| { | |
| "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": 0.4729241877256318, | |
| "eval_loss": 0.3570820987224579, | |
| "eval_runtime": 4.3773, | |
| "eval_samples_per_second": 63.281, | |
| "eval_steps_per_second": 7.996, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.4729241877256318, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.048664529914529915, | |
| "loss": 6.8951, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 1.4464904069900513, | |
| "eval_runtime": 4.4679, | |
| "eval_samples_per_second": 61.998, | |
| "eval_steps_per_second": 7.834, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 1.4737317562103271, | |
| "eval_runtime": 4.4886, | |
| "eval_samples_per_second": 61.712, | |
| "eval_steps_per_second": 7.798, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.04732905982905983, | |
| "loss": 4.4457, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.4591030478477478, | |
| "eval_runtime": 4.4956, | |
| "eval_samples_per_second": 61.615, | |
| "eval_steps_per_second": 7.785, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.04599358974358975, | |
| "loss": 3.2957, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.40218400955200195, | |
| "eval_runtime": 4.4894, | |
| "eval_samples_per_second": 61.7, | |
| "eval_steps_per_second": 7.796, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 1.2355494499206543, | |
| "eval_runtime": 4.4719, | |
| "eval_samples_per_second": 61.942, | |
| "eval_steps_per_second": 7.827, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.044658119658119666, | |
| "loss": 3.7646, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 9.376609802246094, | |
| "eval_runtime": 4.487, | |
| "eval_samples_per_second": 61.733, | |
| "eval_steps_per_second": 7.8, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3763505816459656, | |
| "eval_runtime": 4.4865, | |
| "eval_samples_per_second": 61.741, | |
| "eval_steps_per_second": 7.801, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.04332264957264958, | |
| "loss": 3.3825, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 4.616496562957764, | |
| "eval_runtime": 4.4867, | |
| "eval_samples_per_second": 61.738, | |
| "eval_steps_per_second": 7.801, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.04198717948717949, | |
| "loss": 2.7848, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 3.261960506439209, | |
| "eval_runtime": 4.486, | |
| "eval_samples_per_second": 61.748, | |
| "eval_steps_per_second": 7.802, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 2.300961971282959, | |
| "eval_runtime": 4.482, | |
| "eval_samples_per_second": 61.803, | |
| "eval_steps_per_second": 7.809, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 0.0406517094017094, | |
| "loss": 2.3837, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.34843170642852783, | |
| "eval_runtime": 4.4826, | |
| "eval_samples_per_second": 61.794, | |
| "eval_steps_per_second": 7.808, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.039316239316239315, | |
| "loss": 2.1666, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.43984633684158325, | |
| "eval_runtime": 4.4884, | |
| "eval_samples_per_second": 61.714, | |
| "eval_steps_per_second": 7.798, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 1.4702966213226318, | |
| "eval_runtime": 4.4859, | |
| "eval_samples_per_second": 61.749, | |
| "eval_steps_per_second": 7.802, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 0.037980769230769235, | |
| "loss": 2.107, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 1.0550079345703125, | |
| "eval_runtime": 4.4897, | |
| "eval_samples_per_second": 61.697, | |
| "eval_steps_per_second": 7.796, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 1.000760793685913, | |
| "eval_runtime": 4.4924, | |
| "eval_samples_per_second": 61.659, | |
| "eval_steps_per_second": 7.791, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.03664529914529915, | |
| "loss": 2.161, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.7809963822364807, | |
| "eval_runtime": 4.4932, | |
| "eval_samples_per_second": 61.649, | |
| "eval_steps_per_second": 7.79, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.035309829059829066, | |
| "loss": 1.927, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.84182208776474, | |
| "eval_runtime": 4.4906, | |
| "eval_samples_per_second": 61.684, | |
| "eval_steps_per_second": 7.794, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.5165618062019348, | |
| "eval_runtime": 4.4892, | |
| "eval_samples_per_second": 61.703, | |
| "eval_steps_per_second": 7.796, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.03397435897435898, | |
| "loss": 1.8072, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.34929215908050537, | |
| "eval_runtime": 4.4926, | |
| "eval_samples_per_second": 61.657, | |
| "eval_steps_per_second": 7.791, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 0.03263888888888889, | |
| "loss": 1.7187, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 1.4220978021621704, | |
| "eval_runtime": 4.4942, | |
| "eval_samples_per_second": 61.636, | |
| "eval_steps_per_second": 7.788, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 2.9355978965759277, | |
| "eval_runtime": 4.4848, | |
| "eval_samples_per_second": 61.764, | |
| "eval_steps_per_second": 7.804, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.0313034188034188, | |
| "loss": 2.1333, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.8474471569061279, | |
| "eval_runtime": 4.4899, | |
| "eval_samples_per_second": 61.693, | |
| "eval_steps_per_second": 7.795, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 5.1220269203186035, | |
| "eval_runtime": 4.4961, | |
| "eval_samples_per_second": 61.609, | |
| "eval_steps_per_second": 7.785, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 0.02996794871794872, | |
| "loss": 2.0017, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.3589232265949249, | |
| "eval_runtime": 4.4864, | |
| "eval_samples_per_second": 61.742, | |
| "eval_steps_per_second": 7.801, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.02863247863247863, | |
| "loss": 1.6518, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.39960214495658875, | |
| "eval_runtime": 4.4875, | |
| "eval_samples_per_second": 61.726, | |
| "eval_steps_per_second": 7.799, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.535088062286377, | |
| "eval_runtime": 4.4855, | |
| "eval_samples_per_second": 61.755, | |
| "eval_steps_per_second": 7.803, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 0.027297008547008547, | |
| "loss": 1.5012, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3478943407535553, | |
| "eval_runtime": 4.4915, | |
| "eval_samples_per_second": 61.672, | |
| "eval_steps_per_second": 7.792, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.025961538461538466, | |
| "loss": 1.4194, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3492168188095093, | |
| "eval_runtime": 4.4867, | |
| "eval_samples_per_second": 61.738, | |
| "eval_steps_per_second": 7.801, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.6942079663276672, | |
| "eval_runtime": 4.4877, | |
| "eval_samples_per_second": 61.725, | |
| "eval_steps_per_second": 7.799, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 0.02462606837606838, | |
| "loss": 1.3048, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.5088778734207153, | |
| "eval_runtime": 4.4883, | |
| "eval_samples_per_second": 61.716, | |
| "eval_steps_per_second": 7.798, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 1.1509357690811157, | |
| "eval_runtime": 4.4831, | |
| "eval_samples_per_second": 61.787, | |
| "eval_steps_per_second": 7.807, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.02329059829059829, | |
| "loss": 1.2972, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 1.1207164525985718, | |
| "eval_runtime": 4.4926, | |
| "eval_samples_per_second": 61.657, | |
| "eval_steps_per_second": 7.791, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 0.021955128205128207, | |
| "loss": 1.1774, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 1.4442700147628784, | |
| "eval_runtime": 4.4967, | |
| "eval_samples_per_second": 61.601, | |
| "eval_steps_per_second": 7.783, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 2.3752989768981934, | |
| "eval_runtime": 4.4944, | |
| "eval_samples_per_second": 61.633, | |
| "eval_steps_per_second": 7.788, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.02061965811965812, | |
| "loss": 1.492, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.36219045519828796, | |
| "eval_runtime": 4.4975, | |
| "eval_samples_per_second": 61.59, | |
| "eval_steps_per_second": 7.782, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 0.019284188034188035, | |
| "loss": 1.3617, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 1.356360673904419, | |
| "eval_runtime": 4.4982, | |
| "eval_samples_per_second": 61.58, | |
| "eval_steps_per_second": 7.781, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.6943920254707336, | |
| "eval_runtime": 4.4948, | |
| "eval_samples_per_second": 61.627, | |
| "eval_steps_per_second": 7.787, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.01794871794871795, | |
| "loss": 1.4582, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.5509728193283081, | |
| "eval_runtime": 4.502, | |
| "eval_samples_per_second": 61.528, | |
| "eval_steps_per_second": 7.774, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3659651577472687, | |
| "eval_runtime": 4.4965, | |
| "eval_samples_per_second": 61.603, | |
| "eval_steps_per_second": 7.784, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 0.016613247863247863, | |
| "loss": 1.0904, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3479963541030884, | |
| "eval_runtime": 4.4948, | |
| "eval_samples_per_second": 61.627, | |
| "eval_steps_per_second": 7.787, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.015277777777777779, | |
| "loss": 0.9409, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.48353341221809387, | |
| "eval_runtime": 4.4928, | |
| "eval_samples_per_second": 61.654, | |
| "eval_steps_per_second": 7.79, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.6226072311401367, | |
| "eval_runtime": 4.4898, | |
| "eval_samples_per_second": 61.696, | |
| "eval_steps_per_second": 7.795, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 0.013942307692307693, | |
| "loss": 0.9404, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.402121365070343, | |
| "eval_runtime": 4.4924, | |
| "eval_samples_per_second": 61.659, | |
| "eval_steps_per_second": 7.791, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.012606837606837607, | |
| "loss": 0.8008, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.5381026268005371, | |
| "eval_runtime": 4.4922, | |
| "eval_samples_per_second": 61.663, | |
| "eval_steps_per_second": 7.791, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.3887210786342621, | |
| "eval_runtime": 4.4883, | |
| "eval_samples_per_second": 61.716, | |
| "eval_steps_per_second": 7.798, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 0.011271367521367523, | |
| "loss": 0.841, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3763456344604492, | |
| "eval_runtime": 4.4925, | |
| "eval_samples_per_second": 61.658, | |
| "eval_steps_per_second": 7.791, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.36665645241737366, | |
| "eval_runtime": 4.492, | |
| "eval_samples_per_second": 61.665, | |
| "eval_steps_per_second": 7.792, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 0.009935897435897435, | |
| "loss": 0.6912, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.44896015524864197, | |
| "eval_runtime": 4.4907, | |
| "eval_samples_per_second": 61.684, | |
| "eval_steps_per_second": 7.794, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 0.008600427350427351, | |
| "loss": 0.6381, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.7096900939941406, | |
| "eval_runtime": 4.489, | |
| "eval_samples_per_second": 61.707, | |
| "eval_steps_per_second": 7.797, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.36391106247901917, | |
| "eval_runtime": 4.4886, | |
| "eval_samples_per_second": 61.712, | |
| "eval_steps_per_second": 7.798, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 0.007264957264957266, | |
| "loss": 0.5792, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.379825621843338, | |
| "eval_runtime": 4.4914, | |
| "eval_samples_per_second": 61.673, | |
| "eval_steps_per_second": 7.793, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 0.005929487179487179, | |
| "loss": 0.53, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.38536888360977173, | |
| "eval_runtime": 4.4972, | |
| "eval_samples_per_second": 61.594, | |
| "eval_steps_per_second": 7.783, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.3884303867816925, | |
| "eval_runtime": 4.493, | |
| "eval_samples_per_second": 61.652, | |
| "eval_steps_per_second": 7.79, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 0.004594017094017094, | |
| "loss": 0.4977, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.3898393511772156, | |
| "eval_runtime": 4.497, | |
| "eval_samples_per_second": 61.597, | |
| "eval_steps_per_second": 7.783, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3479559123516083, | |
| "eval_runtime": 4.4975, | |
| "eval_samples_per_second": 61.59, | |
| "eval_steps_per_second": 7.782, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 0.003258547008547009, | |
| "loss": 0.4596, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.3541661202907562, | |
| "eval_runtime": 4.494, | |
| "eval_samples_per_second": 61.638, | |
| "eval_steps_per_second": 7.788, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 0.0019230769230769232, | |
| "loss": 0.4228, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3539113700389862, | |
| "eval_runtime": 4.4902, | |
| "eval_samples_per_second": 61.689, | |
| "eval_steps_per_second": 7.795, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.34990349411964417, | |
| "eval_runtime": 4.4855, | |
| "eval_samples_per_second": 61.755, | |
| "eval_steps_per_second": 7.803, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 0.0005876068376068377, | |
| "loss": 0.3933, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.353112131357193, | |
| "eval_runtime": 4.4599, | |
| "eval_samples_per_second": 62.109, | |
| "eval_steps_per_second": 7.848, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 7.25686341470208e+16, | |
| "train_loss": 1.7262601273691551, | |
| "train_runtime": 4126.2043, | |
| "train_samples_per_second": 36.208, | |
| "train_steps_per_second": 4.537 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 7.25686341470208e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |