| { | |
| "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": 34.459251403808594, | |
| "eval_runtime": 3.3722, | |
| "eval_samples_per_second": 82.142, | |
| "eval_steps_per_second": 10.379, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.4729241877256318, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.732905982905983e-05, | |
| "loss": 34.6035, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 34.190311431884766, | |
| "eval_runtime": 3.3781, | |
| "eval_samples_per_second": 81.998, | |
| "eval_steps_per_second": 10.361, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.4729241877256318, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5342960288808665, | |
| "eval_loss": 33.939701080322266, | |
| "eval_runtime": 3.3802, | |
| "eval_samples_per_second": 81.949, | |
| "eval_steps_per_second": 10.355, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 2, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 9.465811965811966e-05, | |
| "loss": 34.2607, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5342960288808665, | |
| "eval_loss": 33.67730712890625, | |
| "eval_runtime": 3.3621, | |
| "eval_samples_per_second": 82.389, | |
| "eval_steps_per_second": 10.41, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 2, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 9.198717948717949e-05, | |
| "loss": 33.8346, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 33.36012268066406, | |
| "eval_runtime": 3.3664, | |
| "eval_samples_per_second": 82.284, | |
| "eval_steps_per_second": 10.397, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 2, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5234657039711191, | |
| "eval_loss": 32.93340301513672, | |
| "eval_runtime": 3.3715, | |
| "eval_samples_per_second": 82.159, | |
| "eval_steps_per_second": 10.381, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 2, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 8.931623931623932e-05, | |
| "loss": 33.2988, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5451263537906137, | |
| "eval_loss": 32.40928268432617, | |
| "eval_runtime": 3.3808, | |
| "eval_samples_per_second": 81.934, | |
| "eval_steps_per_second": 10.353, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 6, | |
| "best_eval_accuracy": 0.5451263537906137, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5342960288808665, | |
| "eval_loss": 31.661354064941406, | |
| "eval_runtime": 3.3736, | |
| "eval_samples_per_second": 82.109, | |
| "eval_steps_per_second": 10.375, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 6, | |
| "best_eval_accuracy": 0.5451263537906137, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 8.664529914529916e-05, | |
| "loss": 32.523, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5487364620938628, | |
| "eval_loss": 31.12422752380371, | |
| "eval_runtime": 3.3782, | |
| "eval_samples_per_second": 81.996, | |
| "eval_steps_per_second": 10.36, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 8.397435897435898e-05, | |
| "loss": 31.6421, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 30.743305206298828, | |
| "eval_runtime": 3.3752, | |
| "eval_samples_per_second": 82.068, | |
| "eval_steps_per_second": 10.37, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.49097472924187724, | |
| "eval_loss": 30.42652130126953, | |
| "eval_runtime": 3.3681, | |
| "eval_samples_per_second": 82.243, | |
| "eval_steps_per_second": 10.392, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 8.13034188034188e-05, | |
| "loss": 30.9414, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 30.134010314941406, | |
| "eval_runtime": 3.3721, | |
| "eval_samples_per_second": 82.145, | |
| "eval_steps_per_second": 10.379, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 7.863247863247864e-05, | |
| "loss": 30.3998, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 29.693998336791992, | |
| "eval_runtime": 3.3732, | |
| "eval_samples_per_second": 82.117, | |
| "eval_steps_per_second": 10.376, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.48375451263537905, | |
| "eval_loss": 29.257352828979492, | |
| "eval_runtime": 3.363, | |
| "eval_samples_per_second": 82.367, | |
| "eval_steps_per_second": 10.407, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 7.596153846153846e-05, | |
| "loss": 29.7765, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 28.920366287231445, | |
| "eval_runtime": 3.3576, | |
| "eval_samples_per_second": 82.499, | |
| "eval_steps_per_second": 10.424, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 28.791555404663086, | |
| "eval_runtime": 3.354, | |
| "eval_samples_per_second": 82.589, | |
| "eval_steps_per_second": 10.435, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 7.32905982905983e-05, | |
| "loss": 29.2672, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5379061371841155, | |
| "eval_loss": 28.724546432495117, | |
| "eval_runtime": 3.3752, | |
| "eval_samples_per_second": 82.07, | |
| "eval_steps_per_second": 10.37, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 7.061965811965813e-05, | |
| "loss": 29.0545, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 28.66559600830078, | |
| "eval_runtime": 3.3668, | |
| "eval_samples_per_second": 82.274, | |
| "eval_steps_per_second": 10.396, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 28.61313247680664, | |
| "eval_runtime": 3.3665, | |
| "eval_samples_per_second": 82.282, | |
| "eval_steps_per_second": 10.397, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 6.794871794871795e-05, | |
| "loss": 28.9469, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5126353790613718, | |
| "eval_loss": 28.547107696533203, | |
| "eval_runtime": 3.349, | |
| "eval_samples_per_second": 82.711, | |
| "eval_steps_per_second": 10.451, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 6.527777777777778e-05, | |
| "loss": 28.8473, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.5342960288808665, | |
| "eval_loss": 28.47603988647461, | |
| "eval_runtime": 3.3589, | |
| "eval_samples_per_second": 82.467, | |
| "eval_steps_per_second": 10.42, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 28.39781951904297, | |
| "eval_runtime": 3.3527, | |
| "eval_samples_per_second": 82.62, | |
| "eval_steps_per_second": 10.439, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 6.260683760683761e-05, | |
| "loss": 28.7322, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 28.30725860595703, | |
| "eval_runtime": 3.4739, | |
| "eval_samples_per_second": 79.736, | |
| "eval_steps_per_second": 10.075, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 28.189701080322266, | |
| "eval_runtime": 6.9781, | |
| "eval_samples_per_second": 39.696, | |
| "eval_steps_per_second": 5.016, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 5.9935897435897434e-05, | |
| "loss": 28.5992, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 28.04110336303711, | |
| "eval_runtime": 6.923, | |
| "eval_samples_per_second": 40.012, | |
| "eval_steps_per_second": 5.056, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 5.726495726495726e-05, | |
| "loss": 28.4123, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 27.858659744262695, | |
| "eval_runtime": 6.9902, | |
| "eval_samples_per_second": 39.627, | |
| "eval_steps_per_second": 5.007, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 27.61689567565918, | |
| "eval_runtime": 6.9084, | |
| "eval_samples_per_second": 40.096, | |
| "eval_steps_per_second": 5.066, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 5.459401709401709e-05, | |
| "loss": 28.1552, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5018050541516246, | |
| "eval_loss": 27.22528648376465, | |
| "eval_runtime": 6.9142, | |
| "eval_samples_per_second": 40.063, | |
| "eval_steps_per_second": 5.062, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 5.192307692307693e-05, | |
| "loss": 27.7135, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 26.76430892944336, | |
| "eval_runtime": 6.9437, | |
| "eval_samples_per_second": 39.892, | |
| "eval_steps_per_second": 5.041, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.4693140794223827, | |
| "eval_loss": 26.298063278198242, | |
| "eval_runtime": 6.9844, | |
| "eval_samples_per_second": 39.66, | |
| "eval_steps_per_second": 5.011, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 4.925213675213676e-05, | |
| "loss": 27.1493, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.48736462093862815, | |
| "eval_loss": 25.955421447753906, | |
| "eval_runtime": 6.9659, | |
| "eval_samples_per_second": 39.765, | |
| "eval_steps_per_second": 5.024, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.5018050541516246, | |
| "eval_loss": 25.657350540161133, | |
| "eval_runtime": 6.9745, | |
| "eval_samples_per_second": 39.716, | |
| "eval_steps_per_second": 5.018, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 4.6581196581196586e-05, | |
| "loss": 26.68, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 25.384599685668945, | |
| "eval_runtime": 6.8861, | |
| "eval_samples_per_second": 40.226, | |
| "eval_steps_per_second": 5.083, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 4.3910256410256415e-05, | |
| "loss": 26.3235, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 25.09762191772461, | |
| "eval_runtime": 6.9698, | |
| "eval_samples_per_second": 39.743, | |
| "eval_steps_per_second": 5.022, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.48736462093862815, | |
| "eval_loss": 24.830303192138672, | |
| "eval_runtime": 6.869, | |
| "eval_samples_per_second": 40.326, | |
| "eval_steps_per_second": 5.095, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 4.123931623931624e-05, | |
| "loss": 25.9833, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 24.58111572265625, | |
| "eval_runtime": 6.9415, | |
| "eval_samples_per_second": 39.905, | |
| "eval_steps_per_second": 5.042, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 3.856837606837607e-05, | |
| "loss": 25.6663, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.48736462093862815, | |
| "eval_loss": 24.334089279174805, | |
| "eval_runtime": 6.9335, | |
| "eval_samples_per_second": 39.951, | |
| "eval_steps_per_second": 5.048, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 24.107402801513672, | |
| "eval_runtime": 6.9704, | |
| "eval_samples_per_second": 39.74, | |
| "eval_steps_per_second": 5.021, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 3.58974358974359e-05, | |
| "loss": 25.3808, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.48736462093862815, | |
| "eval_loss": 23.90985679626465, | |
| "eval_runtime": 6.9677, | |
| "eval_samples_per_second": 39.755, | |
| "eval_steps_per_second": 5.023, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.5342960288808665, | |
| "eval_loss": 23.713809967041016, | |
| "eval_runtime": 6.9396, | |
| "eval_samples_per_second": 39.916, | |
| "eval_steps_per_second": 5.044, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 3.3226495726495725e-05, | |
| "loss": 25.12, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.48736462093862815, | |
| "eval_loss": 23.543899536132812, | |
| "eval_runtime": 6.9165, | |
| "eval_samples_per_second": 40.049, | |
| "eval_steps_per_second": 5.06, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 24.8956, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 23.37445068359375, | |
| "eval_runtime": 6.8672, | |
| "eval_samples_per_second": 40.337, | |
| "eval_steps_per_second": 5.097, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.516245487364621, | |
| "eval_loss": 23.21479034423828, | |
| "eval_runtime": 6.9132, | |
| "eval_samples_per_second": 40.068, | |
| "eval_steps_per_second": 5.063, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 2.7884615384615386e-05, | |
| "loss": 24.6833, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 23.066547393798828, | |
| "eval_runtime": 6.9112, | |
| "eval_samples_per_second": 40.08, | |
| "eval_steps_per_second": 5.064, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 2.5213675213675215e-05, | |
| "loss": 24.498, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 22.94559097290039, | |
| "eval_runtime": 6.8981, | |
| "eval_samples_per_second": 40.156, | |
| "eval_steps_per_second": 5.074, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 22.820777893066406, | |
| "eval_runtime": 7.0625, | |
| "eval_samples_per_second": 39.221, | |
| "eval_steps_per_second": 4.956, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 2.2542735042735044e-05, | |
| "loss": 24.3449, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.4693140794223827, | |
| "eval_loss": 22.708683013916016, | |
| "eval_runtime": 6.9043, | |
| "eval_samples_per_second": 40.12, | |
| "eval_steps_per_second": 5.069, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.49097472924187724, | |
| "eval_loss": 22.61591911315918, | |
| "eval_runtime": 6.9037, | |
| "eval_samples_per_second": 40.123, | |
| "eval_steps_per_second": 5.07, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 1.987179487179487e-05, | |
| "loss": 24.1996, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.48736462093862815, | |
| "eval_loss": 22.524272918701172, | |
| "eval_runtime": 6.9272, | |
| "eval_samples_per_second": 39.988, | |
| "eval_steps_per_second": 5.053, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 1.7200854700854702e-05, | |
| "loss": 24.0892, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.48014440433212996, | |
| "eval_loss": 22.4456729888916, | |
| "eval_runtime": 6.99, | |
| "eval_samples_per_second": 39.628, | |
| "eval_steps_per_second": 5.007, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.48375451263537905, | |
| "eval_loss": 22.372821807861328, | |
| "eval_runtime": 6.9415, | |
| "eval_samples_per_second": 39.905, | |
| "eval_steps_per_second": 5.042, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 1.4529914529914531e-05, | |
| "loss": 23.9876, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.48736462093862815, | |
| "eval_loss": 22.30811882019043, | |
| "eval_runtime": 7.0623, | |
| "eval_samples_per_second": 39.222, | |
| "eval_steps_per_second": 4.956, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 1.1858974358974359e-05, | |
| "loss": 23.9068, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 22.2525691986084, | |
| "eval_runtime": 6.9668, | |
| "eval_samples_per_second": 39.76, | |
| "eval_steps_per_second": 5.024, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.48014440433212996, | |
| "eval_loss": 22.202903747558594, | |
| "eval_runtime": 6.949, | |
| "eval_samples_per_second": 39.862, | |
| "eval_steps_per_second": 5.037, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 9.18803418803419e-06, | |
| "loss": 23.837, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.48736462093862815, | |
| "eval_loss": 22.162384033203125, | |
| "eval_runtime": 6.8592, | |
| "eval_samples_per_second": 40.384, | |
| "eval_steps_per_second": 5.103, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 22.128917694091797, | |
| "eval_runtime": 6.9017, | |
| "eval_samples_per_second": 40.135, | |
| "eval_steps_per_second": 5.071, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 6.517094017094018e-06, | |
| "loss": 23.7911, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 22.10288429260254, | |
| "eval_runtime": 6.8789, | |
| "eval_samples_per_second": 40.268, | |
| "eval_steps_per_second": 5.088, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 3.846153846153847e-06, | |
| "loss": 23.7521, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 22.085439682006836, | |
| "eval_runtime": 6.9141, | |
| "eval_samples_per_second": 40.063, | |
| "eval_steps_per_second": 5.062, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 22.072628021240234, | |
| "eval_runtime": 6.9386, | |
| "eval_samples_per_second": 39.922, | |
| "eval_steps_per_second": 5.044, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 1.1752136752136752e-06, | |
| "loss": 23.7328, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.48014440433212996, | |
| "eval_loss": 22.06844139099121, | |
| "eval_runtime": 6.938, | |
| "eval_samples_per_second": 39.925, | |
| "eval_steps_per_second": 5.045, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.5487364620938628, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 27.54990701267862, | |
| "train_runtime": 5178.2941, | |
| "train_samples_per_second": 28.851, | |
| "train_steps_per_second": 3.615 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |