| { | |
| "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": 0.555956678700361, | |
| "eval_loss": 0.3513844907283783, | |
| "eval_runtime": 3.3272, | |
| "eval_samples_per_second": 83.252, | |
| "eval_steps_per_second": 10.519, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.555956678700361, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.004866452991452991, | |
| "loss": 0.6229, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5487364620938628, | |
| "eval_loss": 0.6273205876350403, | |
| "eval_runtime": 3.3437, | |
| "eval_samples_per_second": 82.843, | |
| "eval_steps_per_second": 10.468, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.555956678700361, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.8084543943405151, | |
| "eval_runtime": 3.3355, | |
| "eval_samples_per_second": 83.047, | |
| "eval_steps_per_second": 10.493, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.555956678700361, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.004732905982905983, | |
| "loss": 0.5188, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.6059607267379761, | |
| "eval_runtime": 3.3414, | |
| "eval_samples_per_second": 82.9, | |
| "eval_steps_per_second": 10.475, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.555956678700361, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.004599358974358974, | |
| "loss": 0.4693, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.49458483754512633, | |
| "eval_loss": 0.360698938369751, | |
| "eval_runtime": 3.3362, | |
| "eval_samples_per_second": 83.027, | |
| "eval_steps_per_second": 10.491, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.555956678700361, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.48014440433212996, | |
| "eval_loss": 0.3896714150905609, | |
| "eval_runtime": 3.3351, | |
| "eval_samples_per_second": 83.057, | |
| "eval_steps_per_second": 10.495, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.555956678700361, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.004465811965811966, | |
| "loss": 0.4249, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.5828221440315247, | |
| "eval_runtime": 3.3305, | |
| "eval_samples_per_second": 83.17, | |
| "eval_steps_per_second": 10.509, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.555956678700361, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5306859205776173, | |
| "eval_loss": 0.4718327224254608, | |
| "eval_runtime": 3.3348, | |
| "eval_samples_per_second": 83.063, | |
| "eval_steps_per_second": 10.495, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.555956678700361, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.004332264957264957, | |
| "loss": 0.4226, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.534294843673706, | |
| "eval_runtime": 3.3523, | |
| "eval_samples_per_second": 82.629, | |
| "eval_steps_per_second": 10.441, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.555956678700361, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.004198717948717949, | |
| "loss": 0.42, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5451263537906137, | |
| "eval_loss": 0.3477543592453003, | |
| "eval_runtime": 3.3302, | |
| "eval_samples_per_second": 83.178, | |
| "eval_steps_per_second": 10.51, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.555956678700361, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.4041728079319, | |
| "eval_runtime": 3.3307, | |
| "eval_samples_per_second": 83.165, | |
| "eval_steps_per_second": 10.508, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.555956678700361, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 0.00406517094017094, | |
| "loss": 0.407, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.4693140794223827, | |
| "eval_loss": 0.5783184170722961, | |
| "eval_runtime": 3.3406, | |
| "eval_samples_per_second": 82.918, | |
| "eval_steps_per_second": 10.477, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.555956678700361, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.003931623931623931, | |
| "loss": 0.4156, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.5740072202166066, | |
| "eval_loss": 0.3465688228607178, | |
| "eval_runtime": 3.3419, | |
| "eval_samples_per_second": 82.888, | |
| "eval_steps_per_second": 10.473, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 12, | |
| "best_eval_accuracy": 0.5740072202166066, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.5379061371841155, | |
| "eval_loss": 0.37199193239212036, | |
| "eval_runtime": 3.3289, | |
| "eval_samples_per_second": 83.211, | |
| "eval_steps_per_second": 10.514, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 12, | |
| "best_eval_accuracy": 0.5740072202166066, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 0.003798076923076923, | |
| "loss": 0.3784, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.631768953068592, | |
| "eval_loss": 0.3414437770843506, | |
| "eval_runtime": 3.3318, | |
| "eval_samples_per_second": 83.139, | |
| "eval_steps_per_second": 10.505, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 14, | |
| "best_eval_accuracy": 0.631768953068592, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.631768953068592, | |
| "eval_loss": 0.33300819993019104, | |
| "eval_runtime": 3.3351, | |
| "eval_samples_per_second": 83.055, | |
| "eval_steps_per_second": 10.494, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 14, | |
| "best_eval_accuracy": 0.631768953068592, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.003664529914529914, | |
| "loss": 0.3734, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5956678700361011, | |
| "eval_loss": 0.46307575702667236, | |
| "eval_runtime": 3.3402, | |
| "eval_samples_per_second": 82.93, | |
| "eval_steps_per_second": 10.478, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 14, | |
| "best_eval_accuracy": 0.631768953068592, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.003530982905982906, | |
| "loss": 0.3573, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.5848375451263538, | |
| "eval_loss": 0.3375145494937897, | |
| "eval_runtime": 3.3335, | |
| "eval_samples_per_second": 83.097, | |
| "eval_steps_per_second": 10.5, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 14, | |
| "best_eval_accuracy": 0.631768953068592, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.6606498194945848, | |
| "eval_loss": 0.34285253286361694, | |
| "eval_runtime": 3.3376, | |
| "eval_samples_per_second": 82.993, | |
| "eval_steps_per_second": 10.486, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.6606498194945848, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.0033974358974358976, | |
| "loss": 0.3516, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6606498194945848, | |
| "eval_loss": 0.33439937233924866, | |
| "eval_runtime": 3.3338, | |
| "eval_samples_per_second": 83.088, | |
| "eval_steps_per_second": 10.498, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.6606498194945848, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 0.003263888888888889, | |
| "loss": 0.3399, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.6678700361010831, | |
| "eval_loss": 0.3670630156993866, | |
| "eval_runtime": 3.3333, | |
| "eval_samples_per_second": 83.101, | |
| "eval_steps_per_second": 10.5, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.6678700361010831, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.6642599277978339, | |
| "eval_loss": 0.3484797775745392, | |
| "eval_runtime": 3.3363, | |
| "eval_samples_per_second": 83.026, | |
| "eval_steps_per_second": 10.491, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.6678700361010831, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.0031303418803418806, | |
| "loss": 0.3345, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.6678700361010831, | |
| "eval_loss": 0.3415996730327606, | |
| "eval_runtime": 3.3364, | |
| "eval_samples_per_second": 83.023, | |
| "eval_steps_per_second": 10.49, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.6678700361010831, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6967509025270758, | |
| "eval_loss": 0.3263380825519562, | |
| "eval_runtime": 3.3367, | |
| "eval_samples_per_second": 83.017, | |
| "eval_steps_per_second": 10.489, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 23, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 0.0029967948717948716, | |
| "loss": 0.325, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.6895306859205776, | |
| "eval_loss": 0.3330814838409424, | |
| "eval_runtime": 3.3408, | |
| "eval_samples_per_second": 82.915, | |
| "eval_steps_per_second": 10.477, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 23, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.002863247863247863, | |
| "loss": 0.3197, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.6787003610108303, | |
| "eval_loss": 0.3590630888938904, | |
| "eval_runtime": 3.3399, | |
| "eval_samples_per_second": 82.938, | |
| "eval_steps_per_second": 10.48, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 23, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.3174915611743927, | |
| "eval_runtime": 3.3382, | |
| "eval_samples_per_second": 82.979, | |
| "eval_steps_per_second": 10.485, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 0.0027297008547008546, | |
| "loss": 0.3165, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.3208056390285492, | |
| "eval_runtime": 3.3364, | |
| "eval_samples_per_second": 83.024, | |
| "eval_steps_per_second": 10.49, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.0025961538461538466, | |
| "loss": 0.3122, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.31998708844184875, | |
| "eval_runtime": 3.3328, | |
| "eval_samples_per_second": 83.112, | |
| "eval_steps_per_second": 10.502, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.6570397111913358, | |
| "eval_loss": 0.37904560565948486, | |
| "eval_runtime": 3.3324, | |
| "eval_samples_per_second": 83.124, | |
| "eval_steps_per_second": 10.503, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 0.0024626068376068376, | |
| "loss": 0.3072, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7111913357400722, | |
| "eval_loss": 0.32207196950912476, | |
| "eval_runtime": 3.3316, | |
| "eval_samples_per_second": 83.143, | |
| "eval_steps_per_second": 10.505, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.3263281583786011, | |
| "eval_runtime": 3.3438, | |
| "eval_samples_per_second": 82.84, | |
| "eval_steps_per_second": 10.467, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 31, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.002329059829059829, | |
| "loss": 0.3041, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.33217206597328186, | |
| "eval_runtime": 3.3295, | |
| "eval_samples_per_second": 83.195, | |
| "eval_steps_per_second": 10.512, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 31, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 0.0021955128205128206, | |
| "loss": 0.2885, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.32957446575164795, | |
| "eval_runtime": 3.3378, | |
| "eval_samples_per_second": 82.988, | |
| "eval_steps_per_second": 10.486, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 31, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7220216606498195, | |
| "eval_loss": 0.32645183801651, | |
| "eval_runtime": 3.3325, | |
| "eval_samples_per_second": 83.12, | |
| "eval_steps_per_second": 10.502, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 31, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.002061965811965812, | |
| "loss": 0.2875, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7509025270758123, | |
| "eval_loss": 0.3236461281776428, | |
| "eval_runtime": 3.3342, | |
| "eval_samples_per_second": 83.079, | |
| "eval_steps_per_second": 10.497, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7509025270758123, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 0.0019284188034188036, | |
| "loss": 0.2848, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7111913357400722, | |
| "eval_loss": 0.3483838438987732, | |
| "eval_runtime": 3.3335, | |
| "eval_samples_per_second": 83.095, | |
| "eval_steps_per_second": 10.499, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7509025270758123, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.3266400396823883, | |
| "eval_runtime": 3.3349, | |
| "eval_samples_per_second": 83.06, | |
| "eval_steps_per_second": 10.495, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7509025270758123, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.0017948717948717949, | |
| "loss": 0.2766, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.3303963840007782, | |
| "eval_runtime": 3.3393, | |
| "eval_samples_per_second": 82.952, | |
| "eval_steps_per_second": 10.481, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7509025270758123, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.330539733171463, | |
| "eval_runtime": 3.3369, | |
| "eval_samples_per_second": 83.012, | |
| "eval_steps_per_second": 10.489, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7509025270758123, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 0.0016613247863247864, | |
| "loss": 0.2743, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7545126353790613, | |
| "eval_loss": 0.3287397027015686, | |
| "eval_runtime": 3.3359, | |
| "eval_samples_per_second": 83.035, | |
| "eval_steps_per_second": 10.492, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0015277777777777779, | |
| "loss": 0.2708, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.32920366525650024, | |
| "eval_runtime": 3.3386, | |
| "eval_samples_per_second": 82.968, | |
| "eval_steps_per_second": 10.483, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.33632931113243103, | |
| "eval_runtime": 3.3366, | |
| "eval_samples_per_second": 83.019, | |
| "eval_steps_per_second": 10.49, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 0.0013942307692307694, | |
| "loss": 0.2662, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.32028645277023315, | |
| "eval_runtime": 3.3377, | |
| "eval_samples_per_second": 82.991, | |
| "eval_steps_per_second": 10.486, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.0012606837606837606, | |
| "loss": 0.2636, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.3337833881378174, | |
| "eval_runtime": 3.3343, | |
| "eval_samples_per_second": 83.077, | |
| "eval_steps_per_second": 10.497, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.3480018973350525, | |
| "eval_runtime": 3.3357, | |
| "eval_samples_per_second": 83.04, | |
| "eval_steps_per_second": 10.492, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 0.0011271367521367521, | |
| "loss": 0.261, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.3282296061515808, | |
| "eval_runtime": 3.334, | |
| "eval_samples_per_second": 83.084, | |
| "eval_steps_per_second": 10.498, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.33301836252212524, | |
| "eval_runtime": 3.3333, | |
| "eval_samples_per_second": 83.1, | |
| "eval_steps_per_second": 10.5, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 0.0009935897435897436, | |
| "loss": 0.2585, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.35189110040664673, | |
| "eval_runtime": 3.333, | |
| "eval_samples_per_second": 83.107, | |
| "eval_steps_per_second": 10.501, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 0.0008600427350427351, | |
| "loss": 0.2561, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.3215104937553406, | |
| "eval_runtime": 3.3331, | |
| "eval_samples_per_second": 83.106, | |
| "eval_steps_per_second": 10.501, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.33880314230918884, | |
| "eval_runtime": 3.3492, | |
| "eval_samples_per_second": 82.705, | |
| "eval_steps_per_second": 10.45, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 0.0007264957264957266, | |
| "loss": 0.2569, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.3326878845691681, | |
| "eval_runtime": 3.3354, | |
| "eval_samples_per_second": 83.048, | |
| "eval_steps_per_second": 10.493, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 0.000592948717948718, | |
| "loss": 0.2544, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.34021586179733276, | |
| "eval_runtime": 3.3334, | |
| "eval_samples_per_second": 83.098, | |
| "eval_steps_per_second": 10.5, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.3312588930130005, | |
| "eval_runtime": 3.3389, | |
| "eval_samples_per_second": 82.961, | |
| "eval_steps_per_second": 10.482, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 0.00045940170940170943, | |
| "loss": 0.2499, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.33167052268981934, | |
| "eval_runtime": 3.3347, | |
| "eval_samples_per_second": 83.066, | |
| "eval_steps_per_second": 10.496, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.3464829623699188, | |
| "eval_runtime": 3.333, | |
| "eval_samples_per_second": 83.109, | |
| "eval_steps_per_second": 10.501, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 0.00032585470085470087, | |
| "loss": 0.2505, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.3397899866104126, | |
| "eval_runtime": 3.3347, | |
| "eval_samples_per_second": 83.065, | |
| "eval_steps_per_second": 10.496, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 0.00019230769230769233, | |
| "loss": 0.2468, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.33796247839927673, | |
| "eval_runtime": 3.3352, | |
| "eval_samples_per_second": 83.054, | |
| "eval_steps_per_second": 10.494, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.3370416462421417, | |
| "eval_runtime": 3.3454, | |
| "eval_samples_per_second": 82.8, | |
| "eval_steps_per_second": 10.462, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 5.876068376068376e-05, | |
| "loss": 0.2487, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.34018510580062866, | |
| "eval_runtime": 3.3347, | |
| "eval_samples_per_second": 83.067, | |
| "eval_steps_per_second": 10.496, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 40, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 0.3291880776739528, | |
| "train_runtime": 3101.3746, | |
| "train_samples_per_second": 48.172, | |
| "train_steps_per_second": 6.036 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |