| { | |
| "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": 23.58551788330078, | |
| "eval_runtime": 6.7563, | |
| "eval_samples_per_second": 40.999, | |
| "eval_steps_per_second": 5.18, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.009732905982905982, | |
| "loss": 27.3295, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 15.767162322998047, | |
| "eval_runtime": 6.7306, | |
| "eval_samples_per_second": 41.155, | |
| "eval_steps_per_second": 5.2, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 14.181631088256836, | |
| "eval_runtime": 6.7376, | |
| "eval_samples_per_second": 41.113, | |
| "eval_steps_per_second": 5.195, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.009465811965811966, | |
| "loss": 19.6736, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.581140518188477, | |
| "eval_runtime": 6.8422, | |
| "eval_samples_per_second": 40.484, | |
| "eval_steps_per_second": 5.115, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.009198717948717948, | |
| "loss": 18.8481, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.385133743286133, | |
| "eval_runtime": 6.799, | |
| "eval_samples_per_second": 40.741, | |
| "eval_steps_per_second": 5.148, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.019899368286133, | |
| "eval_runtime": 6.7829, | |
| "eval_samples_per_second": 40.838, | |
| "eval_steps_per_second": 5.16, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.008931623931623932, | |
| "loss": 18.5899, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.48375451263537905, | |
| "eval_loss": 12.949692726135254, | |
| "eval_runtime": 6.8051, | |
| "eval_samples_per_second": 40.705, | |
| "eval_steps_per_second": 5.143, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.996054649353027, | |
| "eval_runtime": 6.7778, | |
| "eval_samples_per_second": 40.869, | |
| "eval_steps_per_second": 5.164, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.008664529914529914, | |
| "loss": 18.473, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.827549934387207, | |
| "eval_runtime": 6.7783, | |
| "eval_samples_per_second": 40.866, | |
| "eval_steps_per_second": 5.164, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.008397435897435898, | |
| "loss": 18.3073, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.699183464050293, | |
| "eval_runtime": 6.8687, | |
| "eval_samples_per_second": 40.328, | |
| "eval_steps_per_second": 5.096, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.515963554382324, | |
| "eval_runtime": 6.7643, | |
| "eval_samples_per_second": 40.95, | |
| "eval_steps_per_second": 5.174, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 0.00813034188034188, | |
| "loss": 18.2739, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5306859205776173, | |
| "eval_loss": 12.67311954498291, | |
| "eval_runtime": 6.8268, | |
| "eval_samples_per_second": 40.575, | |
| "eval_steps_per_second": 5.127, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.007863247863247862, | |
| "loss": 18.1236, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.606614112854004, | |
| "eval_runtime": 6.7237, | |
| "eval_samples_per_second": 41.198, | |
| "eval_steps_per_second": 5.205, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.580245971679688, | |
| "eval_runtime": 6.7327, | |
| "eval_samples_per_second": 41.143, | |
| "eval_steps_per_second": 5.199, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 0.007596153846153846, | |
| "loss": 18.1096, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.644716262817383, | |
| "eval_runtime": 6.8476, | |
| "eval_samples_per_second": 40.452, | |
| "eval_steps_per_second": 5.111, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.309383392333984, | |
| "eval_runtime": 6.7717, | |
| "eval_samples_per_second": 40.906, | |
| "eval_steps_per_second": 5.169, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.007329059829059828, | |
| "loss": 18.1134, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.096991539001465, | |
| "eval_runtime": 6.9132, | |
| "eval_samples_per_second": 40.068, | |
| "eval_steps_per_second": 5.063, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.007061965811965812, | |
| "loss": 18.1098, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.729278564453125, | |
| "eval_runtime": 6.7858, | |
| "eval_samples_per_second": 40.821, | |
| "eval_steps_per_second": 5.158, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.616609573364258, | |
| "eval_runtime": 6.7613, | |
| "eval_samples_per_second": 40.968, | |
| "eval_steps_per_second": 5.177, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.006794871794871795, | |
| "loss": 18.0277, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.560620307922363, | |
| "eval_runtime": 6.7972, | |
| "eval_samples_per_second": 40.752, | |
| "eval_steps_per_second": 5.149, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 0.006527777777777778, | |
| "loss": 18.0289, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.532211303710938, | |
| "eval_runtime": 6.7373, | |
| "eval_samples_per_second": 41.114, | |
| "eval_steps_per_second": 5.195, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.734131813049316, | |
| "eval_runtime": 6.7144, | |
| "eval_samples_per_second": 41.255, | |
| "eval_steps_per_second": 5.213, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.006260683760683761, | |
| "loss": 18.0223, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.549654960632324, | |
| "eval_runtime": 6.7477, | |
| "eval_samples_per_second": 41.051, | |
| "eval_steps_per_second": 5.187, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.419885635375977, | |
| "eval_runtime": 6.7465, | |
| "eval_samples_per_second": 41.058, | |
| "eval_steps_per_second": 5.188, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 0.005993589743589743, | |
| "loss": 17.9317, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.786826133728027, | |
| "eval_runtime": 6.8039, | |
| "eval_samples_per_second": 40.712, | |
| "eval_steps_per_second": 5.144, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.005726495726495726, | |
| "loss": 17.9107, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.329524040222168, | |
| "eval_runtime": 6.7093, | |
| "eval_samples_per_second": 41.286, | |
| "eval_steps_per_second": 5.217, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.603827476501465, | |
| "eval_runtime": 6.715, | |
| "eval_samples_per_second": 41.251, | |
| "eval_steps_per_second": 5.212, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 0.005459401709401709, | |
| "loss": 17.8944, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.332864761352539, | |
| "eval_runtime": 6.7174, | |
| "eval_samples_per_second": 41.236, | |
| "eval_steps_per_second": 5.21, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.005192307692307693, | |
| "loss": 17.8667, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.303411483764648, | |
| "eval_runtime": 6.7285, | |
| "eval_samples_per_second": 41.168, | |
| "eval_steps_per_second": 5.202, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.460461616516113, | |
| "eval_runtime": 6.8018, | |
| "eval_samples_per_second": 40.725, | |
| "eval_steps_per_second": 5.146, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 0.004925213675213675, | |
| "loss": 17.8228, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.51104736328125, | |
| "eval_runtime": 6.7123, | |
| "eval_samples_per_second": 41.268, | |
| "eval_steps_per_second": 5.214, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.422727584838867, | |
| "eval_runtime": 6.7496, | |
| "eval_samples_per_second": 41.039, | |
| "eval_steps_per_second": 5.185, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.004658119658119658, | |
| "loss": 17.8006, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.297224044799805, | |
| "eval_runtime": 6.7368, | |
| "eval_samples_per_second": 41.118, | |
| "eval_steps_per_second": 5.195, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 0.004391025641025641, | |
| "loss": 17.76, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.301063537597656, | |
| "eval_runtime": 6.7413, | |
| "eval_samples_per_second": 41.09, | |
| "eval_steps_per_second": 5.192, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.217933654785156, | |
| "eval_runtime": 6.8901, | |
| "eval_samples_per_second": 40.203, | |
| "eval_steps_per_second": 5.08, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.004123931623931624, | |
| "loss": 17.7564, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.238066673278809, | |
| "eval_runtime": 6.8926, | |
| "eval_samples_per_second": 40.188, | |
| "eval_steps_per_second": 5.078, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 0.003856837606837607, | |
| "loss": 17.7084, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.874678611755371, | |
| "eval_runtime": 6.8036, | |
| "eval_samples_per_second": 40.714, | |
| "eval_steps_per_second": 5.144, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.194494247436523, | |
| "eval_runtime": 6.9457, | |
| "eval_samples_per_second": 39.881, | |
| "eval_steps_per_second": 5.039, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.0035897435897435897, | |
| "loss": 17.7035, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.21796703338623, | |
| "eval_runtime": 6.8901, | |
| "eval_samples_per_second": 40.202, | |
| "eval_steps_per_second": 5.08, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.282953262329102, | |
| "eval_runtime": 6.7911, | |
| "eval_samples_per_second": 40.788, | |
| "eval_steps_per_second": 5.154, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 0.0033226495726495727, | |
| "loss": 17.6668, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.4693140794223827, | |
| "eval_loss": 12.185731887817383, | |
| "eval_runtime": 6.8018, | |
| "eval_samples_per_second": 40.724, | |
| "eval_steps_per_second": 5.146, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0030555555555555557, | |
| "loss": 17.6396, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.5379061371841155, | |
| "eval_loss": 12.2239408493042, | |
| "eval_runtime": 6.8368, | |
| "eval_samples_per_second": 40.516, | |
| "eval_steps_per_second": 5.119, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.158435821533203, | |
| "eval_runtime": 6.7914, | |
| "eval_samples_per_second": 40.787, | |
| "eval_steps_per_second": 5.154, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 0.0027884615384615387, | |
| "loss": 17.6452, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.318547248840332, | |
| "eval_runtime": 6.7753, | |
| "eval_samples_per_second": 40.884, | |
| "eval_steps_per_second": 5.166, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.0025213675213675213, | |
| "loss": 17.6074, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.24209213256836, | |
| "eval_runtime": 6.8413, | |
| "eval_samples_per_second": 40.489, | |
| "eval_steps_per_second": 5.116, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.191246032714844, | |
| "eval_runtime": 6.7445, | |
| "eval_samples_per_second": 41.071, | |
| "eval_steps_per_second": 5.189, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 0.0022542735042735042, | |
| "loss": 17.6167, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.202165603637695, | |
| "eval_runtime": 6.7512, | |
| "eval_samples_per_second": 41.03, | |
| "eval_steps_per_second": 5.184, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.13256549835205, | |
| "eval_runtime": 6.7893, | |
| "eval_samples_per_second": 40.799, | |
| "eval_steps_per_second": 5.155, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 0.0019871794871794872, | |
| "loss": 17.5782, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.155043601989746, | |
| "eval_runtime": 6.8327, | |
| "eval_samples_per_second": 40.54, | |
| "eval_steps_per_second": 5.122, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 0.0017200854700854702, | |
| "loss": 17.562, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.225010871887207, | |
| "eval_runtime": 6.7916, | |
| "eval_samples_per_second": 40.786, | |
| "eval_steps_per_second": 5.153, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.119040489196777, | |
| "eval_runtime": 6.8127, | |
| "eval_samples_per_second": 40.659, | |
| "eval_steps_per_second": 5.137, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 0.0014529914529914532, | |
| "loss": 17.5409, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.150501251220703, | |
| "eval_runtime": 6.7591, | |
| "eval_samples_per_second": 40.982, | |
| "eval_steps_per_second": 5.178, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 0.001185897435897436, | |
| "loss": 17.5211, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.104633331298828, | |
| "eval_runtime": 6.8314, | |
| "eval_samples_per_second": 40.548, | |
| "eval_steps_per_second": 5.123, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.113192558288574, | |
| "eval_runtime": 6.8331, | |
| "eval_samples_per_second": 40.538, | |
| "eval_steps_per_second": 5.122, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 0.0009188034188034189, | |
| "loss": 17.5043, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.11585807800293, | |
| "eval_runtime": 6.8139, | |
| "eval_samples_per_second": 40.652, | |
| "eval_steps_per_second": 5.137, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.108481407165527, | |
| "eval_runtime": 6.7999, | |
| "eval_samples_per_second": 40.736, | |
| "eval_steps_per_second": 5.147, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 0.0006517094017094017, | |
| "loss": 17.4952, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.102400779724121, | |
| "eval_runtime": 6.9307, | |
| "eval_samples_per_second": 39.967, | |
| "eval_steps_per_second": 5.05, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 0.00038461538461538467, | |
| "loss": 17.4731, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.095499992370605, | |
| "eval_runtime": 6.771, | |
| "eval_samples_per_second": 40.91, | |
| "eval_steps_per_second": 5.169, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.09808349609375, | |
| "eval_runtime": 6.7995, | |
| "eval_samples_per_second": 40.738, | |
| "eval_steps_per_second": 5.147, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 0.00011752136752136752, | |
| "loss": 17.4654, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.09249496459961, | |
| "eval_runtime": 3.2881, | |
| "eval_samples_per_second": 84.244, | |
| "eval_steps_per_second": 10.645, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 18.167257181803386, | |
| "train_runtime": 6211.4613, | |
| "train_samples_per_second": 24.052, | |
| "train_steps_per_second": 3.014 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |