| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 53280, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.876876876876877e-08, | |
| "loss": 26.3774, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5.011261261261262e-06, | |
| "loss": 28.5448, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.0022522522522524e-05, | |
| "loss": 27.0258, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.5033783783783784e-05, | |
| "loss": 22.7776, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.0045045045045048e-05, | |
| "loss": 17.4592, | |
| "step": 1068 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.505630630630631e-05, | |
| "loss": 8.3509, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.006756756756757e-05, | |
| "loss": 0.8438, | |
| "step": 1602 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.507882882882883e-05, | |
| "loss": 0.3406, | |
| "step": 1869 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.0090090090090096e-05, | |
| "loss": 0.2968, | |
| "step": 2136 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.510135135135135e-05, | |
| "loss": 0.2324, | |
| "step": 2403 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.10719971358776093, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.1818, | |
| "eval_samples_per_second": 302.937, | |
| "eval_steps_per_second": 20.309, | |
| "step": 2664 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.011261261261262e-05, | |
| "loss": 0.122, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 5.512387387387388e-05, | |
| "loss": 0.1234, | |
| "step": 2937 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 6.013513513513514e-05, | |
| "loss": 0.1377, | |
| "step": 3204 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 6.514639639639641e-05, | |
| "loss": 0.0721, | |
| "step": 3471 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 7.015765765765766e-05, | |
| "loss": 0.0447, | |
| "step": 3738 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.516891891891891e-05, | |
| "loss": 0.0262, | |
| "step": 4005 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 8.018018018018019e-05, | |
| "loss": 0.0262, | |
| "step": 4272 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.519144144144144e-05, | |
| "loss": 0.0235, | |
| "step": 4539 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 9.02027027027027e-05, | |
| "loss": 0.0163, | |
| "step": 4806 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 9.521396396396397e-05, | |
| "loss": 0.0151, | |
| "step": 5073 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.04358534514904022, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.906, | |
| "eval_samples_per_second": 395.165, | |
| "eval_steps_per_second": 26.492, | |
| "step": 5328 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.997497497497498e-05, | |
| "loss": 0.014, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.941816816816817e-05, | |
| "loss": 0.0136, | |
| "step": 5607 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 9.886136136136137e-05, | |
| "loss": 0.007, | |
| "step": 5874 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 9.830455455455457e-05, | |
| "loss": 0.0144, | |
| "step": 6141 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.774774774774775e-05, | |
| "loss": 0.008, | |
| "step": 6408 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 9.719094094094095e-05, | |
| "loss": 0.0109, | |
| "step": 6675 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 9.663413413413414e-05, | |
| "loss": 0.0141, | |
| "step": 6942 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 9.607732732732732e-05, | |
| "loss": 0.011, | |
| "step": 7209 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 9.552052052052053e-05, | |
| "loss": 0.0136, | |
| "step": 7476 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 9.496371371371372e-05, | |
| "loss": 0.0094, | |
| "step": 7743 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.024132976308465004, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.9049, | |
| "eval_samples_per_second": 395.615, | |
| "eval_steps_per_second": 26.522, | |
| "step": 7992 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 9.440690690690692e-05, | |
| "loss": 0.0158, | |
| "step": 8010 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 9.38501001001001e-05, | |
| "loss": 0.0085, | |
| "step": 8277 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 9.329329329329329e-05, | |
| "loss": 0.0074, | |
| "step": 8544 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 9.27364864864865e-05, | |
| "loss": 0.0069, | |
| "step": 8811 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 9.217967967967968e-05, | |
| "loss": 0.0049, | |
| "step": 9078 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 9.162287287287288e-05, | |
| "loss": 0.0045, | |
| "step": 9345 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 9.106606606606607e-05, | |
| "loss": 0.0053, | |
| "step": 9612 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 9.050925925925925e-05, | |
| "loss": 0.0069, | |
| "step": 9879 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 8.995245245245245e-05, | |
| "loss": 0.0067, | |
| "step": 10146 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 8.939564564564565e-05, | |
| "loss": 0.0056, | |
| "step": 10413 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.030885161831974983, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.9782, | |
| "eval_samples_per_second": 365.991, | |
| "eval_steps_per_second": 24.536, | |
| "step": 10656 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 8.883883883883885e-05, | |
| "loss": 0.0057, | |
| "step": 10680 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 8.828203203203204e-05, | |
| "loss": 0.0018, | |
| "step": 10947 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 8.772522522522522e-05, | |
| "loss": 0.0034, | |
| "step": 11214 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 8.716841841841842e-05, | |
| "loss": 0.0074, | |
| "step": 11481 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 8.661161161161162e-05, | |
| "loss": 0.002, | |
| "step": 11748 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 8.605480480480482e-05, | |
| "loss": 0.0121, | |
| "step": 12015 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 8.5497997997998e-05, | |
| "loss": 0.0049, | |
| "step": 12282 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 8.49411911911912e-05, | |
| "loss": 0.0045, | |
| "step": 12549 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 8.438438438438439e-05, | |
| "loss": 0.0022, | |
| "step": 12816 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 8.382757757757757e-05, | |
| "loss": 0.0068, | |
| "step": 13083 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.03561040014028549, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.882, | |
| "eval_samples_per_second": 405.884, | |
| "eval_steps_per_second": 27.21, | |
| "step": 13320 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 8.327077077077078e-05, | |
| "loss": 0.0063, | |
| "step": 13350 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 8.271396396396397e-05, | |
| "loss": 0.002, | |
| "step": 13617 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 8.215715715715717e-05, | |
| "loss": 0.007, | |
| "step": 13884 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 8.160035035035035e-05, | |
| "loss": 0.0036, | |
| "step": 14151 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 8.104354354354354e-05, | |
| "loss": 0.0036, | |
| "step": 14418 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 8.048673673673675e-05, | |
| "loss": 0.0087, | |
| "step": 14685 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 7.992992992992994e-05, | |
| "loss": 0.0013, | |
| "step": 14952 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 7.937312312312313e-05, | |
| "loss": 0.0031, | |
| "step": 15219 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 7.881631631631632e-05, | |
| "loss": 0.0031, | |
| "step": 15486 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 7.82595095095095e-05, | |
| "loss": 0.0041, | |
| "step": 15753 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.018554789945483208, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.8772, | |
| "eval_samples_per_second": 408.133, | |
| "eval_steps_per_second": 27.361, | |
| "step": 15984 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 7.77027027027027e-05, | |
| "loss": 0.0044, | |
| "step": 16020 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 7.71458958958959e-05, | |
| "loss": 0.0012, | |
| "step": 16287 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 7.65890890890891e-05, | |
| "loss": 0.0036, | |
| "step": 16554 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 7.603228228228229e-05, | |
| "loss": 0.0028, | |
| "step": 16821 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 7.547547547547547e-05, | |
| "loss": 0.0039, | |
| "step": 17088 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 7.491866866866867e-05, | |
| "loss": 0.0013, | |
| "step": 17355 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 7.436186186186187e-05, | |
| "loss": 0.0026, | |
| "step": 17622 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 7.380505505505507e-05, | |
| "loss": 0.0015, | |
| "step": 17889 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 7.324824824824825e-05, | |
| "loss": 0.0009, | |
| "step": 18156 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 7.269144144144144e-05, | |
| "loss": 0.0034, | |
| "step": 18423 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.04260706901550293, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.9016, | |
| "eval_samples_per_second": 397.069, | |
| "eval_steps_per_second": 26.619, | |
| "step": 18648 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 7.213463463463464e-05, | |
| "loss": 0.0027, | |
| "step": 18690 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 7.157782782782782e-05, | |
| "loss": 0.0018, | |
| "step": 18957 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 7.102102102102103e-05, | |
| "loss": 0.0024, | |
| "step": 19224 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 7.046421421421422e-05, | |
| "loss": 0.0021, | |
| "step": 19491 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 6.99074074074074e-05, | |
| "loss": 0.0017, | |
| "step": 19758 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 6.93506006006006e-05, | |
| "loss": 0.0013, | |
| "step": 20025 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 6.879379379379379e-05, | |
| "loss": 0.0025, | |
| "step": 20292 | |
| }, | |
| { | |
| "epoch": 7.72, | |
| "learning_rate": 6.8236986986987e-05, | |
| "loss": 0.0017, | |
| "step": 20559 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 6.768018018018019e-05, | |
| "loss": 0.0022, | |
| "step": 20826 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 6.712337337337337e-05, | |
| "loss": 0.0043, | |
| "step": 21093 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.017180927097797394, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.8803, | |
| "eval_samples_per_second": 406.66, | |
| "eval_steps_per_second": 27.262, | |
| "step": 21312 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 6.656656656656657e-05, | |
| "loss": 0.0035, | |
| "step": 21360 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 6.600975975975976e-05, | |
| "loss": 0.0024, | |
| "step": 21627 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 6.545295295295295e-05, | |
| "loss": 0.0036, | |
| "step": 21894 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 6.489614614614615e-05, | |
| "loss": 0.0034, | |
| "step": 22161 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 6.433933933933934e-05, | |
| "loss": 0.002, | |
| "step": 22428 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "learning_rate": 6.378253253253254e-05, | |
| "loss": 0.0029, | |
| "step": 22695 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 6.322572572572572e-05, | |
| "loss": 0.002, | |
| "step": 22962 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "learning_rate": 6.266891891891892e-05, | |
| "loss": 0.0011, | |
| "step": 23229 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 6.211211211211212e-05, | |
| "loss": 0.0006, | |
| "step": 23496 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 6.15553053053053e-05, | |
| "loss": 0.004, | |
| "step": 23763 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.027217011898756027, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.8897, | |
| "eval_samples_per_second": 402.398, | |
| "eval_steps_per_second": 26.976, | |
| "step": 23976 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 6.0998498498498503e-05, | |
| "loss": 0.0038, | |
| "step": 24030 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 6.0441691691691695e-05, | |
| "loss": 0.0022, | |
| "step": 24297 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 5.988488488488489e-05, | |
| "loss": 0.0011, | |
| "step": 24564 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 5.932807807807807e-05, | |
| "loss": 0.0013, | |
| "step": 24831 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 5.877127127127128e-05, | |
| "loss": 0.0014, | |
| "step": 25098 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 5.821446446446447e-05, | |
| "loss": 0.0037, | |
| "step": 25365 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 5.765765765765766e-05, | |
| "loss": 0.0011, | |
| "step": 25632 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 5.7100850850850854e-05, | |
| "loss": 0.0028, | |
| "step": 25899 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 5.654404404404404e-05, | |
| "loss": 0.0012, | |
| "step": 26166 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 5.5987237237237245e-05, | |
| "loss": 0.0005, | |
| "step": 26433 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.033312857151031494, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.9102, | |
| "eval_samples_per_second": 393.315, | |
| "eval_steps_per_second": 26.367, | |
| "step": 26640 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 5.543043043043044e-05, | |
| "loss": 0.0023, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 10.12, | |
| "learning_rate": 5.487362362362363e-05, | |
| "loss": 0.0032, | |
| "step": 26967 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 5.431681681681682e-05, | |
| "loss": 0.0013, | |
| "step": 27234 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "learning_rate": 5.3760010010010006e-05, | |
| "loss": 0.0009, | |
| "step": 27501 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "learning_rate": 5.320320320320321e-05, | |
| "loss": 0.0039, | |
| "step": 27768 | |
| }, | |
| { | |
| "epoch": 10.52, | |
| "learning_rate": 5.2646396396396403e-05, | |
| "loss": 0.0008, | |
| "step": 28035 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "learning_rate": 5.2089589589589595e-05, | |
| "loss": 0.0009, | |
| "step": 28302 | |
| }, | |
| { | |
| "epoch": 10.72, | |
| "learning_rate": 5.153278278278279e-05, | |
| "loss": 0.002, | |
| "step": 28569 | |
| }, | |
| { | |
| "epoch": 10.82, | |
| "learning_rate": 5.097597597597597e-05, | |
| "loss": 0.0006, | |
| "step": 28836 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "learning_rate": 5.0419169169169165e-05, | |
| "loss": 0.0025, | |
| "step": 29103 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.03584469109773636, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.8813, | |
| "eval_samples_per_second": 406.214, | |
| "eval_steps_per_second": 27.232, | |
| "step": 29304 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 4.9862362362362363e-05, | |
| "loss": 0.0041, | |
| "step": 29370 | |
| }, | |
| { | |
| "epoch": 11.12, | |
| "learning_rate": 4.930555555555556e-05, | |
| "loss": 0.0002, | |
| "step": 29637 | |
| }, | |
| { | |
| "epoch": 11.23, | |
| "learning_rate": 4.8748748748748754e-05, | |
| "loss": 0.0001, | |
| "step": 29904 | |
| }, | |
| { | |
| "epoch": 11.33, | |
| "learning_rate": 4.819194194194194e-05, | |
| "loss": 0.0001, | |
| "step": 30171 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 4.763513513513514e-05, | |
| "loss": 0.0003, | |
| "step": 30438 | |
| }, | |
| { | |
| "epoch": 11.53, | |
| "learning_rate": 4.707832832832833e-05, | |
| "loss": 0.003, | |
| "step": 30705 | |
| }, | |
| { | |
| "epoch": 11.63, | |
| "learning_rate": 4.652152152152152e-05, | |
| "loss": 0.0002, | |
| "step": 30972 | |
| }, | |
| { | |
| "epoch": 11.73, | |
| "learning_rate": 4.596471471471472e-05, | |
| "loss": 0.0037, | |
| "step": 31239 | |
| }, | |
| { | |
| "epoch": 11.83, | |
| "learning_rate": 4.540790790790791e-05, | |
| "loss": 0.0014, | |
| "step": 31506 | |
| }, | |
| { | |
| "epoch": 11.93, | |
| "learning_rate": 4.48511011011011e-05, | |
| "loss": 0.0021, | |
| "step": 31773 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.04740298539400101, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.881, | |
| "eval_samples_per_second": 406.347, | |
| "eval_steps_per_second": 27.241, | |
| "step": 31968 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 4.42942942942943e-05, | |
| "loss": 0.0006, | |
| "step": 32040 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "learning_rate": 4.373748748748749e-05, | |
| "loss": 0.0007, | |
| "step": 32307 | |
| }, | |
| { | |
| "epoch": 12.23, | |
| "learning_rate": 4.318068068068069e-05, | |
| "loss": 0.0015, | |
| "step": 32574 | |
| }, | |
| { | |
| "epoch": 12.33, | |
| "learning_rate": 4.262387387387388e-05, | |
| "loss": 0.0014, | |
| "step": 32841 | |
| }, | |
| { | |
| "epoch": 12.43, | |
| "learning_rate": 4.2067067067067065e-05, | |
| "loss": 0.0012, | |
| "step": 33108 | |
| }, | |
| { | |
| "epoch": 12.53, | |
| "learning_rate": 4.1510260260260263e-05, | |
| "loss": 0.0019, | |
| "step": 33375 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "learning_rate": 4.0953453453453455e-05, | |
| "loss": 0.0011, | |
| "step": 33642 | |
| }, | |
| { | |
| "epoch": 12.73, | |
| "learning_rate": 4.039664664664665e-05, | |
| "loss": 0.0016, | |
| "step": 33909 | |
| }, | |
| { | |
| "epoch": 12.83, | |
| "learning_rate": 3.9839839839839846e-05, | |
| "loss": 0.0001, | |
| "step": 34176 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "learning_rate": 3.928303303303303e-05, | |
| "loss": 0.0007, | |
| "step": 34443 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.0401989221572876, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.887, | |
| "eval_samples_per_second": 403.585, | |
| "eval_steps_per_second": 27.056, | |
| "step": 34632 | |
| }, | |
| { | |
| "epoch": 13.03, | |
| "learning_rate": 3.8726226226226223e-05, | |
| "loss": 0.0006, | |
| "step": 34710 | |
| }, | |
| { | |
| "epoch": 13.13, | |
| "learning_rate": 3.816941941941942e-05, | |
| "loss": 0.0002, | |
| "step": 34977 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "learning_rate": 3.7612612612612614e-05, | |
| "loss": 0.0012, | |
| "step": 35244 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 3.705580580580581e-05, | |
| "loss": 0.0027, | |
| "step": 35511 | |
| }, | |
| { | |
| "epoch": 13.43, | |
| "learning_rate": 3.6498998998999e-05, | |
| "loss": 0.0014, | |
| "step": 35778 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "learning_rate": 3.594219219219219e-05, | |
| "loss": 0.0006, | |
| "step": 36045 | |
| }, | |
| { | |
| "epoch": 13.63, | |
| "learning_rate": 3.538538538538539e-05, | |
| "loss": 0.0023, | |
| "step": 36312 | |
| }, | |
| { | |
| "epoch": 13.73, | |
| "learning_rate": 3.482857857857858e-05, | |
| "loss": 0.0, | |
| "step": 36579 | |
| }, | |
| { | |
| "epoch": 13.83, | |
| "learning_rate": 3.427177177177177e-05, | |
| "loss": 0.0056, | |
| "step": 36846 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "learning_rate": 3.3714964964964965e-05, | |
| "loss": 0.0017, | |
| "step": 37113 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.03919493407011032, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.8793, | |
| "eval_samples_per_second": 407.126, | |
| "eval_steps_per_second": 27.293, | |
| "step": 37296 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 3.315815815815816e-05, | |
| "loss": 0.0002, | |
| "step": 37380 | |
| }, | |
| { | |
| "epoch": 14.13, | |
| "learning_rate": 3.260135135135135e-05, | |
| "loss": 0.0012, | |
| "step": 37647 | |
| }, | |
| { | |
| "epoch": 14.23, | |
| "learning_rate": 3.204454454454455e-05, | |
| "loss": 0.0009, | |
| "step": 37914 | |
| }, | |
| { | |
| "epoch": 14.33, | |
| "learning_rate": 3.148773773773774e-05, | |
| "loss": 0.0006, | |
| "step": 38181 | |
| }, | |
| { | |
| "epoch": 14.43, | |
| "learning_rate": 3.093093093093093e-05, | |
| "loss": 0.0006, | |
| "step": 38448 | |
| }, | |
| { | |
| "epoch": 14.53, | |
| "learning_rate": 3.0374124124124127e-05, | |
| "loss": 0.0015, | |
| "step": 38715 | |
| }, | |
| { | |
| "epoch": 14.63, | |
| "learning_rate": 2.9817317317317315e-05, | |
| "loss": 0.0014, | |
| "step": 38982 | |
| }, | |
| { | |
| "epoch": 14.73, | |
| "learning_rate": 2.9260510510510514e-05, | |
| "loss": 0.0009, | |
| "step": 39249 | |
| }, | |
| { | |
| "epoch": 14.83, | |
| "learning_rate": 2.8703703703703706e-05, | |
| "loss": 0.0016, | |
| "step": 39516 | |
| }, | |
| { | |
| "epoch": 14.93, | |
| "learning_rate": 2.8146896896896895e-05, | |
| "loss": 0.0007, | |
| "step": 39783 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.03942238539457321, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.8858, | |
| "eval_samples_per_second": 404.155, | |
| "eval_steps_per_second": 27.094, | |
| "step": 39960 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 2.7590090090090094e-05, | |
| "loss": 0.0003, | |
| "step": 40050 | |
| }, | |
| { | |
| "epoch": 15.13, | |
| "learning_rate": 2.7033283283283286e-05, | |
| "loss": 0.0002, | |
| "step": 40317 | |
| }, | |
| { | |
| "epoch": 15.23, | |
| "learning_rate": 2.6476476476476474e-05, | |
| "loss": 0.0002, | |
| "step": 40584 | |
| }, | |
| { | |
| "epoch": 15.33, | |
| "learning_rate": 2.5919669669669673e-05, | |
| "loss": 0.0, | |
| "step": 40851 | |
| }, | |
| { | |
| "epoch": 15.43, | |
| "learning_rate": 2.536286286286286e-05, | |
| "loss": 0.0017, | |
| "step": 41118 | |
| }, | |
| { | |
| "epoch": 15.53, | |
| "learning_rate": 2.4806056056056057e-05, | |
| "loss": 0.0002, | |
| "step": 41385 | |
| }, | |
| { | |
| "epoch": 15.64, | |
| "learning_rate": 2.4249249249249252e-05, | |
| "loss": 0.0007, | |
| "step": 41652 | |
| }, | |
| { | |
| "epoch": 15.74, | |
| "learning_rate": 2.3692442442442444e-05, | |
| "loss": 0.0001, | |
| "step": 41919 | |
| }, | |
| { | |
| "epoch": 15.84, | |
| "learning_rate": 2.3135635635635636e-05, | |
| "loss": 0.0011, | |
| "step": 42186 | |
| }, | |
| { | |
| "epoch": 15.94, | |
| "learning_rate": 2.2578828828828828e-05, | |
| "loss": 0.0013, | |
| "step": 42453 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.04424785450100899, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.8837, | |
| "eval_samples_per_second": 405.133, | |
| "eval_steps_per_second": 27.16, | |
| "step": 42624 | |
| }, | |
| { | |
| "epoch": 16.04, | |
| "learning_rate": 2.2022022022022024e-05, | |
| "loss": 0.0006, | |
| "step": 42720 | |
| }, | |
| { | |
| "epoch": 16.14, | |
| "learning_rate": 2.146521521521522e-05, | |
| "loss": 0.0013, | |
| "step": 42987 | |
| }, | |
| { | |
| "epoch": 16.24, | |
| "learning_rate": 2.0908408408408408e-05, | |
| "loss": 0.0005, | |
| "step": 43254 | |
| }, | |
| { | |
| "epoch": 16.34, | |
| "learning_rate": 2.0351601601601603e-05, | |
| "loss": 0.0008, | |
| "step": 43521 | |
| }, | |
| { | |
| "epoch": 16.44, | |
| "learning_rate": 1.9794794794794795e-05, | |
| "loss": 0.0003, | |
| "step": 43788 | |
| }, | |
| { | |
| "epoch": 16.54, | |
| "learning_rate": 1.9237987987987987e-05, | |
| "loss": 0.0001, | |
| "step": 44055 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 1.8681181181181182e-05, | |
| "loss": 0.0005, | |
| "step": 44322 | |
| }, | |
| { | |
| "epoch": 16.74, | |
| "learning_rate": 1.8124374374374374e-05, | |
| "loss": 0.0026, | |
| "step": 44589 | |
| }, | |
| { | |
| "epoch": 16.84, | |
| "learning_rate": 1.756756756756757e-05, | |
| "loss": 0.0008, | |
| "step": 44856 | |
| }, | |
| { | |
| "epoch": 16.94, | |
| "learning_rate": 1.701076076076076e-05, | |
| "loss": 0.0002, | |
| "step": 45123 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.04427039995789528, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.8885, | |
| "eval_samples_per_second": 402.91, | |
| "eval_steps_per_second": 27.011, | |
| "step": 45288 | |
| }, | |
| { | |
| "epoch": 17.04, | |
| "learning_rate": 1.6453953953953954e-05, | |
| "loss": 0.0001, | |
| "step": 45390 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 1.589714714714715e-05, | |
| "loss": 0.0004, | |
| "step": 45657 | |
| }, | |
| { | |
| "epoch": 17.24, | |
| "learning_rate": 1.534034034034034e-05, | |
| "loss": 0.0001, | |
| "step": 45924 | |
| }, | |
| { | |
| "epoch": 17.34, | |
| "learning_rate": 1.4783533533533533e-05, | |
| "loss": 0.0011, | |
| "step": 46191 | |
| }, | |
| { | |
| "epoch": 17.44, | |
| "learning_rate": 1.4226726726726727e-05, | |
| "loss": 0.001, | |
| "step": 46458 | |
| }, | |
| { | |
| "epoch": 17.54, | |
| "learning_rate": 1.3669919919919922e-05, | |
| "loss": 0.0003, | |
| "step": 46725 | |
| }, | |
| { | |
| "epoch": 17.64, | |
| "learning_rate": 1.3113113113113112e-05, | |
| "loss": 0.0007, | |
| "step": 46992 | |
| }, | |
| { | |
| "epoch": 17.74, | |
| "learning_rate": 1.2556306306306306e-05, | |
| "loss": 0.0002, | |
| "step": 47259 | |
| }, | |
| { | |
| "epoch": 17.84, | |
| "learning_rate": 1.19994994994995e-05, | |
| "loss": 0.0024, | |
| "step": 47526 | |
| }, | |
| { | |
| "epoch": 17.94, | |
| "learning_rate": 1.1442692692692693e-05, | |
| "loss": 0.0013, | |
| "step": 47793 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.038870543241500854, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.8826, | |
| "eval_samples_per_second": 405.621, | |
| "eval_steps_per_second": 27.192, | |
| "step": 47952 | |
| }, | |
| { | |
| "epoch": 18.04, | |
| "learning_rate": 1.0885885885885887e-05, | |
| "loss": 0.0005, | |
| "step": 48060 | |
| }, | |
| { | |
| "epoch": 18.14, | |
| "learning_rate": 1.0329079079079079e-05, | |
| "loss": 0.0, | |
| "step": 48327 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 9.772272272272273e-06, | |
| "loss": 0.0005, | |
| "step": 48594 | |
| }, | |
| { | |
| "epoch": 18.34, | |
| "learning_rate": 9.215465465465466e-06, | |
| "loss": 0.0017, | |
| "step": 48861 | |
| }, | |
| { | |
| "epoch": 18.44, | |
| "learning_rate": 8.65865865865866e-06, | |
| "loss": 0.0003, | |
| "step": 49128 | |
| }, | |
| { | |
| "epoch": 18.54, | |
| "learning_rate": 8.101851851851852e-06, | |
| "loss": 0.0012, | |
| "step": 49395 | |
| }, | |
| { | |
| "epoch": 18.64, | |
| "learning_rate": 7.545045045045046e-06, | |
| "loss": 0.0, | |
| "step": 49662 | |
| }, | |
| { | |
| "epoch": 18.74, | |
| "learning_rate": 6.9882382382382385e-06, | |
| "loss": 0.0011, | |
| "step": 49929 | |
| }, | |
| { | |
| "epoch": 18.84, | |
| "learning_rate": 6.431431431431431e-06, | |
| "loss": 0.0013, | |
| "step": 50196 | |
| }, | |
| { | |
| "epoch": 18.94, | |
| "learning_rate": 5.874624624624625e-06, | |
| "loss": 0.0001, | |
| "step": 50463 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.04122824966907501, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.8851, | |
| "eval_samples_per_second": 404.458, | |
| "eval_steps_per_second": 27.114, | |
| "step": 50616 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 5.317817817817819e-06, | |
| "loss": 0.0012, | |
| "step": 50730 | |
| }, | |
| { | |
| "epoch": 19.14, | |
| "learning_rate": 4.7610110110110115e-06, | |
| "loss": 0.0001, | |
| "step": 50997 | |
| }, | |
| { | |
| "epoch": 19.24, | |
| "learning_rate": 4.204204204204204e-06, | |
| "loss": 0.0002, | |
| "step": 51264 | |
| }, | |
| { | |
| "epoch": 19.34, | |
| "learning_rate": 3.647397397397397e-06, | |
| "loss": 0.0, | |
| "step": 51531 | |
| }, | |
| { | |
| "epoch": 19.44, | |
| "learning_rate": 3.090590590590591e-06, | |
| "loss": 0.0003, | |
| "step": 51798 | |
| }, | |
| { | |
| "epoch": 19.54, | |
| "learning_rate": 2.533783783783784e-06, | |
| "loss": 0.0021, | |
| "step": 52065 | |
| }, | |
| { | |
| "epoch": 19.64, | |
| "learning_rate": 1.976976976976977e-06, | |
| "loss": 0.0, | |
| "step": 52332 | |
| }, | |
| { | |
| "epoch": 19.74, | |
| "learning_rate": 1.4201701701701704e-06, | |
| "loss": 0.0001, | |
| "step": 52599 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 8.633633633633634e-07, | |
| "loss": 0.0009, | |
| "step": 52866 | |
| }, | |
| { | |
| "epoch": 19.94, | |
| "learning_rate": 3.0655655655655656e-07, | |
| "loss": 0.0001, | |
| "step": 53133 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.0392613410949707, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.8819, | |
| "eval_samples_per_second": 405.923, | |
| "eval_steps_per_second": 27.213, | |
| "step": 53280 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 53280, | |
| "total_flos": 3.004276018040832e+16, | |
| "train_loss": 0.5359516274340651, | |
| "train_runtime": 5327.8303, | |
| "train_samples_per_second": 149.956, | |
| "train_steps_per_second": 10.0 | |
| } | |
| ], | |
| "logging_steps": 267, | |
| "max_steps": 53280, | |
| "num_train_epochs": 20, | |
| "save_steps": 533, | |
| "total_flos": 3.004276018040832e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |