| { | |
| "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": 0.516245487364621, | |
| "eval_loss": 0.37735894322395325, | |
| "eval_runtime": 4.3147, | |
| "eval_samples_per_second": 64.199, | |
| "eval_steps_per_second": 8.112, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.516245487364621, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.003893162393162393, | |
| "loss": 0.5343, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5018050541516246, | |
| "eval_loss": 0.35060495138168335, | |
| "eval_runtime": 4.3354, | |
| "eval_samples_per_second": 63.893, | |
| "eval_steps_per_second": 8.073, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.516245487364621, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.45752400159835815, | |
| "eval_runtime": 4.3375, | |
| "eval_samples_per_second": 63.862, | |
| "eval_steps_per_second": 8.069, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.516245487364621, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.0037863247863247863, | |
| "loss": 0.4659, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5306859205776173, | |
| "eval_loss": 0.3758547008037567, | |
| "eval_runtime": 4.3393, | |
| "eval_samples_per_second": 63.836, | |
| "eval_steps_per_second": 8.066, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 3, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.0036794871794871794, | |
| "loss": 0.4691, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5812274368231047, | |
| "eval_loss": 0.3500436246395111, | |
| "eval_runtime": 4.3557, | |
| "eval_samples_per_second": 63.595, | |
| "eval_steps_per_second": 8.035, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5812274368231047, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5992779783393501, | |
| "eval_loss": 0.345672607421875, | |
| "eval_runtime": 4.342, | |
| "eval_samples_per_second": 63.796, | |
| "eval_steps_per_second": 8.061, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5992779783393501, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.003572649572649573, | |
| "loss": 0.4442, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.6101083032490975, | |
| "eval_loss": 0.34997570514678955, | |
| "eval_runtime": 4.338, | |
| "eval_samples_per_second": 63.854, | |
| "eval_steps_per_second": 8.068, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 6, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6173285198555957, | |
| "eval_loss": 0.3403359055519104, | |
| "eval_runtime": 4.3408, | |
| "eval_samples_per_second": 63.814, | |
| "eval_steps_per_second": 8.063, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.6173285198555957, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.003465811965811966, | |
| "loss": 0.4366, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5776173285198556, | |
| "eval_loss": 0.38398295640945435, | |
| "eval_runtime": 4.3382, | |
| "eval_samples_per_second": 63.852, | |
| "eval_steps_per_second": 8.068, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.6173285198555957, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.003358974358974359, | |
| "loss": 0.4097, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5487364620938628, | |
| "eval_loss": 0.43909069895744324, | |
| "eval_runtime": 4.3443, | |
| "eval_samples_per_second": 63.762, | |
| "eval_steps_per_second": 8.057, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.6173285198555957, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6028880866425993, | |
| "eval_loss": 0.35843461751937866, | |
| "eval_runtime": 4.3422, | |
| "eval_samples_per_second": 63.793, | |
| "eval_steps_per_second": 8.06, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.6173285198555957, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 0.0032521367521367523, | |
| "loss": 0.3922, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6498194945848376, | |
| "eval_loss": 0.33557796478271484, | |
| "eval_runtime": 4.3425, | |
| "eval_samples_per_second": 63.788, | |
| "eval_steps_per_second": 8.06, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.6498194945848376, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.0031452991452991454, | |
| "loss": 0.3564, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.6931407942238267, | |
| "eval_loss": 0.32750093936920166, | |
| "eval_runtime": 4.3335, | |
| "eval_samples_per_second": 63.921, | |
| "eval_steps_per_second": 8.077, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 12, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.32828277349472046, | |
| "eval_runtime": 4.3334, | |
| "eval_samples_per_second": 63.922, | |
| "eval_steps_per_second": 8.077, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.7075812274368231, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 0.0030384615384615385, | |
| "loss": 0.3343, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.6462093862815884, | |
| "eval_loss": 0.3377060890197754, | |
| "eval_runtime": 4.3243, | |
| "eval_samples_per_second": 64.056, | |
| "eval_steps_per_second": 8.094, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.7075812274368231, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6389891696750902, | |
| "eval_loss": 0.35497620701789856, | |
| "eval_runtime": 4.328, | |
| "eval_samples_per_second": 64.002, | |
| "eval_steps_per_second": 8.087, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.7075812274368231, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.0029316239316239316, | |
| "loss": 0.335, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.6895306859205776, | |
| "eval_loss": 0.3370417058467865, | |
| "eval_runtime": 4.3279, | |
| "eval_samples_per_second": 64.003, | |
| "eval_steps_per_second": 8.087, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.7075812274368231, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.002824786324786325, | |
| "loss": 0.3233, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.6787003610108303, | |
| "eval_loss": 0.32560163736343384, | |
| "eval_runtime": 4.3346, | |
| "eval_samples_per_second": 63.904, | |
| "eval_steps_per_second": 8.075, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.7075812274368231, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7111913357400722, | |
| "eval_loss": 0.31737250089645386, | |
| "eval_runtime": 4.3417, | |
| "eval_samples_per_second": 63.8, | |
| "eval_steps_per_second": 8.061, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7111913357400722, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.0027179487179487182, | |
| "loss": 0.3232, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6642599277978339, | |
| "eval_loss": 0.34402281045913696, | |
| "eval_runtime": 4.3368, | |
| "eval_samples_per_second": 63.872, | |
| "eval_steps_per_second": 8.07, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7111913357400722, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 0.0026111111111111114, | |
| "loss": 0.3102, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.6895306859205776, | |
| "eval_loss": 0.3374693691730499, | |
| "eval_runtime": 4.3363, | |
| "eval_samples_per_second": 63.879, | |
| "eval_steps_per_second": 8.071, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7111913357400722, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.6787003610108303, | |
| "eval_loss": 0.3433131277561188, | |
| "eval_runtime": 4.3244, | |
| "eval_samples_per_second": 64.055, | |
| "eval_steps_per_second": 8.094, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7111913357400722, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.0025042735042735045, | |
| "loss": 0.3064, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.6714801444043321, | |
| "eval_loss": 0.36901581287384033, | |
| "eval_runtime": 4.3278, | |
| "eval_samples_per_second": 64.005, | |
| "eval_steps_per_second": 8.087, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7111913357400722, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6931407942238267, | |
| "eval_loss": 0.3393624722957611, | |
| "eval_runtime": 4.332, | |
| "eval_samples_per_second": 63.943, | |
| "eval_steps_per_second": 8.079, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7111913357400722, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 0.0023974358974358976, | |
| "loss": 0.3004, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.3376837372779846, | |
| "eval_runtime": 4.3275, | |
| "eval_samples_per_second": 64.009, | |
| "eval_steps_per_second": 8.088, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.7256317689530686, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.0022905982905982907, | |
| "loss": 0.2962, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.6750902527075813, | |
| "eval_loss": 0.34352612495422363, | |
| "eval_runtime": 4.336, | |
| "eval_samples_per_second": 63.884, | |
| "eval_steps_per_second": 8.072, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.7256317689530686, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.31822633743286133, | |
| "eval_runtime": 4.336, | |
| "eval_samples_per_second": 63.884, | |
| "eval_steps_per_second": 8.072, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 0.002183760683760684, | |
| "loss": 0.2937, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7111913357400722, | |
| "eval_loss": 0.3305753767490387, | |
| "eval_runtime": 4.3337, | |
| "eval_samples_per_second": 63.918, | |
| "eval_steps_per_second": 8.076, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.0020769230769230773, | |
| "loss": 0.2905, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.3361673057079315, | |
| "eval_runtime": 4.3378, | |
| "eval_samples_per_second": 63.857, | |
| "eval_steps_per_second": 8.069, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.6750902527075813, | |
| "eval_loss": 0.36750420928001404, | |
| "eval_runtime": 4.3383, | |
| "eval_samples_per_second": 63.85, | |
| "eval_steps_per_second": 8.068, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 0.0019700854700854704, | |
| "loss": 0.2865, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.34060072898864746, | |
| "eval_runtime": 4.3406, | |
| "eval_samples_per_second": 63.816, | |
| "eval_steps_per_second": 8.063, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.334277480840683, | |
| "eval_runtime": 4.3332, | |
| "eval_samples_per_second": 63.924, | |
| "eval_steps_per_second": 8.077, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.0018632478632478633, | |
| "loss": 0.2812, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.6859205776173285, | |
| "eval_loss": 0.34722989797592163, | |
| "eval_runtime": 4.3283, | |
| "eval_samples_per_second": 63.998, | |
| "eval_steps_per_second": 8.086, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 0.0017564102564102564, | |
| "loss": 0.2727, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.337159126996994, | |
| "eval_runtime": 4.3326, | |
| "eval_samples_per_second": 63.933, | |
| "eval_steps_per_second": 8.078, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.35748186707496643, | |
| "eval_runtime": 4.3343, | |
| "eval_samples_per_second": 63.909, | |
| "eval_steps_per_second": 8.075, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.0016495726495726495, | |
| "loss": 0.2735, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.3299775719642639, | |
| "eval_runtime": 4.3421, | |
| "eval_samples_per_second": 63.794, | |
| "eval_steps_per_second": 8.061, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 0.0015427350427350429, | |
| "loss": 0.2701, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.6967509025270758, | |
| "eval_loss": 0.3585418164730072, | |
| "eval_runtime": 4.3353, | |
| "eval_samples_per_second": 63.894, | |
| "eval_steps_per_second": 8.073, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.3422161340713501, | |
| "eval_runtime": 4.3273, | |
| "eval_samples_per_second": 64.012, | |
| "eval_steps_per_second": 8.088, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.001435897435897436, | |
| "loss": 0.2688, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.6931407942238267, | |
| "eval_loss": 0.3579197824001312, | |
| "eval_runtime": 4.3267, | |
| "eval_samples_per_second": 64.021, | |
| "eval_steps_per_second": 8.089, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.33261609077453613, | |
| "eval_runtime": 4.3229, | |
| "eval_samples_per_second": 64.078, | |
| "eval_steps_per_second": 8.097, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 0.001329059829059829, | |
| "loss": 0.2644, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.3463744819164276, | |
| "eval_runtime": 4.3279, | |
| "eval_samples_per_second": 64.003, | |
| "eval_steps_per_second": 8.087, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0012222222222222224, | |
| "loss": 0.2637, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.6931407942238267, | |
| "eval_loss": 0.35785871744155884, | |
| "eval_runtime": 4.3221, | |
| "eval_samples_per_second": 64.089, | |
| "eval_steps_per_second": 8.098, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.3489207327365875, | |
| "eval_runtime": 4.3156, | |
| "eval_samples_per_second": 64.186, | |
| "eval_steps_per_second": 8.11, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 0.0011153846153846155, | |
| "loss": 0.26, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.3438562750816345, | |
| "eval_runtime": 4.3177, | |
| "eval_samples_per_second": 64.154, | |
| "eval_steps_per_second": 8.106, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.0010085470085470086, | |
| "loss": 0.2582, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7003610108303249, | |
| "eval_loss": 0.3585074543952942, | |
| "eval_runtime": 4.3123, | |
| "eval_samples_per_second": 64.235, | |
| "eval_steps_per_second": 8.116, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.35347476601600647, | |
| "eval_runtime": 4.3136, | |
| "eval_samples_per_second": 64.215, | |
| "eval_steps_per_second": 8.114, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 0.0009017094017094017, | |
| "loss": 0.2533, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.34402725100517273, | |
| "eval_runtime": 4.315, | |
| "eval_samples_per_second": 64.194, | |
| "eval_steps_per_second": 8.111, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.3505990207195282, | |
| "eval_runtime": 4.3143, | |
| "eval_samples_per_second": 64.206, | |
| "eval_steps_per_second": 8.113, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 0.0007948717948717948, | |
| "loss": 0.2535, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.35185110569000244, | |
| "eval_runtime": 4.3151, | |
| "eval_samples_per_second": 64.193, | |
| "eval_steps_per_second": 8.111, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 0.0006880341880341881, | |
| "loss": 0.2498, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.6931407942238267, | |
| "eval_loss": 0.3456619083881378, | |
| "eval_runtime": 4.3131, | |
| "eval_samples_per_second": 64.223, | |
| "eval_steps_per_second": 8.115, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7111913357400722, | |
| "eval_loss": 0.34943750500679016, | |
| "eval_runtime": 4.314, | |
| "eval_samples_per_second": 64.21, | |
| "eval_steps_per_second": 8.113, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 0.0005811965811965813, | |
| "loss": 0.2504, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.3430747985839844, | |
| "eval_runtime": 4.3163, | |
| "eval_samples_per_second": 64.176, | |
| "eval_steps_per_second": 8.109, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 0.00047435897435897434, | |
| "loss": 0.2499, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.34503889083862305, | |
| "eval_runtime": 4.3129, | |
| "eval_samples_per_second": 64.226, | |
| "eval_steps_per_second": 8.115, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.6895306859205776, | |
| "eval_loss": 0.3484850227832794, | |
| "eval_runtime": 4.3131, | |
| "eval_samples_per_second": 64.223, | |
| "eval_steps_per_second": 8.115, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 0.00036752136752136755, | |
| "loss": 0.2488, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7003610108303249, | |
| "eval_loss": 0.3436543345451355, | |
| "eval_runtime": 4.3132, | |
| "eval_samples_per_second": 64.222, | |
| "eval_steps_per_second": 8.115, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7003610108303249, | |
| "eval_loss": 0.3464801013469696, | |
| "eval_runtime": 4.3155, | |
| "eval_samples_per_second": 64.187, | |
| "eval_steps_per_second": 8.11, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 0.0002606837606837607, | |
| "loss": 0.2479, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.6895306859205776, | |
| "eval_loss": 0.34788957238197327, | |
| "eval_runtime": 4.3164, | |
| "eval_samples_per_second": 64.173, | |
| "eval_steps_per_second": 8.109, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 0.247, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7003610108303249, | |
| "eval_loss": 0.34465810656547546, | |
| "eval_runtime": 4.3158, | |
| "eval_samples_per_second": 64.183, | |
| "eval_steps_per_second": 8.11, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7003610108303249, | |
| "eval_loss": 0.3520893454551697, | |
| "eval_runtime": 4.3122, | |
| "eval_samples_per_second": 64.236, | |
| "eval_steps_per_second": 8.116, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 4.700854700854701e-05, | |
| "loss": 0.2468, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.6967509025270758, | |
| "eval_loss": 0.3493305444717407, | |
| "eval_runtime": 4.3274, | |
| "eval_samples_per_second": 64.011, | |
| "eval_steps_per_second": 8.088, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 0.3118535759102585, | |
| "train_runtime": 3964.0197, | |
| "train_samples_per_second": 37.689, | |
| "train_steps_per_second": 4.722 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |