| { | |
| "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": 0.4693140794223827, | |
| "eval_loss": 0.554839015007019, | |
| "eval_runtime": 4.3616, | |
| "eval_samples_per_second": 63.509, | |
| "eval_steps_per_second": 8.025, | |
| "step": 156 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.4693140794223827, | |
| "epoch": 1.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.48375451263537905, | |
| "eval_loss": 0.5564807653427124, | |
| "eval_runtime": 4.4769, | |
| "eval_samples_per_second": 61.873, | |
| "eval_steps_per_second": 7.818, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.48375451263537905, | |
| "epoch": 2.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.5531193017959595, | |
| "eval_runtime": 4.5245, | |
| "eval_samples_per_second": 61.222, | |
| "eval_steps_per_second": 7.736, | |
| "step": 468 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.48375451263537905, | |
| "epoch": 3.0, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.0028397435897435895, | |
| "loss": 0.6259, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.5810030698776245, | |
| "eval_runtime": 4.5312, | |
| "eval_samples_per_second": 61.131, | |
| "eval_steps_per_second": 7.724, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.48375451263537905, | |
| "epoch": 4.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5595667870036101, | |
| "eval_loss": 0.6009803414344788, | |
| "eval_runtime": 4.5226, | |
| "eval_samples_per_second": 61.249, | |
| "eval_steps_per_second": 7.739, | |
| "step": 780 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 5.0, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6462093862815884, | |
| "eval_loss": 0.49691498279571533, | |
| "eval_runtime": 4.5117, | |
| "eval_samples_per_second": 61.396, | |
| "eval_steps_per_second": 7.758, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.6462093862815884, | |
| "epoch": 6.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.00267948717948718, | |
| "loss": 0.5907, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5487364620938628, | |
| "eval_loss": 0.7981559634208679, | |
| "eval_runtime": 4.518, | |
| "eval_samples_per_second": 61.31, | |
| "eval_steps_per_second": 7.747, | |
| "step": 1092 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.6462093862815884, | |
| "epoch": 7.0, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.631768953068592, | |
| "eval_loss": 0.4882575571537018, | |
| "eval_runtime": 4.5152, | |
| "eval_samples_per_second": 61.349, | |
| "eval_steps_per_second": 7.752, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.6462093862815884, | |
| "epoch": 8.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6931407942238267, | |
| "eval_loss": 0.4714406132698059, | |
| "eval_runtime": 4.5186, | |
| "eval_samples_per_second": 61.302, | |
| "eval_steps_per_second": 7.746, | |
| "step": 1404 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 9.0, | |
| "step": 1404 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.0025192307692307693, | |
| "loss": 0.5602, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.555956678700361, | |
| "eval_loss": 0.9236112236976624, | |
| "eval_runtime": 4.512, | |
| "eval_samples_per_second": 61.391, | |
| "eval_steps_per_second": 7.757, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 10.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6967509025270758, | |
| "eval_loss": 0.49723225831985474, | |
| "eval_runtime": 4.5165, | |
| "eval_samples_per_second": 61.331, | |
| "eval_steps_per_second": 7.749, | |
| "step": 1716 | |
| }, | |
| { | |
| "best_epoch": 10, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 11.0, | |
| "step": 1716 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6895306859205776, | |
| "eval_loss": 0.5116312503814697, | |
| "eval_runtime": 4.5179, | |
| "eval_samples_per_second": 61.311, | |
| "eval_steps_per_second": 7.747, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 10, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 12.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.002358974358974359, | |
| "loss": 0.5015, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.4912594258785248, | |
| "eval_runtime": 4.519, | |
| "eval_samples_per_second": 61.296, | |
| "eval_steps_per_second": 7.745, | |
| "step": 2028 | |
| }, | |
| { | |
| "best_epoch": 12, | |
| "best_eval_accuracy": 0.7075812274368231, | |
| "epoch": 13.0, | |
| "step": 2028 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7111913357400722, | |
| "eval_loss": 0.4682758152484894, | |
| "eval_runtime": 4.5179, | |
| "eval_samples_per_second": 61.311, | |
| "eval_steps_per_second": 7.747, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.7111913357400722, | |
| "epoch": 14.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.6895306859205776, | |
| "eval_loss": 0.5264927744865417, | |
| "eval_runtime": 4.5188, | |
| "eval_samples_per_second": 61.3, | |
| "eval_steps_per_second": 7.745, | |
| "step": 2340 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.7111913357400722, | |
| "epoch": 15.0, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.4616451859474182, | |
| "eval_runtime": 4.5164, | |
| "eval_samples_per_second": 61.332, | |
| "eval_steps_per_second": 7.749, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.7111913357400722, | |
| "epoch": 16.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.0021987179487179486, | |
| "loss": 0.4782, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.6678700361010831, | |
| "eval_loss": 0.5787555575370789, | |
| "eval_runtime": 4.5274, | |
| "eval_samples_per_second": 61.183, | |
| "eval_steps_per_second": 7.731, | |
| "step": 2652 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.7111913357400722, | |
| "epoch": 17.0, | |
| "step": 2652 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.44711267948150635, | |
| "eval_runtime": 4.5354, | |
| "eval_samples_per_second": 61.076, | |
| "eval_steps_per_second": 7.717, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 17, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 18.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7545126353790613, | |
| "eval_loss": 0.458781361579895, | |
| "eval_runtime": 4.5233, | |
| "eval_samples_per_second": 61.239, | |
| "eval_steps_per_second": 7.738, | |
| "step": 2964 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 19.0, | |
| "step": 2964 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.0020384615384615385, | |
| "loss": 0.4628, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6425992779783394, | |
| "eval_loss": 0.6477251648902893, | |
| "eval_runtime": 4.5142, | |
| "eval_samples_per_second": 61.362, | |
| "eval_steps_per_second": 7.753, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 20.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.6967509025270758, | |
| "eval_loss": 0.5305241942405701, | |
| "eval_runtime": 4.5156, | |
| "eval_samples_per_second": 61.343, | |
| "eval_steps_per_second": 7.751, | |
| "step": 3276 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 21.0, | |
| "step": 3276 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.4549444615840912, | |
| "eval_runtime": 4.5147, | |
| "eval_samples_per_second": 61.355, | |
| "eval_steps_per_second": 7.752, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 22.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.0018782051282051281, | |
| "loss": 0.4248, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.510131299495697, | |
| "eval_runtime": 4.5083, | |
| "eval_samples_per_second": 61.443, | |
| "eval_steps_per_second": 7.764, | |
| "step": 3588 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 23.0, | |
| "step": 3588 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7184115523465704, | |
| "eval_loss": 0.47630512714385986, | |
| "eval_runtime": 4.5103, | |
| "eval_samples_per_second": 61.415, | |
| "eval_steps_per_second": 7.76, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 24.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.6895306859205776, | |
| "eval_loss": 0.580871045589447, | |
| "eval_runtime": 4.5211, | |
| "eval_samples_per_second": 61.269, | |
| "eval_steps_per_second": 7.742, | |
| "step": 3900 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 25.0, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.0017179487179487178, | |
| "loss": 0.4067, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.44606083631515503, | |
| "eval_runtime": 4.512, | |
| "eval_samples_per_second": 61.392, | |
| "eval_steps_per_second": 7.757, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 26.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.44597113132476807, | |
| "eval_runtime": 4.5146, | |
| "eval_samples_per_second": 61.356, | |
| "eval_steps_per_second": 7.753, | |
| "step": 4212 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 27.0, | |
| "step": 4212 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7509025270758123, | |
| "eval_loss": 0.4453907907009125, | |
| "eval_runtime": 4.5068, | |
| "eval_samples_per_second": 61.462, | |
| "eval_steps_per_second": 7.766, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 28.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.0015576923076923079, | |
| "loss": 0.3941, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.4664019048213959, | |
| "eval_runtime": 4.5147, | |
| "eval_samples_per_second": 61.355, | |
| "eval_steps_per_second": 7.752, | |
| "step": 4524 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 29.0, | |
| "step": 4524 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.5038701295852661, | |
| "eval_runtime": 4.5095, | |
| "eval_samples_per_second": 61.426, | |
| "eval_steps_per_second": 7.761, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 30.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.45480838418006897, | |
| "eval_runtime": 4.5065, | |
| "eval_samples_per_second": 61.467, | |
| "eval_steps_per_second": 7.767, | |
| "step": 4836 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 31.0, | |
| "step": 4836 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.448424369096756, | |
| "eval_runtime": 4.5029, | |
| "eval_samples_per_second": 61.516, | |
| "eval_steps_per_second": 7.773, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 32.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.0013974358974358976, | |
| "loss": 0.3749, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.49240007996559143, | |
| "eval_runtime": 4.5076, | |
| "eval_samples_per_second": 61.452, | |
| "eval_steps_per_second": 7.765, | |
| "step": 5148 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 33.0, | |
| "step": 5148 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.45687469840049744, | |
| "eval_runtime": 4.5091, | |
| "eval_samples_per_second": 61.432, | |
| "eval_steps_per_second": 7.762, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 34.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7617328519855595, | |
| "eval_loss": 0.4603608548641205, | |
| "eval_runtime": 4.5099, | |
| "eval_samples_per_second": 61.42, | |
| "eval_steps_per_second": 7.761, | |
| "step": 5460 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 35.0, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.0012371794871794872, | |
| "loss": 0.3586, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7653429602888087, | |
| "eval_loss": 0.4447592794895172, | |
| "eval_runtime": 4.5158, | |
| "eval_samples_per_second": 61.34, | |
| "eval_steps_per_second": 7.751, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 36.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.47678714990615845, | |
| "eval_runtime": 4.5221, | |
| "eval_samples_per_second": 61.254, | |
| "eval_steps_per_second": 7.74, | |
| "step": 5772 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 37.0, | |
| "step": 5772 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.5052057504653931, | |
| "eval_runtime": 4.5169, | |
| "eval_samples_per_second": 61.325, | |
| "eval_steps_per_second": 7.749, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 38.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.0010769230769230769, | |
| "loss": 0.3521, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.5166675448417664, | |
| "eval_runtime": 4.5231, | |
| "eval_samples_per_second": 61.241, | |
| "eval_steps_per_second": 7.738, | |
| "step": 6084 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 39.0, | |
| "step": 6084 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7509025270758123, | |
| "eval_loss": 0.4424862563610077, | |
| "eval_runtime": 4.5215, | |
| "eval_samples_per_second": 61.263, | |
| "eval_steps_per_second": 7.741, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 40.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7545126353790613, | |
| "eval_loss": 0.47295689582824707, | |
| "eval_runtime": 4.5231, | |
| "eval_samples_per_second": 61.241, | |
| "eval_steps_per_second": 7.738, | |
| "step": 6396 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 41.0, | |
| "step": 6396 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0009166666666666668, | |
| "loss": 0.3407, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7509025270758123, | |
| "eval_loss": 0.4623565077781677, | |
| "eval_runtime": 4.5243, | |
| "eval_samples_per_second": 61.225, | |
| "eval_steps_per_second": 7.736, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 42.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7509025270758123, | |
| "eval_loss": 0.4847128987312317, | |
| "eval_runtime": 4.5246, | |
| "eval_samples_per_second": 61.221, | |
| "eval_steps_per_second": 7.736, | |
| "step": 6708 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 43.0, | |
| "step": 6708 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.5370722413063049, | |
| "eval_runtime": 4.5236, | |
| "eval_samples_per_second": 61.234, | |
| "eval_steps_per_second": 7.737, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 44.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.0007564102564102564, | |
| "loss": 0.3329, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7545126353790613, | |
| "eval_loss": 0.48414450883865356, | |
| "eval_runtime": 4.531, | |
| "eval_samples_per_second": 61.134, | |
| "eval_steps_per_second": 7.725, | |
| "step": 7020 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 45.0, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.4815019369125366, | |
| "eval_runtime": 4.5295, | |
| "eval_samples_per_second": 61.154, | |
| "eval_steps_per_second": 7.727, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 46.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7509025270758123, | |
| "eval_loss": 0.4678334891796112, | |
| "eval_runtime": 4.5262, | |
| "eval_samples_per_second": 61.199, | |
| "eval_steps_per_second": 7.733, | |
| "step": 7332 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 47.0, | |
| "step": 7332 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.49180135130882263, | |
| "eval_runtime": 4.527, | |
| "eval_samples_per_second": 61.188, | |
| "eval_steps_per_second": 7.731, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 48.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 0.0005961538461538461, | |
| "loss": 0.3235, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7581227436823105, | |
| "eval_loss": 0.459226131439209, | |
| "eval_runtime": 4.528, | |
| "eval_samples_per_second": 61.175, | |
| "eval_steps_per_second": 7.73, | |
| "step": 7644 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 49.0, | |
| "step": 7644 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.5004814267158508, | |
| "eval_runtime": 4.529, | |
| "eval_samples_per_second": 61.162, | |
| "eval_steps_per_second": 7.728, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 50.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7545126353790613, | |
| "eval_loss": 0.4776909351348877, | |
| "eval_runtime": 4.5302, | |
| "eval_samples_per_second": 61.145, | |
| "eval_steps_per_second": 7.726, | |
| "step": 7956 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 51.0, | |
| "step": 7956 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 0.00043589743589743596, | |
| "loss": 0.3193, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7545126353790613, | |
| "eval_loss": 0.45583781599998474, | |
| "eval_runtime": 4.5285, | |
| "eval_samples_per_second": 61.168, | |
| "eval_steps_per_second": 7.729, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 52.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.48702728748321533, | |
| "eval_runtime": 4.5349, | |
| "eval_samples_per_second": 61.082, | |
| "eval_steps_per_second": 7.718, | |
| "step": 8268 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 53.0, | |
| "step": 8268 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.47922226786613464, | |
| "eval_runtime": 4.5301, | |
| "eval_samples_per_second": 61.146, | |
| "eval_steps_per_second": 7.726, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 54.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 0.0002756410256410257, | |
| "loss": 0.3132, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.46733495593070984, | |
| "eval_runtime": 4.5359, | |
| "eval_samples_per_second": 61.069, | |
| "eval_steps_per_second": 7.716, | |
| "step": 8580 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 55.0, | |
| "step": 8580 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.4943315386772156, | |
| "eval_runtime": 4.5312, | |
| "eval_samples_per_second": 61.132, | |
| "eval_steps_per_second": 7.724, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 56.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.49698954820632935, | |
| "eval_runtime": 4.5298, | |
| "eval_samples_per_second": 61.151, | |
| "eval_steps_per_second": 7.727, | |
| "step": 8892 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 57.0, | |
| "step": 8892 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 0.0001153846153846154, | |
| "loss": 0.311, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.49142444133758545, | |
| "eval_runtime": 4.5346, | |
| "eval_samples_per_second": 61.086, | |
| "eval_steps_per_second": 7.718, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 58.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.4886566698551178, | |
| "eval_runtime": 4.5139, | |
| "eval_samples_per_second": 61.367, | |
| "eval_steps_per_second": 7.754, | |
| "step": 9204 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 59.0, | |
| "step": 9204 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.48362648487091064, | |
| "eval_runtime": 4.5024, | |
| "eval_samples_per_second": 61.522, | |
| "eval_steps_per_second": 7.774, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 60.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 9360, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 0.41104679596729765, | |
| "train_runtime": 3875.9051, | |
| "train_samples_per_second": 38.546, | |
| "train_steps_per_second": 2.415 | |
| } | |
| ], | |
| "max_steps": 9360, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |