| { | |
| "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": 0.5270758122743683, | |
| "eval_loss": 27.07662582397461, | |
| "eval_runtime": 3.2794, | |
| "eval_samples_per_second": 84.466, | |
| "eval_steps_per_second": 10.673, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.009732905982905982, | |
| "loss": 29.447, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 24.088668823242188, | |
| "eval_runtime": 3.2857, | |
| "eval_samples_per_second": 84.304, | |
| "eval_steps_per_second": 10.652, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 23.964040756225586, | |
| "eval_runtime": 3.2866, | |
| "eval_samples_per_second": 84.282, | |
| "eval_steps_per_second": 10.649, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.009465811965811966, | |
| "loss": 27.7172, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 22.026033401489258, | |
| "eval_runtime": 3.2885, | |
| "eval_samples_per_second": 84.232, | |
| "eval_steps_per_second": 10.643, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.009198717948717948, | |
| "loss": 26.4345, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 22.050241470336914, | |
| "eval_runtime": 3.2777, | |
| "eval_samples_per_second": 84.511, | |
| "eval_steps_per_second": 10.678, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 22.933731079101562, | |
| "eval_runtime": 3.2673, | |
| "eval_samples_per_second": 84.78, | |
| "eval_steps_per_second": 10.712, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.008931623931623932, | |
| "loss": 27.0832, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 21.285945892333984, | |
| "eval_runtime": 3.2711, | |
| "eval_samples_per_second": 84.68, | |
| "eval_steps_per_second": 10.7, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 21.470870971679688, | |
| "eval_runtime": 3.2744, | |
| "eval_samples_per_second": 84.596, | |
| "eval_steps_per_second": 10.689, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.008664529914529914, | |
| "loss": 25.6523, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 20.353946685791016, | |
| "eval_runtime": 3.2711, | |
| "eval_samples_per_second": 84.68, | |
| "eval_steps_per_second": 10.7, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.008397435897435898, | |
| "loss": 25.5288, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 21.298246383666992, | |
| "eval_runtime": 3.2754, | |
| "eval_samples_per_second": 84.569, | |
| "eval_steps_per_second": 10.686, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 22.059904098510742, | |
| "eval_runtime": 3.2708, | |
| "eval_samples_per_second": 84.69, | |
| "eval_steps_per_second": 10.701, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 0.00813034188034188, | |
| "loss": 25.9846, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 22.10004997253418, | |
| "eval_runtime": 3.2728, | |
| "eval_samples_per_second": 84.637, | |
| "eval_steps_per_second": 10.694, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.007863247863247862, | |
| "loss": 26.609, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 24.113325119018555, | |
| "eval_runtime": 3.2603, | |
| "eval_samples_per_second": 84.961, | |
| "eval_steps_per_second": 10.735, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 22.439191818237305, | |
| "eval_runtime": 3.2721, | |
| "eval_samples_per_second": 84.656, | |
| "eval_steps_per_second": 10.697, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 0.007596153846153846, | |
| "loss": 26.7751, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 22.051416397094727, | |
| "eval_runtime": 3.2657, | |
| "eval_samples_per_second": 84.82, | |
| "eval_steps_per_second": 10.717, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 21.441261291503906, | |
| "eval_runtime": 3.2728, | |
| "eval_samples_per_second": 84.636, | |
| "eval_steps_per_second": 10.694, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.007329059829059828, | |
| "loss": 25.8484, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 21.67586898803711, | |
| "eval_runtime": 3.2717, | |
| "eval_samples_per_second": 84.666, | |
| "eval_steps_per_second": 10.698, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.007061965811965812, | |
| "loss": 25.7937, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 21.272621154785156, | |
| "eval_runtime": 3.2737, | |
| "eval_samples_per_second": 84.614, | |
| "eval_steps_per_second": 10.691, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 21.248903274536133, | |
| "eval_runtime": 3.2728, | |
| "eval_samples_per_second": 84.638, | |
| "eval_steps_per_second": 10.694, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.006794871794871795, | |
| "loss": 25.6479, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 21.18812370300293, | |
| "eval_runtime": 3.2717, | |
| "eval_samples_per_second": 84.665, | |
| "eval_steps_per_second": 10.698, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 0.006527777777777778, | |
| "loss": 25.6144, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 21.03541374206543, | |
| "eval_runtime": 3.2731, | |
| "eval_samples_per_second": 84.628, | |
| "eval_steps_per_second": 10.693, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 21.06875228881836, | |
| "eval_runtime": 3.27, | |
| "eval_samples_per_second": 84.709, | |
| "eval_steps_per_second": 10.703, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.006260683760683761, | |
| "loss": 25.4368, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 21.21544075012207, | |
| "eval_runtime": 3.2774, | |
| "eval_samples_per_second": 84.519, | |
| "eval_steps_per_second": 10.679, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 21.234771728515625, | |
| "eval_runtime": 3.2735, | |
| "eval_samples_per_second": 84.62, | |
| "eval_steps_per_second": 10.692, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 0.005993589743589743, | |
| "loss": 25.5564, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 21.15097999572754, | |
| "eval_runtime": 3.2785, | |
| "eval_samples_per_second": 84.49, | |
| "eval_steps_per_second": 10.676, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.005726495726495726, | |
| "loss": 25.5495, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 21.399234771728516, | |
| "eval_runtime": 3.2797, | |
| "eval_samples_per_second": 84.46, | |
| "eval_steps_per_second": 10.672, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 21.403474807739258, | |
| "eval_runtime": 3.2783, | |
| "eval_samples_per_second": 84.496, | |
| "eval_steps_per_second": 10.676, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 0.005459401709401709, | |
| "loss": 25.4536, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 20.964290618896484, | |
| "eval_runtime": 3.2695, | |
| "eval_samples_per_second": 84.721, | |
| "eval_steps_per_second": 10.705, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.005192307692307693, | |
| "loss": 25.3641, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 20.778039932250977, | |
| "eval_runtime": 3.2743, | |
| "eval_samples_per_second": 84.598, | |
| "eval_steps_per_second": 10.689, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 21.47609519958496, | |
| "eval_runtime": 3.2759, | |
| "eval_samples_per_second": 84.557, | |
| "eval_steps_per_second": 10.684, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 0.004925213675213675, | |
| "loss": 25.4089, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 21.10526466369629, | |
| "eval_runtime": 3.2774, | |
| "eval_samples_per_second": 84.519, | |
| "eval_steps_per_second": 10.679, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 21.15567398071289, | |
| "eval_runtime": 3.2733, | |
| "eval_samples_per_second": 84.624, | |
| "eval_steps_per_second": 10.693, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.004658119658119658, | |
| "loss": 25.6056, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 21.017988204956055, | |
| "eval_runtime": 3.2716, | |
| "eval_samples_per_second": 84.668, | |
| "eval_steps_per_second": 10.698, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 0.004391025641025641, | |
| "loss": 25.5078, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 21.102638244628906, | |
| "eval_runtime": 3.2768, | |
| "eval_samples_per_second": 84.534, | |
| "eval_steps_per_second": 10.681, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 21.372339248657227, | |
| "eval_runtime": 3.278, | |
| "eval_samples_per_second": 84.503, | |
| "eval_steps_per_second": 10.677, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.004123931623931624, | |
| "loss": 25.6607, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 21.430931091308594, | |
| "eval_runtime": 3.271, | |
| "eval_samples_per_second": 84.683, | |
| "eval_steps_per_second": 10.7, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 0.003856837606837607, | |
| "loss": 25.9641, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 21.40829849243164, | |
| "eval_runtime": 3.2761, | |
| "eval_samples_per_second": 84.553, | |
| "eval_steps_per_second": 10.684, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 21.287500381469727, | |
| "eval_runtime": 3.2756, | |
| "eval_samples_per_second": 84.564, | |
| "eval_steps_per_second": 10.685, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.0035897435897435897, | |
| "loss": 25.6756, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 21.453834533691406, | |
| "eval_runtime": 3.2765, | |
| "eval_samples_per_second": 84.54, | |
| "eval_steps_per_second": 10.682, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 21.18698501586914, | |
| "eval_runtime": 3.2787, | |
| "eval_samples_per_second": 84.484, | |
| "eval_steps_per_second": 10.675, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 0.0033226495726495727, | |
| "loss": 25.4709, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 21.079587936401367, | |
| "eval_runtime": 3.2743, | |
| "eval_samples_per_second": 84.599, | |
| "eval_steps_per_second": 10.689, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0030555555555555557, | |
| "loss": 25.2913, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 20.941194534301758, | |
| "eval_runtime": 3.265, | |
| "eval_samples_per_second": 84.839, | |
| "eval_steps_per_second": 10.72, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 20.893199920654297, | |
| "eval_runtime": 3.2682, | |
| "eval_samples_per_second": 84.756, | |
| "eval_steps_per_second": 10.709, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 0.0027884615384615387, | |
| "loss": 25.1541, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 20.917190551757812, | |
| "eval_runtime": 3.2676, | |
| "eval_samples_per_second": 84.771, | |
| "eval_steps_per_second": 10.711, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.0025213675213675213, | |
| "loss": 25.0679, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 20.67868995666504, | |
| "eval_runtime": 3.2617, | |
| "eval_samples_per_second": 84.924, | |
| "eval_steps_per_second": 10.731, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 20.630779266357422, | |
| "eval_runtime": 3.2725, | |
| "eval_samples_per_second": 84.644, | |
| "eval_steps_per_second": 10.695, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 0.0022542735042735042, | |
| "loss": 24.965, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 20.524005889892578, | |
| "eval_runtime": 3.262, | |
| "eval_samples_per_second": 84.918, | |
| "eval_steps_per_second": 10.73, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 20.637798309326172, | |
| "eval_runtime": 3.2694, | |
| "eval_samples_per_second": 84.724, | |
| "eval_steps_per_second": 10.705, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 0.0019871794871794872, | |
| "loss": 24.8969, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 20.50297737121582, | |
| "eval_runtime": 3.2754, | |
| "eval_samples_per_second": 84.57, | |
| "eval_steps_per_second": 10.686, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 0.0017200854700854702, | |
| "loss": 24.8319, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 20.325740814208984, | |
| "eval_runtime": 3.272, | |
| "eval_samples_per_second": 84.657, | |
| "eval_steps_per_second": 10.697, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 20.298986434936523, | |
| "eval_runtime": 3.2697, | |
| "eval_samples_per_second": 84.718, | |
| "eval_steps_per_second": 10.704, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 0.0014529914529914532, | |
| "loss": 24.7301, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 20.36614418029785, | |
| "eval_runtime": 3.272, | |
| "eval_samples_per_second": 84.658, | |
| "eval_steps_per_second": 10.697, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 0.001185897435897436, | |
| "loss": 24.6644, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 20.20882225036621, | |
| "eval_runtime": 3.2794, | |
| "eval_samples_per_second": 84.467, | |
| "eval_steps_per_second": 10.673, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 20.15430450439453, | |
| "eval_runtime": 3.2814, | |
| "eval_samples_per_second": 84.414, | |
| "eval_steps_per_second": 10.666, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 0.0009188034188034189, | |
| "loss": 24.5917, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 20.086036682128906, | |
| "eval_runtime": 3.2838, | |
| "eval_samples_per_second": 84.354, | |
| "eval_steps_per_second": 10.658, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 20.067216873168945, | |
| "eval_runtime": 3.2742, | |
| "eval_samples_per_second": 84.601, | |
| "eval_steps_per_second": 10.69, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 0.0006517094017094017, | |
| "loss": 24.5505, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 20.051782608032227, | |
| "eval_runtime": 3.2808, | |
| "eval_samples_per_second": 84.431, | |
| "eval_steps_per_second": 10.668, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 0.00038461538461538467, | |
| "loss": 24.5065, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 20.003583908081055, | |
| "eval_runtime": 3.2825, | |
| "eval_samples_per_second": 84.387, | |
| "eval_steps_per_second": 10.663, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 19.99390411376953, | |
| "eval_runtime": 3.2846, | |
| "eval_samples_per_second": 84.332, | |
| "eval_steps_per_second": 10.656, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 0.00011752136752136752, | |
| "loss": 24.4773, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 19.989938735961914, | |
| "eval_runtime": 3.2766, | |
| "eval_samples_per_second": 84.539, | |
| "eval_steps_per_second": 10.682, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 7.25686341470208e+16, | |
| "train_loss": 25.62186534914196, | |
| "train_runtime": 3131.9415, | |
| "train_samples_per_second": 47.702, | |
| "train_steps_per_second": 5.977 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 7.25686341470208e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |