| { | |
| "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": 0.45126353790613716, | |
| "eval_loss": 33.11911392211914, | |
| "eval_runtime": 3.3144, | |
| "eval_samples_per_second": 83.574, | |
| "eval_steps_per_second": 10.56, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.45126353790613716, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00048664529914529915, | |
| "loss": 33.504, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5126353790613718, | |
| "eval_loss": 30.1104793548584, | |
| "eval_runtime": 3.3405, | |
| "eval_samples_per_second": 82.922, | |
| "eval_steps_per_second": 10.478, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5126353790613718, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 28.659645080566406, | |
| "eval_runtime": 3.3435, | |
| "eval_samples_per_second": 82.847, | |
| "eval_steps_per_second": 10.468, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5126353790613718, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.0004732905982905983, | |
| "loss": 29.6796, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5018050541516246, | |
| "eval_loss": 28.11885643005371, | |
| "eval_runtime": 3.3454, | |
| "eval_samples_per_second": 82.799, | |
| "eval_steps_per_second": 10.462, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5126353790613718, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.0004599358974358974, | |
| "loss": 28.1744, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 24.776138305664062, | |
| "eval_runtime": 3.3621, | |
| "eval_samples_per_second": 82.389, | |
| "eval_steps_per_second": 10.41, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5126353790613718, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5234657039711191, | |
| "eval_loss": 21.962665557861328, | |
| "eval_runtime": 6.9401, | |
| "eval_samples_per_second": 39.913, | |
| "eval_steps_per_second": 5.043, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5234657039711191, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.0004465811965811966, | |
| "loss": 24.4505, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 19.001855850219727, | |
| "eval_runtime": 6.9517, | |
| "eval_samples_per_second": 39.847, | |
| "eval_steps_per_second": 5.035, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 6, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 17.127729415893555, | |
| "eval_runtime": 6.9691, | |
| "eval_samples_per_second": 39.747, | |
| "eval_steps_per_second": 5.022, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 6, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.00043322649572649576, | |
| "loss": 21.3932, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 16.165973663330078, | |
| "eval_runtime": 6.9785, | |
| "eval_samples_per_second": 39.693, | |
| "eval_steps_per_second": 5.015, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 6, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.0004198717948717949, | |
| "loss": 19.6922, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 15.595091819763184, | |
| "eval_runtime": 6.979, | |
| "eval_samples_per_second": 39.691, | |
| "eval_steps_per_second": 5.015, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 6, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 15.082429885864258, | |
| "eval_runtime": 6.9266, | |
| "eval_samples_per_second": 39.991, | |
| "eval_steps_per_second": 5.053, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 6, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 0.00040651709401709403, | |
| "loss": 18.9663, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 14.85202407836914, | |
| "eval_runtime": 6.9923, | |
| "eval_samples_per_second": 39.615, | |
| "eval_steps_per_second": 5.006, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 6, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.00039316239316239317, | |
| "loss": 18.4915, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 14.519148826599121, | |
| "eval_runtime": 6.9304, | |
| "eval_samples_per_second": 39.969, | |
| "eval_steps_per_second": 5.05, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 6, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 14.279762268066406, | |
| "eval_runtime": 6.951, | |
| "eval_samples_per_second": 39.851, | |
| "eval_steps_per_second": 5.035, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 6, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 0.0003798076923076923, | |
| "loss": 18.1712, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 14.12159538269043, | |
| "eval_runtime": 6.9418, | |
| "eval_samples_per_second": 39.903, | |
| "eval_steps_per_second": 5.042, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 6, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.964988708496094, | |
| "eval_runtime": 7.0061, | |
| "eval_samples_per_second": 39.537, | |
| "eval_steps_per_second": 4.996, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 6, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.00036645299145299145, | |
| "loss": 17.9497, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5306859205776173, | |
| "eval_loss": 13.823695182800293, | |
| "eval_runtime": 7.0035, | |
| "eval_samples_per_second": 39.552, | |
| "eval_steps_per_second": 4.997, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.00035309829059829064, | |
| "loss": 17.7679, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.703110694885254, | |
| "eval_runtime": 7.0049, | |
| "eval_samples_per_second": 39.544, | |
| "eval_steps_per_second": 4.996, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.660018920898438, | |
| "eval_runtime": 7.0006, | |
| "eval_samples_per_second": 39.568, | |
| "eval_steps_per_second": 5.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.0003397435897435898, | |
| "loss": 17.6276, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.494658470153809, | |
| "eval_runtime": 6.9826, | |
| "eval_samples_per_second": 39.67, | |
| "eval_steps_per_second": 5.012, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 0.0003263888888888889, | |
| "loss": 17.4928, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.392991065979004, | |
| "eval_runtime": 7.0139, | |
| "eval_samples_per_second": 39.493, | |
| "eval_steps_per_second": 4.99, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.324033737182617, | |
| "eval_runtime": 6.9483, | |
| "eval_samples_per_second": 39.866, | |
| "eval_steps_per_second": 5.037, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.00031303418803418806, | |
| "loss": 17.3723, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.230449676513672, | |
| "eval_runtime": 6.9663, | |
| "eval_samples_per_second": 39.763, | |
| "eval_steps_per_second": 5.024, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.154191017150879, | |
| "eval_runtime": 6.8761, | |
| "eval_samples_per_second": 40.284, | |
| "eval_steps_per_second": 5.09, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 0.0002996794871794872, | |
| "loss": 17.2738, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.051920890808105, | |
| "eval_runtime": 7.0035, | |
| "eval_samples_per_second": 39.552, | |
| "eval_steps_per_second": 4.998, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.00028632478632478634, | |
| "loss": 17.1691, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.035033226013184, | |
| "eval_runtime": 6.9965, | |
| "eval_samples_per_second": 39.591, | |
| "eval_steps_per_second": 5.003, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.924749374389648, | |
| "eval_runtime": 6.9729, | |
| "eval_samples_per_second": 39.725, | |
| "eval_steps_per_second": 5.019, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 0.0002729700854700855, | |
| "loss": 17.0746, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5126353790613718, | |
| "eval_loss": 12.845624923706055, | |
| "eval_runtime": 6.9969, | |
| "eval_samples_per_second": 39.589, | |
| "eval_steps_per_second": 5.002, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.00025961538461538467, | |
| "loss": 16.9881, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.794411659240723, | |
| "eval_runtime": 7.0003, | |
| "eval_samples_per_second": 39.57, | |
| "eval_steps_per_second": 5.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.747382164001465, | |
| "eval_runtime": 6.9138, | |
| "eval_samples_per_second": 40.065, | |
| "eval_steps_per_second": 5.062, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 0.0002462606837606838, | |
| "loss": 16.9201, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.713140487670898, | |
| "eval_runtime": 7.0105, | |
| "eval_samples_per_second": 39.512, | |
| "eval_steps_per_second": 4.992, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.667033195495605, | |
| "eval_runtime": 6.9755, | |
| "eval_samples_per_second": 39.71, | |
| "eval_steps_per_second": 5.018, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.00023290598290598292, | |
| "loss": 16.8521, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.62850284576416, | |
| "eval_runtime": 7.0056, | |
| "eval_samples_per_second": 39.54, | |
| "eval_steps_per_second": 4.996, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 0.00021955128205128206, | |
| "loss": 16.7917, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.583124160766602, | |
| "eval_runtime": 7.0251, | |
| "eval_samples_per_second": 39.43, | |
| "eval_steps_per_second": 4.982, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.548803329467773, | |
| "eval_runtime": 7.0257, | |
| "eval_samples_per_second": 39.427, | |
| "eval_steps_per_second": 4.982, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.0002061965811965812, | |
| "loss": 16.7467, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.52231502532959, | |
| "eval_runtime": 6.9389, | |
| "eval_samples_per_second": 39.92, | |
| "eval_steps_per_second": 5.044, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 0.00019284188034188036, | |
| "loss": 16.7092, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.48852825164795, | |
| "eval_runtime": 7.0064, | |
| "eval_samples_per_second": 39.535, | |
| "eval_steps_per_second": 4.995, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.46063232421875, | |
| "eval_runtime": 7.024, | |
| "eval_samples_per_second": 39.436, | |
| "eval_steps_per_second": 4.983, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.0001794871794871795, | |
| "loss": 16.6584, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.435160636901855, | |
| "eval_runtime": 7.0389, | |
| "eval_samples_per_second": 39.353, | |
| "eval_steps_per_second": 4.972, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.411623001098633, | |
| "eval_runtime": 6.9653, | |
| "eval_samples_per_second": 39.768, | |
| "eval_steps_per_second": 5.025, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 0.00016613247863247864, | |
| "loss": 16.6245, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.39089584350586, | |
| "eval_runtime": 7.0116, | |
| "eval_samples_per_second": 39.506, | |
| "eval_steps_per_second": 4.992, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0001527777777777778, | |
| "loss": 16.5986, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.411885261535645, | |
| "eval_runtime": 7.0008, | |
| "eval_samples_per_second": 39.567, | |
| "eval_steps_per_second": 4.999, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.347926139831543, | |
| "eval_runtime": 7.0204, | |
| "eval_samples_per_second": 39.457, | |
| "eval_steps_per_second": 4.986, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 0.00013942307692307694, | |
| "loss": 16.5728, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.332773208618164, | |
| "eval_runtime": 6.9788, | |
| "eval_samples_per_second": 39.692, | |
| "eval_steps_per_second": 5.015, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.00012606837606837608, | |
| "loss": 16.5395, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.335871696472168, | |
| "eval_runtime": 7.0332, | |
| "eval_samples_per_second": 39.384, | |
| "eval_steps_per_second": 4.976, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.3195161819458, | |
| "eval_runtime": 7.0217, | |
| "eval_samples_per_second": 39.449, | |
| "eval_steps_per_second": 4.985, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 0.00011271367521367522, | |
| "loss": 16.5222, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.303064346313477, | |
| "eval_runtime": 7.0206, | |
| "eval_samples_per_second": 39.456, | |
| "eval_steps_per_second": 4.985, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.27875804901123, | |
| "eval_runtime": 7.0328, | |
| "eval_samples_per_second": 39.387, | |
| "eval_steps_per_second": 4.977, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 9.935897435897436e-05, | |
| "loss": 16.5068, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.5595667870036101, | |
| "eval_loss": 12.263042449951172, | |
| "eval_runtime": 7.0151, | |
| "eval_samples_per_second": 39.486, | |
| "eval_steps_per_second": 4.989, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 8.600427350427351e-05, | |
| "loss": 16.4947, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.253250122070312, | |
| "eval_runtime": 6.9744, | |
| "eval_samples_per_second": 39.717, | |
| "eval_steps_per_second": 5.018, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.25307559967041, | |
| "eval_runtime": 6.974, | |
| "eval_samples_per_second": 39.719, | |
| "eval_steps_per_second": 5.019, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 7.264957264957266e-05, | |
| "loss": 16.4716, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.247926712036133, | |
| "eval_runtime": 6.9555, | |
| "eval_samples_per_second": 39.825, | |
| "eval_steps_per_second": 5.032, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 5.929487179487179e-05, | |
| "loss": 16.4646, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.227167129516602, | |
| "eval_runtime": 6.9728, | |
| "eval_samples_per_second": 39.726, | |
| "eval_steps_per_second": 5.019, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.221315383911133, | |
| "eval_runtime": 7.0581, | |
| "eval_samples_per_second": 39.246, | |
| "eval_steps_per_second": 4.959, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 4.5940170940170944e-05, | |
| "loss": 16.4479, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.21772289276123, | |
| "eval_runtime": 6.9495, | |
| "eval_samples_per_second": 39.859, | |
| "eval_steps_per_second": 5.036, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 12.21120834350586, | |
| "eval_runtime": 6.9033, | |
| "eval_samples_per_second": 40.126, | |
| "eval_steps_per_second": 5.07, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 3.258547008547009e-05, | |
| "loss": 16.447, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.21062183380127, | |
| "eval_runtime": 7.0594, | |
| "eval_samples_per_second": 39.239, | |
| "eval_steps_per_second": 4.958, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 1.923076923076923e-05, | |
| "loss": 16.4403, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.205535888671875, | |
| "eval_runtime": 7.0065, | |
| "eval_samples_per_second": 39.535, | |
| "eval_steps_per_second": 4.995, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.203934669494629, | |
| "eval_runtime": 7.0384, | |
| "eval_samples_per_second": 39.355, | |
| "eval_steps_per_second": 4.973, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 5.876068376068376e-06, | |
| "loss": 16.4371, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.203690528869629, | |
| "eval_runtime": 7.0557, | |
| "eval_samples_per_second": 39.259, | |
| "eval_steps_per_second": 4.961, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 18.475407879169172, | |
| "train_runtime": 6147.1974, | |
| "train_samples_per_second": 24.304, | |
| "train_steps_per_second": 3.045 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |