| { | |
| "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": 0.4693140794223827, | |
| "eval_loss": 33.111061096191406, | |
| "eval_runtime": 7.0298, | |
| "eval_samples_per_second": 39.404, | |
| "eval_steps_per_second": 4.979, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.4693140794223827, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00048664529914529915, | |
| "loss": 33.5632, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 29.4329833984375, | |
| "eval_runtime": 7.0194, | |
| "eval_samples_per_second": 39.462, | |
| "eval_steps_per_second": 4.986, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.4729241877256318, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 28.657472610473633, | |
| "eval_runtime": 7.0397, | |
| "eval_samples_per_second": 39.348, | |
| "eval_steps_per_second": 4.972, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.4729241877256318, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.0004732905982905983, | |
| "loss": 29.5796, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.49458483754512633, | |
| "eval_loss": 27.559425354003906, | |
| "eval_runtime": 7.0574, | |
| "eval_samples_per_second": 39.249, | |
| "eval_steps_per_second": 4.959, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 3, | |
| "best_eval_accuracy": 0.49458483754512633, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.0004599358974358974, | |
| "loss": 27.7947, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 24.001134872436523, | |
| "eval_runtime": 7.0529, | |
| "eval_samples_per_second": 39.274, | |
| "eval_steps_per_second": 4.962, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 3, | |
| "best_eval_accuracy": 0.49458483754512633, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5306859205776173, | |
| "eval_loss": 21.849742889404297, | |
| "eval_runtime": 6.9198, | |
| "eval_samples_per_second": 40.03, | |
| "eval_steps_per_second": 5.058, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.0004465811965811966, | |
| "loss": 24.4291, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 18.93817138671875, | |
| "eval_runtime": 6.9705, | |
| "eval_samples_per_second": 39.739, | |
| "eval_steps_per_second": 5.021, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 17.022798538208008, | |
| "eval_runtime": 7.0475, | |
| "eval_samples_per_second": 39.305, | |
| "eval_steps_per_second": 4.966, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.00043322649572649576, | |
| "loss": 21.7331, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 16.219053268432617, | |
| "eval_runtime": 7.0492, | |
| "eval_samples_per_second": 39.295, | |
| "eval_steps_per_second": 4.965, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.0004198717948717949, | |
| "loss": 20.2434, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 15.6640043258667, | |
| "eval_runtime": 7.009, | |
| "eval_samples_per_second": 39.521, | |
| "eval_steps_per_second": 4.994, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 15.320855140686035, | |
| "eval_runtime": 6.928, | |
| "eval_samples_per_second": 39.983, | |
| "eval_steps_per_second": 5.052, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 0.00040651709401709403, | |
| "loss": 19.5791, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 15.036731719970703, | |
| "eval_runtime": 7.0537, | |
| "eval_samples_per_second": 39.27, | |
| "eval_steps_per_second": 4.962, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.00039316239316239317, | |
| "loss": 19.1759, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 14.785924911499023, | |
| "eval_runtime": 6.9672, | |
| "eval_samples_per_second": 39.758, | |
| "eval_steps_per_second": 5.024, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 14.568937301635742, | |
| "eval_runtime": 7.0271, | |
| "eval_samples_per_second": 39.419, | |
| "eval_steps_per_second": 4.981, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 0.0003798076923076923, | |
| "loss": 18.9129, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 14.419888496398926, | |
| "eval_runtime": 7.0292, | |
| "eval_samples_per_second": 39.407, | |
| "eval_steps_per_second": 4.979, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 14.306955337524414, | |
| "eval_runtime": 6.9501, | |
| "eval_samples_per_second": 39.856, | |
| "eval_steps_per_second": 5.036, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.00036645299145299145, | |
| "loss": 18.725, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 14.20071029663086, | |
| "eval_runtime": 7.0305, | |
| "eval_samples_per_second": 39.4, | |
| "eval_steps_per_second": 4.978, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.00035309829059829064, | |
| "loss": 18.5733, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 14.099628448486328, | |
| "eval_runtime": 7.0315, | |
| "eval_samples_per_second": 39.394, | |
| "eval_steps_per_second": 4.978, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 14.055991172790527, | |
| "eval_runtime": 7.0244, | |
| "eval_samples_per_second": 39.434, | |
| "eval_steps_per_second": 4.983, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.0003397435897435898, | |
| "loss": 18.4591, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.947591781616211, | |
| "eval_runtime": 6.9888, | |
| "eval_samples_per_second": 39.635, | |
| "eval_steps_per_second": 5.008, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 0.0003263888888888889, | |
| "loss": 18.3533, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.853177070617676, | |
| "eval_runtime": 7.0232, | |
| "eval_samples_per_second": 39.44, | |
| "eval_steps_per_second": 4.983, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.809125900268555, | |
| "eval_runtime": 6.9984, | |
| "eval_samples_per_second": 39.58, | |
| "eval_steps_per_second": 5.001, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.00031303418803418806, | |
| "loss": 18.2596, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.72776985168457, | |
| "eval_runtime": 7.0025, | |
| "eval_samples_per_second": 39.558, | |
| "eval_steps_per_second": 4.998, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.661612510681152, | |
| "eval_runtime": 7.0007, | |
| "eval_samples_per_second": 39.567, | |
| "eval_steps_per_second": 4.999, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 0.0002996794871794872, | |
| "loss": 18.1857, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.58198356628418, | |
| "eval_runtime": 7.0185, | |
| "eval_samples_per_second": 39.467, | |
| "eval_steps_per_second": 4.987, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.00028632478632478634, | |
| "loss": 18.1091, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.565810203552246, | |
| "eval_runtime": 6.9956, | |
| "eval_samples_per_second": 39.597, | |
| "eval_steps_per_second": 5.003, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.495006561279297, | |
| "eval_runtime": 7.0216, | |
| "eval_samples_per_second": 39.45, | |
| "eval_steps_per_second": 4.985, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 0.0002729700854700855, | |
| "loss": 18.0388, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.410882949829102, | |
| "eval_runtime": 7.0403, | |
| "eval_samples_per_second": 39.345, | |
| "eval_steps_per_second": 4.971, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.00025961538461538467, | |
| "loss": 17.9676, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.357146263122559, | |
| "eval_runtime": 7.0135, | |
| "eval_samples_per_second": 39.495, | |
| "eval_steps_per_second": 4.99, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.309640884399414, | |
| "eval_runtime": 6.9911, | |
| "eval_samples_per_second": 39.622, | |
| "eval_steps_per_second": 5.006, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 0.0002462606837606838, | |
| "loss": 17.9109, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.26890754699707, | |
| "eval_runtime": 7.0321, | |
| "eval_samples_per_second": 39.391, | |
| "eval_steps_per_second": 4.977, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.219923973083496, | |
| "eval_runtime": 7.0259, | |
| "eval_samples_per_second": 39.425, | |
| "eval_steps_per_second": 4.982, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.00023290598290598292, | |
| "loss": 17.8555, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.170161247253418, | |
| "eval_runtime": 7.0381, | |
| "eval_samples_per_second": 39.357, | |
| "eval_steps_per_second": 4.973, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 0.00021955128205128206, | |
| "loss": 17.7959, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.131486892700195, | |
| "eval_runtime": 7.0195, | |
| "eval_samples_per_second": 39.462, | |
| "eval_steps_per_second": 4.986, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.097670555114746, | |
| "eval_runtime": 7.0588, | |
| "eval_samples_per_second": 39.242, | |
| "eval_steps_per_second": 4.958, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.0002061965811965812, | |
| "loss": 17.7567, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.071810722351074, | |
| "eval_runtime": 7.0557, | |
| "eval_samples_per_second": 39.259, | |
| "eval_steps_per_second": 4.961, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 0.00019284188034188036, | |
| "loss": 17.718, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.024420738220215, | |
| "eval_runtime": 7.0253, | |
| "eval_samples_per_second": 39.429, | |
| "eval_steps_per_second": 4.982, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.006111145019531, | |
| "eval_runtime": 7.0291, | |
| "eval_samples_per_second": 39.408, | |
| "eval_steps_per_second": 4.979, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.0001794871794871795, | |
| "loss": 17.6743, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.977677345275879, | |
| "eval_runtime": 7.0704, | |
| "eval_samples_per_second": 39.177, | |
| "eval_steps_per_second": 4.95, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.9545259475708, | |
| "eval_runtime": 7.0367, | |
| "eval_samples_per_second": 39.365, | |
| "eval_steps_per_second": 4.974, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 0.00016613247863247864, | |
| "loss": 17.6411, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.93622875213623, | |
| "eval_runtime": 7.0219, | |
| "eval_samples_per_second": 39.448, | |
| "eval_steps_per_second": 4.984, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0001527777777777778, | |
| "loss": 17.6197, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.95643138885498, | |
| "eval_runtime": 7.0397, | |
| "eval_samples_per_second": 39.348, | |
| "eval_steps_per_second": 4.972, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.893377304077148, | |
| "eval_runtime": 7.0406, | |
| "eval_samples_per_second": 39.343, | |
| "eval_steps_per_second": 4.971, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 0.00013942307692307694, | |
| "loss": 17.598, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.88237476348877, | |
| "eval_runtime": 7.0375, | |
| "eval_samples_per_second": 39.36, | |
| "eval_steps_per_second": 4.973, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.00012606837606837608, | |
| "loss": 17.5669, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.892475128173828, | |
| "eval_runtime": 7.0533, | |
| "eval_samples_per_second": 39.272, | |
| "eval_steps_per_second": 4.962, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.856684684753418, | |
| "eval_runtime": 7.0329, | |
| "eval_samples_per_second": 39.386, | |
| "eval_steps_per_second": 4.977, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 0.00011271367521367522, | |
| "loss": 17.5513, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.852547645568848, | |
| "eval_runtime": 7.0648, | |
| "eval_samples_per_second": 39.208, | |
| "eval_steps_per_second": 4.954, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.82678508758545, | |
| "eval_runtime": 7.0826, | |
| "eval_samples_per_second": 39.11, | |
| "eval_steps_per_second": 4.942, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 9.935897435897436e-05, | |
| "loss": 17.5412, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.810016632080078, | |
| "eval_runtime": 7.0391, | |
| "eval_samples_per_second": 39.352, | |
| "eval_steps_per_second": 4.972, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 8.600427350427351e-05, | |
| "loss": 17.5282, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.805554389953613, | |
| "eval_runtime": 7.0839, | |
| "eval_samples_per_second": 39.103, | |
| "eval_steps_per_second": 4.941, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.799531936645508, | |
| "eval_runtime": 7.0532, | |
| "eval_samples_per_second": 39.273, | |
| "eval_steps_per_second": 4.962, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 7.264957264957266e-05, | |
| "loss": 17.51, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.799637794494629, | |
| "eval_runtime": 7.0595, | |
| "eval_samples_per_second": 39.238, | |
| "eval_steps_per_second": 4.958, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 5.929487179487179e-05, | |
| "loss": 17.5032, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.77934455871582, | |
| "eval_runtime": 7.037, | |
| "eval_samples_per_second": 39.363, | |
| "eval_steps_per_second": 4.974, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.773187637329102, | |
| "eval_runtime": 7.0038, | |
| "eval_samples_per_second": 39.55, | |
| "eval_steps_per_second": 4.997, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 4.5940170940170944e-05, | |
| "loss": 17.4893, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.768193244934082, | |
| "eval_runtime": 4.4858, | |
| "eval_samples_per_second": 61.751, | |
| "eval_steps_per_second": 7.802, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.762487411499023, | |
| "eval_runtime": 3.356, | |
| "eval_samples_per_second": 82.538, | |
| "eval_steps_per_second": 10.429, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 3.258547008547009e-05, | |
| "loss": 17.4874, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.764068603515625, | |
| "eval_runtime": 3.3645, | |
| "eval_samples_per_second": 82.331, | |
| "eval_steps_per_second": 10.403, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 1.923076923076923e-05, | |
| "loss": 17.4805, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.757027626037598, | |
| "eval_runtime": 3.3549, | |
| "eval_samples_per_second": 82.566, | |
| "eval_steps_per_second": 10.432, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.756416320800781, | |
| "eval_runtime": 3.3544, | |
| "eval_samples_per_second": 82.578, | |
| "eval_steps_per_second": 10.434, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 5.876068376068376e-06, | |
| "loss": 17.4784, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.755927085876465, | |
| "eval_runtime": 3.3587, | |
| "eval_samples_per_second": 82.474, | |
| "eval_steps_per_second": 10.421, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 19.286396724342282, | |
| "train_runtime": 6149.9047, | |
| "train_samples_per_second": 24.293, | |
| "train_steps_per_second": 3.044 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |