833, | |
| "eval_runtime": 8.8844, | |
| "eval_samples_per_second": 31.178, | |
| "eval_steps_per_second": 3.939, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 34.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.32305726408958435, | |
| "eval_runtime": 8.9015, | |
| "eval_samples_per_second": 31.118, | |
| "eval_steps_per_second": 3.932, | |
| "step": 5460 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 35.0, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.0016495726495726495, | |
| "loss": 0.312, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.325504332780838, | |
| "eval_runtime": 8.9164, | |
| "eval_samples_per_second": 31.066, | |
| "eval_steps_per_second": 3.925, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 36.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.33250829577445984, | |
| "eval_runtime": 8.8964, | |
| "eval_samples_per_second": 31.136, | |
| "eval_steps_per_second": 3.934, | |
| "step": 5772 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 37.0, | |
| "step": 5772 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.3350552022457123, | |
| "eval_runtime": 8.8999, | |
| "eval_samples_per_second": 31.124, | |
| "eval_steps_per_second": 3.933, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 38.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.001435897435897436, | |
| "loss": 0.3083, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.3361571431159973, | |
| "eval_runtime": 8.8805, | |
| "eval_samples_per_second": 31.192, | |
| "eval_steps_per_second": 3.941, | |
| "step": 6084 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 39.0, | |
| "step": 6084 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.33255627751350403, | |
| "eval_runtime": 8.896, | |
| "eval_samples_per_second": 31.138, | |
| "eval_steps_per_second": 3.934, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 40.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7220216606498195, | |
| "eval_loss": 0.3366214632987976, | |
| "eval_runtime": 8.8975, | |
| "eval_samples_per_second": 31.132, | |
| "eval_steps_per_second": 3.934, | |
| "step": 6396 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 41.0, | |
| "step": 6396 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0012222222222222224, | |
| "loss": 0.3081, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.3264662027359009, | |
| "eval_runtime": 8.9131, | |
| "eval_samples_per_second": 31.078, | |
| "eval_steps_per_second": 3.927, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 42.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.3351312577724457, | |
| "eval_runtime": 8.9174, | |
| "eval_samples_per_second": 31.063, | |
| "eval_steps_per_second": 3.925, | |
| "step": 6708 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 43.0, | |
| "step": 6708 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.3383844196796417, | |
| "eval_runtime": 8.9057, | |
| "eval_samples_per_second": 31.104, | |
| "eval_steps_per_second": 3.93, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 44.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.0010085470085470086, | |
| "loss": 0.3032, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7220216606498195, | |
| "eval_loss": 0.32982781529426575, | |
| "eval_runtime": 8.8961, | |
| "eval_samples_per_second": 31.137, | |
| "eval_steps_per_second": 3.934, | |
| "step": 7020 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 45.0, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.3309342563152313, | |
| "eval_runtime": 8.8931, | |
| "eval_samples_per_second": 31.148, | |
| "eval_steps_per_second": 3.936, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 46.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.3318590819835663, | |
| "eval_runtime": 8.8948, | |
| "eval_samples_per_second": 31.142, | |
| "eval_steps_per_second": 3.935, | |
| "step": 7332 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 47.0, | |
| "step": 7332 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.34517648816108704, | |
| "eval_runtime": 8.9043, | |
| "eval_samples_per_second": 31.108, | |
| "eval_steps_per_second": 3.931, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 48.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 0.0007948717948717948, | |
| "loss": 0.2998, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.3364735543727875, | |
| "eval_runtime": 8.9076, | |
| "eval_samples_per_second": 31.097, | |
| "eval_steps_per_second": 3.929, | |
| "step": 7644 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 49.0, | |
| "step": 7644 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.3290213346481323, | |
| "eval_runtime": 8.8977, | |
| "eval_samples_per_second": 31.132, | |
| "eval_steps_per_second": 3.934, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 50.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7509025270758123, | |
| "eval_loss": 0.3251466155052185, | |
| "eval_runtime": 8.9086, | |
| "eval_samples_per_second": 31.093, | |
| "eval_steps_per_second": 3.929, | |
| "step": 7956 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7509025270758123, | |
| "epoch": 51.0, | |
| "step": 7956 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 0.0005811965811965813, | |
| "loss": 0.2989, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.3253740072250366, | |
| "eval_runtime": 8.8806, | |
| "eval_samples_per_second": 31.192, | |
| "eval_steps_per_second": 3.941, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7509025270758123, | |
| "epoch": 52.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.3372468054294586, | |
| "eval_runtime": 8.9258, | |
| "eval_samples_per_second": 31.034, | |
| "eval_steps_per_second": 3.921, | |
| "step": 8268 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7509025270758123, | |
| "epoch": 53.0, | |
| "step": 8268 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.340105801820755, | |
| "eval_runtime": 8.9051, | |
| "eval_samples_per_second": 31.106, | |
| "eval_steps_per_second": 3.93, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7509025270758123, | |
| "epoch": 54.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 0.00036752136752136755, | |
| "loss": 0.2951, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.33145537972450256, | |
| "eval_runtime": 8.91, | |
| "eval_samples_per_second": 31.089, | |
| "eval_steps_per_second": 3.928, | |
| "step": 8580 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7509025270758123, | |
| "epoch": 55.0, | |
| "step": 8580 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.33449816703796387, | |
| "eval_runtime": 8.899, | |
| "eval_samples_per_second": 31.127, | |
| "eval_steps_per_second": 3.933, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7509025270758123, | |
| "epoch": 56.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.33013680577278137, | |
| "eval_runtime": 8.9036, | |
| "eval_samples_per_second": 31.111, | |
| "eval_steps_per_second": 3.931, | |
| "step": 8892 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7509025270758123, | |
| "epoch": 57.0, | |
| "step": 8892 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 0.2945, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.3321804106235504, | |
| "eval_runtime": 9.3599, | |
| "eval_samples_per_second": 29.594, | |
| "eval_steps_per_second": 3.739, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7509025270758123, | |
| "epoch": 58.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.3304736912250519, | |
| "eval_runtime": 9.3479, | |
| "eval_samples_per_second": 29.632, | |
| "eval_steps_per_second": 3.744, | |
| "step": 9204 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7509025270758123, | |
| "epoch": 59.0, | |
| "step": 9204 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.3315790295600891, | |
| "eval_runtime": 9.3813, | |
| "eval_samples_per_second": 29.527, | |
| "eval_steps_per_second": 3.731, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7509025270758123, | |
| "epoch": 60.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 9360, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 0.34035047710451305, | |
| "train_runtime": 7833.6103, | |
| "train_samples_per_second": 19.072, | |
| "train_steps_per_second": 1.195 | |
| } | |
| ], | |
| "max_steps": 9360, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |