| { | |
| "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": 0.3687332570552826, | |
| "eval_runtime": 4.3048, | |
| "eval_samples_per_second": 64.346, | |
| "eval_steps_per_second": 8.13, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.4729241877256318, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.732905982905983e-05, | |
| "loss": 0.3745, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5379061371841155, | |
| "eval_loss": 0.3523375689983368, | |
| "eval_runtime": 4.3685, | |
| "eval_samples_per_second": 63.408, | |
| "eval_steps_per_second": 8.012, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.35980018973350525, | |
| "eval_runtime": 4.353, | |
| "eval_samples_per_second": 63.634, | |
| "eval_steps_per_second": 8.04, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 9.465811965811966e-05, | |
| "loss": 0.3798, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.34790441393852234, | |
| "eval_runtime": 4.3588, | |
| "eval_samples_per_second": 63.55, | |
| "eval_steps_per_second": 8.03, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 9.198717948717949e-05, | |
| "loss": 0.3752, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.35927093029022217, | |
| "eval_runtime": 4.3511, | |
| "eval_samples_per_second": 63.662, | |
| "eval_steps_per_second": 8.044, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3504946231842041, | |
| "eval_runtime": 4.3363, | |
| "eval_samples_per_second": 63.879, | |
| "eval_steps_per_second": 8.071, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 8.931623931623932e-05, | |
| "loss": 0.373, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3479885756969452, | |
| "eval_runtime": 4.3405, | |
| "eval_samples_per_second": 63.818, | |
| "eval_steps_per_second": 8.064, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.35928189754486084, | |
| "eval_runtime": 4.3427, | |
| "eval_samples_per_second": 63.785, | |
| "eval_steps_per_second": 8.059, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 8.664529914529916e-05, | |
| "loss": 0.3724, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3490194082260132, | |
| "eval_runtime": 4.3424, | |
| "eval_samples_per_second": 63.79, | |
| "eval_steps_per_second": 8.06, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 8.397435897435898e-05, | |
| "loss": 0.3669, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.34893110394477844, | |
| "eval_runtime": 4.3468, | |
| "eval_samples_per_second": 63.725, | |
| "eval_steps_per_second": 8.052, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3486764132976532, | |
| "eval_runtime": 4.3467, | |
| "eval_samples_per_second": 63.727, | |
| "eval_steps_per_second": 8.052, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 8.13034188034188e-05, | |
| "loss": 0.3681, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.3587585389614105, | |
| "eval_runtime": 4.3467, | |
| "eval_samples_per_second": 63.726, | |
| "eval_steps_per_second": 8.052, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 7.863247863247864e-05, | |
| "loss": 0.3636, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3518940210342407, | |
| "eval_runtime": 4.3497, | |
| "eval_samples_per_second": 63.682, | |
| "eval_steps_per_second": 8.046, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.35109788179397583, | |
| "eval_runtime": 4.3616, | |
| "eval_samples_per_second": 63.509, | |
| "eval_steps_per_second": 8.025, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 7.596153846153846e-05, | |
| "loss": 0.3629, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3510183095932007, | |
| "eval_runtime": 4.3453, | |
| "eval_samples_per_second": 63.746, | |
| "eval_steps_per_second": 8.055, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3477706015110016, | |
| "eval_runtime": 4.3391, | |
| "eval_samples_per_second": 63.838, | |
| "eval_steps_per_second": 8.066, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 7.32905982905983e-05, | |
| "loss": 0.3591, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3501521646976471, | |
| "eval_runtime": 4.3406, | |
| "eval_samples_per_second": 63.815, | |
| "eval_steps_per_second": 8.063, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 7.061965811965813e-05, | |
| "loss": 0.3564, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3480573892593384, | |
| "eval_runtime": 4.3405, | |
| "eval_samples_per_second": 63.817, | |
| "eval_steps_per_second": 8.064, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3510577082633972, | |
| "eval_runtime": 4.3404, | |
| "eval_samples_per_second": 63.819, | |
| "eval_steps_per_second": 8.064, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 6.794871794871795e-05, | |
| "loss": 0.3573, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.35122740268707275, | |
| "eval_runtime": 4.3372, | |
| "eval_samples_per_second": 63.866, | |
| "eval_steps_per_second": 8.07, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 6.527777777777778e-05, | |
| "loss": 0.3574, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.34808871150016785, | |
| "eval_runtime": 4.3389, | |
| "eval_samples_per_second": 63.841, | |
| "eval_steps_per_second": 8.067, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.348792165517807, | |
| "eval_runtime": 4.3427, | |
| "eval_samples_per_second": 63.785, | |
| "eval_steps_per_second": 8.059, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 6.260683760683761e-05, | |
| "loss": 0.3566, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.35162776708602905, | |
| "eval_runtime": 4.3371, | |
| "eval_samples_per_second": 63.867, | |
| "eval_steps_per_second": 8.07, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3483467102050781, | |
| "eval_runtime": 4.3395, | |
| "eval_samples_per_second": 63.832, | |
| "eval_steps_per_second": 8.065, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 5.9935897435897434e-05, | |
| "loss": 0.3571, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3478488028049469, | |
| "eval_runtime": 4.3385, | |
| "eval_samples_per_second": 63.847, | |
| "eval_steps_per_second": 8.067, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 5.726495726495726e-05, | |
| "loss": 0.3562, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3478386104106903, | |
| "eval_runtime": 4.337, | |
| "eval_samples_per_second": 63.869, | |
| "eval_steps_per_second": 8.07, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.353412389755249, | |
| "eval_runtime": 4.3381, | |
| "eval_samples_per_second": 63.853, | |
| "eval_steps_per_second": 8.068, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 5.459401709401709e-05, | |
| "loss": 0.356, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.34818387031555176, | |
| "eval_runtime": 4.3382, | |
| "eval_samples_per_second": 63.852, | |
| "eval_steps_per_second": 8.068, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 5.192307692307693e-05, | |
| "loss": 0.3564, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3479267954826355, | |
| "eval_runtime": 4.3443, | |
| "eval_samples_per_second": 63.762, | |
| "eval_steps_per_second": 8.057, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3506244421005249, | |
| "eval_runtime": 4.345, | |
| "eval_samples_per_second": 63.752, | |
| "eval_steps_per_second": 8.055, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 4.925213675213676e-05, | |
| "loss": 0.3566, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3481433689594269, | |
| "eval_runtime": 4.3417, | |
| "eval_samples_per_second": 63.799, | |
| "eval_steps_per_second": 8.061, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.34804922342300415, | |
| "eval_runtime": 4.3401, | |
| "eval_samples_per_second": 63.824, | |
| "eval_steps_per_second": 8.064, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 4.6581196581196586e-05, | |
| "loss": 0.3552, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3479154706001282, | |
| "eval_runtime": 4.3362, | |
| "eval_samples_per_second": 63.881, | |
| "eval_steps_per_second": 8.072, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 4.3910256410256415e-05, | |
| "loss": 0.3558, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.34827256202697754, | |
| "eval_runtime": 4.3393, | |
| "eval_samples_per_second": 63.835, | |
| "eval_steps_per_second": 8.066, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3481837213039398, | |
| "eval_runtime": 4.3385, | |
| "eval_samples_per_second": 63.847, | |
| "eval_steps_per_second": 8.067, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 4.123931623931624e-05, | |
| "loss": 0.3553, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3493901193141937, | |
| "eval_runtime": 4.3365, | |
| "eval_samples_per_second": 63.876, | |
| "eval_steps_per_second": 8.071, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 3.856837606837607e-05, | |
| "loss": 0.3546, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3477574288845062, | |
| "eval_runtime": 4.333, | |
| "eval_samples_per_second": 63.928, | |
| "eval_steps_per_second": 8.078, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3490616977214813, | |
| "eval_runtime": 4.3368, | |
| "eval_samples_per_second": 63.872, | |
| "eval_steps_per_second": 8.071, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 3.58974358974359e-05, | |
| "loss": 0.3558, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3478951156139374, | |
| "eval_runtime": 4.3361, | |
| "eval_samples_per_second": 63.882, | |
| "eval_steps_per_second": 8.072, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.34864434599876404, | |
| "eval_runtime": 4.338, | |
| "eval_samples_per_second": 63.855, | |
| "eval_steps_per_second": 8.068, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 3.3226495726495725e-05, | |
| "loss": 0.3558, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.34804537892341614, | |
| "eval_runtime": 4.3347, | |
| "eval_samples_per_second": 63.903, | |
| "eval_steps_per_second": 8.074, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.3551, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3495274782180786, | |
| "eval_runtime": 4.3376, | |
| "eval_samples_per_second": 63.86, | |
| "eval_steps_per_second": 8.069, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3478722870349884, | |
| "eval_runtime": 4.3353, | |
| "eval_samples_per_second": 63.894, | |
| "eval_steps_per_second": 8.073, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 2.7884615384615386e-05, | |
| "loss": 0.3563, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3480492830276489, | |
| "eval_runtime": 4.3398, | |
| "eval_samples_per_second": 63.828, | |
| "eval_steps_per_second": 8.065, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 2.5213675213675215e-05, | |
| "loss": 0.3549, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3502560257911682, | |
| "eval_runtime": 4.342, | |
| "eval_samples_per_second": 63.795, | |
| "eval_steps_per_second": 8.061, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.34895843267440796, | |
| "eval_runtime": 4.3397, | |
| "eval_samples_per_second": 63.83, | |
| "eval_steps_per_second": 8.065, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 2.2542735042735044e-05, | |
| "loss": 0.355, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.34932848811149597, | |
| "eval_runtime": 4.3405, | |
| "eval_samples_per_second": 63.817, | |
| "eval_steps_per_second": 8.064, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3478783965110779, | |
| "eval_runtime": 4.3362, | |
| "eval_samples_per_second": 63.882, | |
| "eval_steps_per_second": 8.072, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 1.987179487179487e-05, | |
| "loss": 0.3551, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.348417192697525, | |
| "eval_runtime": 4.3401, | |
| "eval_samples_per_second": 63.824, | |
| "eval_steps_per_second": 8.064, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 1.7200854700854702e-05, | |
| "loss": 0.3558, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3478577435016632, | |
| "eval_runtime": 4.3354, | |
| "eval_samples_per_second": 63.893, | |
| "eval_steps_per_second": 8.073, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3480057716369629, | |
| "eval_runtime": 4.3382, | |
| "eval_samples_per_second": 63.852, | |
| "eval_steps_per_second": 8.068, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 1.4529914529914531e-05, | |
| "loss": 0.3542, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.34878429770469666, | |
| "eval_runtime": 4.338, | |
| "eval_samples_per_second": 63.855, | |
| "eval_steps_per_second": 8.068, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 1.1858974358974359e-05, | |
| "loss": 0.3553, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3482593595981598, | |
| "eval_runtime": 4.3388, | |
| "eval_samples_per_second": 63.842, | |
| "eval_steps_per_second": 8.067, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3484840393066406, | |
| "eval_runtime": 4.3395, | |
| "eval_samples_per_second": 63.833, | |
| "eval_steps_per_second": 8.065, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 9.18803418803419e-06, | |
| "loss": 0.3544, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3480793237686157, | |
| "eval_runtime": 4.3369, | |
| "eval_samples_per_second": 63.87, | |
| "eval_steps_per_second": 8.07, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.34800031781196594, | |
| "eval_runtime": 4.3409, | |
| "eval_samples_per_second": 63.812, | |
| "eval_steps_per_second": 8.063, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 6.517094017094018e-06, | |
| "loss": 0.3549, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.3482745885848999, | |
| "eval_runtime": 4.3469, | |
| "eval_samples_per_second": 63.723, | |
| "eval_steps_per_second": 8.052, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 3.846153846153847e-06, | |
| "loss": 0.3544, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.34807997941970825, | |
| "eval_runtime": 4.3307, | |
| "eval_samples_per_second": 63.962, | |
| "eval_steps_per_second": 8.082, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.34806886315345764, | |
| "eval_runtime": 4.3268, | |
| "eval_samples_per_second": 64.02, | |
| "eval_steps_per_second": 8.089, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 1.1752136752136752e-06, | |
| "loss": 0.3537, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.34800583124160767, | |
| "eval_runtime": 4.33, | |
| "eval_samples_per_second": 63.973, | |
| "eval_steps_per_second": 8.083, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 7.25686341470208e+16, | |
| "train_loss": 0.35934105734539845, | |
| "train_runtime": 4012.3556, | |
| "train_samples_per_second": 37.235, | |
| "train_steps_per_second": 4.666 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 7.25686341470208e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |