| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 274520, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.6427218417601638e-09, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5.001457088736705e-06, | |
| "loss": 0.0052, | |
| "step": 1373 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.000291417747341e-05, | |
| "loss": 0.0041, | |
| "step": 2746 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.5004371266210113e-05, | |
| "loss": 0.0025, | |
| "step": 4119 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.000582835494682e-05, | |
| "loss": 0.002, | |
| "step": 5492 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.500728544368352e-05, | |
| "loss": 0.0018, | |
| "step": 6865 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.0008742532420226e-05, | |
| "loss": 0.0014, | |
| "step": 8238 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.501019962115693e-05, | |
| "loss": 0.0015, | |
| "step": 9611 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.001165670989364e-05, | |
| "loss": 0.0012, | |
| "step": 10984 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.501311379863034e-05, | |
| "loss": 0.001, | |
| "step": 12357 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.011379459872841835, | |
| "eval_max_distance": 5, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 13.5607, | |
| "eval_samples_per_second": 19.763, | |
| "eval_steps_per_second": 1.327, | |
| "step": 13726 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.001457088736704e-05, | |
| "loss": 0.0009, | |
| "step": 13730 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 5.501602797610374e-05, | |
| "loss": 0.0008, | |
| "step": 15103 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 6.001748506484045e-05, | |
| "loss": 0.0009, | |
| "step": 16476 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 6.501894215357715e-05, | |
| "loss": 0.0008, | |
| "step": 17849 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 7.002039924231386e-05, | |
| "loss": 0.0007, | |
| "step": 19222 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.502185633105057e-05, | |
| "loss": 0.0008, | |
| "step": 20595 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 8.002331341978728e-05, | |
| "loss": 0.0008, | |
| "step": 21968 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.502477050852397e-05, | |
| "loss": 0.0009, | |
| "step": 23341 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 9.002622759726068e-05, | |
| "loss": 0.0008, | |
| "step": 24714 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 9.502768468599739e-05, | |
| "loss": 0.0009, | |
| "step": 26087 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.01430370844900608, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 14.233, | |
| "eval_samples_per_second": 18.829, | |
| "eval_steps_per_second": 1.265, | |
| "step": 27452 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.999676202502955e-05, | |
| "loss": 0.0008, | |
| "step": 27460 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.944104457072547e-05, | |
| "loss": 0.0008, | |
| "step": 28833 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 9.88853271164214e-05, | |
| "loss": 0.0008, | |
| "step": 30206 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 9.832960966211731e-05, | |
| "loss": 0.0008, | |
| "step": 31579 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.777389220781323e-05, | |
| "loss": 0.0009, | |
| "step": 32952 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.721817475350917e-05, | |
| "loss": 0.0008, | |
| "step": 34325 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 9.666245729920507e-05, | |
| "loss": 0.0009, | |
| "step": 35698 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 9.6106739844901e-05, | |
| "loss": 0.0008, | |
| "step": 37071 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 9.555102239059693e-05, | |
| "loss": 0.0008, | |
| "step": 38444 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 9.499530493629284e-05, | |
| "loss": 0.0008, | |
| "step": 39817 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.014528523199260235, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 12.815, | |
| "eval_samples_per_second": 20.913, | |
| "eval_steps_per_second": 1.405, | |
| "step": 41178 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.443958748198876e-05, | |
| "loss": 0.0009, | |
| "step": 41190 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 9.38838700276847e-05, | |
| "loss": 0.0008, | |
| "step": 42563 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 9.332815257338062e-05, | |
| "loss": 0.0008, | |
| "step": 43936 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 9.277243511907654e-05, | |
| "loss": 0.0008, | |
| "step": 45309 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 9.221671766477246e-05, | |
| "loss": 0.0008, | |
| "step": 46682 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 9.166100021046838e-05, | |
| "loss": 0.0008, | |
| "step": 48055 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 9.11052827561643e-05, | |
| "loss": 0.0008, | |
| "step": 49428 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 9.054956530186022e-05, | |
| "loss": 0.0008, | |
| "step": 50801 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 8.999384784755615e-05, | |
| "loss": 0.0008, | |
| "step": 52174 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 8.943813039325206e-05, | |
| "loss": 0.0009, | |
| "step": 53547 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.009767626412212849, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 13.1075, | |
| "eval_samples_per_second": 20.446, | |
| "eval_steps_per_second": 1.373, | |
| "step": 54904 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8.888241293894799e-05, | |
| "loss": 0.0009, | |
| "step": 54920 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 8.832669548464391e-05, | |
| "loss": 0.0008, | |
| "step": 56293 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 8.777097803033983e-05, | |
| "loss": 0.0008, | |
| "step": 57666 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 8.721526057603575e-05, | |
| "loss": 0.0007, | |
| "step": 59039 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 8.665954312173167e-05, | |
| "loss": 0.0008, | |
| "step": 60412 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 8.61038256674276e-05, | |
| "loss": 0.0008, | |
| "step": 61785 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 8.554810821312351e-05, | |
| "loss": 0.0008, | |
| "step": 63158 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 8.499239075881944e-05, | |
| "loss": 0.0008, | |
| "step": 64531 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 8.443667330451536e-05, | |
| "loss": 0.0008, | |
| "step": 65904 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 8.388095585021128e-05, | |
| "loss": 0.0007, | |
| "step": 67277 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.012975725345313549, | |
| "eval_max_distance": 2, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 13.0896, | |
| "eval_samples_per_second": 20.474, | |
| "eval_steps_per_second": 1.375, | |
| "step": 68630 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 8.33252383959072e-05, | |
| "loss": 0.0008, | |
| "step": 68650 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 8.276952094160313e-05, | |
| "loss": 0.0008, | |
| "step": 70023 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 8.221380348729904e-05, | |
| "loss": 0.0007, | |
| "step": 71396 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 8.165808603299497e-05, | |
| "loss": 0.0008, | |
| "step": 72769 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 8.11023685786909e-05, | |
| "loss": 0.0008, | |
| "step": 74142 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 8.054665112438681e-05, | |
| "loss": 0.0007, | |
| "step": 75515 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 7.999093367008273e-05, | |
| "loss": 0.0008, | |
| "step": 76888 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 7.943521621577865e-05, | |
| "loss": 0.0007, | |
| "step": 78261 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 7.887949876147457e-05, | |
| "loss": 0.0008, | |
| "step": 79634 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 7.832378130717049e-05, | |
| "loss": 0.0008, | |
| "step": 81007 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.015315458178520203, | |
| "eval_max_distance": 2, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 13.1351, | |
| "eval_samples_per_second": 20.403, | |
| "eval_steps_per_second": 1.37, | |
| "step": 82356 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 7.776806385286643e-05, | |
| "loss": 0.0008, | |
| "step": 82380 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 7.721234639856235e-05, | |
| "loss": 0.0007, | |
| "step": 83753 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 7.665662894425827e-05, | |
| "loss": 0.0007, | |
| "step": 85126 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 7.610091148995419e-05, | |
| "loss": 0.0006, | |
| "step": 86499 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 7.554519403565012e-05, | |
| "loss": 0.0007, | |
| "step": 87872 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 7.498947658134603e-05, | |
| "loss": 0.0007, | |
| "step": 89245 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 7.443375912704195e-05, | |
| "loss": 0.0007, | |
| "step": 90618 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 7.387804167273788e-05, | |
| "loss": 0.0007, | |
| "step": 91991 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 7.332232421843378e-05, | |
| "loss": 0.0007, | |
| "step": 93364 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 7.276660676412972e-05, | |
| "loss": 0.0007, | |
| "step": 94737 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.01277723629027605, | |
| "eval_max_distance": 2, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 13.169, | |
| "eval_samples_per_second": 20.351, | |
| "eval_steps_per_second": 1.367, | |
| "step": 96082 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 7.221088930982564e-05, | |
| "loss": 0.0007, | |
| "step": 96110 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 7.165517185552156e-05, | |
| "loss": 0.0007, | |
| "step": 97483 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 7.109945440121748e-05, | |
| "loss": 0.0006, | |
| "step": 98856 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 7.054373694691341e-05, | |
| "loss": 0.0006, | |
| "step": 100229 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 6.998801949260933e-05, | |
| "loss": 0.0007, | |
| "step": 101602 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 6.943230203830525e-05, | |
| "loss": 0.0006, | |
| "step": 102975 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 6.887658458400117e-05, | |
| "loss": 0.0006, | |
| "step": 104348 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 6.832086712969709e-05, | |
| "loss": 0.0007, | |
| "step": 105721 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 6.776514967539301e-05, | |
| "loss": 0.0006, | |
| "step": 107094 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 6.720943222108893e-05, | |
| "loss": 0.0006, | |
| "step": 108467 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.013012989424169064, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 12.4679, | |
| "eval_samples_per_second": 21.495, | |
| "eval_steps_per_second": 1.444, | |
| "step": 109808 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 6.665371476678486e-05, | |
| "loss": 0.0007, | |
| "step": 109840 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 6.609799731248077e-05, | |
| "loss": 0.0007, | |
| "step": 111213 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 6.55422798581767e-05, | |
| "loss": 0.0005, | |
| "step": 112586 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 6.498656240387262e-05, | |
| "loss": 0.0007, | |
| "step": 113959 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 6.443084494956854e-05, | |
| "loss": 0.0006, | |
| "step": 115332 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 6.387512749526446e-05, | |
| "loss": 0.0006, | |
| "step": 116705 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 6.33194100409604e-05, | |
| "loss": 0.0007, | |
| "step": 118078 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 6.276369258665632e-05, | |
| "loss": 0.0006, | |
| "step": 119451 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 6.220797513235222e-05, | |
| "loss": 0.0006, | |
| "step": 120824 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 6.165225767804815e-05, | |
| "loss": 0.0006, | |
| "step": 122197 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.015804793685674667, | |
| "eval_max_distance": 5, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 12.8641, | |
| "eval_samples_per_second": 20.833, | |
| "eval_steps_per_second": 1.399, | |
| "step": 123534 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 6.109654022374407e-05, | |
| "loss": 0.0005, | |
| "step": 123570 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 6.0540822769439994e-05, | |
| "loss": 0.0005, | |
| "step": 124943 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 5.9985105315135914e-05, | |
| "loss": 0.0006, | |
| "step": 126316 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 5.942938786083184e-05, | |
| "loss": 0.0005, | |
| "step": 127689 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 5.887367040652776e-05, | |
| "loss": 0.0006, | |
| "step": 129062 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 5.831795295222369e-05, | |
| "loss": 0.0006, | |
| "step": 130435 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 5.77622354979196e-05, | |
| "loss": 0.0006, | |
| "step": 131808 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 5.720651804361552e-05, | |
| "loss": 0.0007, | |
| "step": 133181 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 5.6650800589311447e-05, | |
| "loss": 0.0006, | |
| "step": 134554 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 5.6095083135007366e-05, | |
| "loss": 0.0006, | |
| "step": 135927 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.015074091032147408, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 12.5962, | |
| "eval_samples_per_second": 21.276, | |
| "eval_steps_per_second": 1.429, | |
| "step": 137260 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5.553936568070329e-05, | |
| "loss": 0.0006, | |
| "step": 137300 | |
| }, | |
| { | |
| "epoch": 10.1, | |
| "learning_rate": 5.4983648226399206e-05, | |
| "loss": 0.0006, | |
| "step": 138673 | |
| }, | |
| { | |
| "epoch": 10.2, | |
| "learning_rate": 5.442793077209514e-05, | |
| "loss": 0.0006, | |
| "step": 140046 | |
| }, | |
| { | |
| "epoch": 10.3, | |
| "learning_rate": 5.387221331779105e-05, | |
| "loss": 0.0006, | |
| "step": 141419 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 5.331649586348698e-05, | |
| "loss": 0.0008, | |
| "step": 142792 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "learning_rate": 5.27607784091829e-05, | |
| "loss": 0.0005, | |
| "step": 144165 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "learning_rate": 5.2205060954878825e-05, | |
| "loss": 0.0006, | |
| "step": 145538 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "learning_rate": 5.1649343500574745e-05, | |
| "loss": 0.0006, | |
| "step": 146911 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "learning_rate": 5.109362604627066e-05, | |
| "loss": 0.0006, | |
| "step": 148284 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 5.0537908591966585e-05, | |
| "loss": 0.0005, | |
| "step": 149657 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.016692565754055977, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 12.5906, | |
| "eval_samples_per_second": 21.286, | |
| "eval_steps_per_second": 1.43, | |
| "step": 150986 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.998219113766251e-05, | |
| "loss": 0.0006, | |
| "step": 151030 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "learning_rate": 4.942647368335843e-05, | |
| "loss": 0.0005, | |
| "step": 152403 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 4.887075622905435e-05, | |
| "loss": 0.0005, | |
| "step": 153776 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "learning_rate": 4.831503877475027e-05, | |
| "loss": 0.0005, | |
| "step": 155149 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 4.775932132044619e-05, | |
| "loss": 0.0005, | |
| "step": 156522 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "learning_rate": 4.720360386614212e-05, | |
| "loss": 0.0005, | |
| "step": 157895 | |
| }, | |
| { | |
| "epoch": 11.6, | |
| "learning_rate": 4.664788641183804e-05, | |
| "loss": 0.0005, | |
| "step": 159268 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "learning_rate": 4.6092168957533957e-05, | |
| "loss": 0.0005, | |
| "step": 160641 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 4.553645150322988e-05, | |
| "loss": 0.0005, | |
| "step": 162014 | |
| }, | |
| { | |
| "epoch": 11.9, | |
| "learning_rate": 4.49807340489258e-05, | |
| "loss": 0.0005, | |
| "step": 163387 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.014475121162831783, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 12.6623, | |
| "eval_samples_per_second": 21.165, | |
| "eval_steps_per_second": 1.422, | |
| "step": 164712 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.442501659462173e-05, | |
| "loss": 0.0005, | |
| "step": 164760 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 4.386929914031765e-05, | |
| "loss": 0.0005, | |
| "step": 166133 | |
| }, | |
| { | |
| "epoch": 12.2, | |
| "learning_rate": 4.331358168601357e-05, | |
| "loss": 0.0005, | |
| "step": 167506 | |
| }, | |
| { | |
| "epoch": 12.3, | |
| "learning_rate": 4.2757864231709496e-05, | |
| "loss": 0.0005, | |
| "step": 168879 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "learning_rate": 4.220214677740541e-05, | |
| "loss": 0.0005, | |
| "step": 170252 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 4.1646429323101335e-05, | |
| "loss": 0.0004, | |
| "step": 171625 | |
| }, | |
| { | |
| "epoch": 12.6, | |
| "learning_rate": 4.1090711868797255e-05, | |
| "loss": 0.0006, | |
| "step": 172998 | |
| }, | |
| { | |
| "epoch": 12.7, | |
| "learning_rate": 4.0534994414493175e-05, | |
| "loss": 0.0006, | |
| "step": 174371 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 3.99792769601891e-05, | |
| "loss": 0.0006, | |
| "step": 175744 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 3.942355950588502e-05, | |
| "loss": 0.0005, | |
| "step": 177117 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.016049271449446678, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 12.7374, | |
| "eval_samples_per_second": 21.04, | |
| "eval_steps_per_second": 1.413, | |
| "step": 178438 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 3.886784205158094e-05, | |
| "loss": 0.0005, | |
| "step": 178490 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "learning_rate": 3.831212459727687e-05, | |
| "loss": 0.0005, | |
| "step": 179863 | |
| }, | |
| { | |
| "epoch": 13.2, | |
| "learning_rate": 3.775640714297279e-05, | |
| "loss": 0.0005, | |
| "step": 181236 | |
| }, | |
| { | |
| "epoch": 13.3, | |
| "learning_rate": 3.720068968866871e-05, | |
| "loss": 0.0005, | |
| "step": 182609 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "learning_rate": 3.6644972234364634e-05, | |
| "loss": 0.0005, | |
| "step": 183982 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "learning_rate": 3.608925478006055e-05, | |
| "loss": 0.0004, | |
| "step": 185355 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 3.5533537325756473e-05, | |
| "loss": 0.0005, | |
| "step": 186728 | |
| }, | |
| { | |
| "epoch": 13.7, | |
| "learning_rate": 3.497781987145239e-05, | |
| "loss": 0.0005, | |
| "step": 188101 | |
| }, | |
| { | |
| "epoch": 13.8, | |
| "learning_rate": 3.442210241714832e-05, | |
| "loss": 0.0005, | |
| "step": 189474 | |
| }, | |
| { | |
| "epoch": 13.9, | |
| "learning_rate": 3.386638496284424e-05, | |
| "loss": 0.0005, | |
| "step": 190847 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.015727248042821884, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 12.6356, | |
| "eval_samples_per_second": 21.21, | |
| "eval_steps_per_second": 1.425, | |
| "step": 192164 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 3.331066750854016e-05, | |
| "loss": 0.0004, | |
| "step": 192220 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "learning_rate": 3.2754950054236086e-05, | |
| "loss": 0.0005, | |
| "step": 193593 | |
| }, | |
| { | |
| "epoch": 14.2, | |
| "learning_rate": 3.2199232599932006e-05, | |
| "loss": 0.0005, | |
| "step": 194966 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "learning_rate": 3.1643515145627926e-05, | |
| "loss": 0.0004, | |
| "step": 196339 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 3.108779769132385e-05, | |
| "loss": 0.0004, | |
| "step": 197712 | |
| }, | |
| { | |
| "epoch": 14.5, | |
| "learning_rate": 3.0532080237019765e-05, | |
| "loss": 0.0005, | |
| "step": 199085 | |
| }, | |
| { | |
| "epoch": 14.6, | |
| "learning_rate": 2.997636278271569e-05, | |
| "loss": 0.0005, | |
| "step": 200458 | |
| }, | |
| { | |
| "epoch": 14.7, | |
| "learning_rate": 2.942064532841161e-05, | |
| "loss": 0.0004, | |
| "step": 201831 | |
| }, | |
| { | |
| "epoch": 14.8, | |
| "learning_rate": 2.8864927874107535e-05, | |
| "loss": 0.0004, | |
| "step": 203204 | |
| }, | |
| { | |
| "epoch": 14.9, | |
| "learning_rate": 2.8309210419803455e-05, | |
| "loss": 0.0004, | |
| "step": 204577 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.015685711055994034, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 12.7509, | |
| "eval_samples_per_second": 21.018, | |
| "eval_steps_per_second": 1.412, | |
| "step": 205890 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 2.7753492965499378e-05, | |
| "loss": 0.0004, | |
| "step": 205950 | |
| }, | |
| { | |
| "epoch": 15.1, | |
| "learning_rate": 2.71977755111953e-05, | |
| "loss": 0.0004, | |
| "step": 207323 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "learning_rate": 2.6642058056891224e-05, | |
| "loss": 0.0004, | |
| "step": 208696 | |
| }, | |
| { | |
| "epoch": 15.3, | |
| "learning_rate": 2.6086340602587144e-05, | |
| "loss": 0.0004, | |
| "step": 210069 | |
| }, | |
| { | |
| "epoch": 15.4, | |
| "learning_rate": 2.5530623148283067e-05, | |
| "loss": 0.0004, | |
| "step": 211442 | |
| }, | |
| { | |
| "epoch": 15.5, | |
| "learning_rate": 2.4974905693978987e-05, | |
| "loss": 0.0005, | |
| "step": 212815 | |
| }, | |
| { | |
| "epoch": 15.6, | |
| "learning_rate": 2.441918823967491e-05, | |
| "loss": 0.0004, | |
| "step": 214188 | |
| }, | |
| { | |
| "epoch": 15.7, | |
| "learning_rate": 2.386347078537083e-05, | |
| "loss": 0.0004, | |
| "step": 215561 | |
| }, | |
| { | |
| "epoch": 15.8, | |
| "learning_rate": 2.330775333106675e-05, | |
| "loss": 0.0005, | |
| "step": 216934 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "learning_rate": 2.2752035876762673e-05, | |
| "loss": 0.0004, | |
| "step": 218307 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.017339130863547325, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 12.871, | |
| "eval_samples_per_second": 20.822, | |
| "eval_steps_per_second": 1.398, | |
| "step": 219616 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.2196318422458596e-05, | |
| "loss": 0.0004, | |
| "step": 219680 | |
| }, | |
| { | |
| "epoch": 16.1, | |
| "learning_rate": 2.1640600968154516e-05, | |
| "loss": 0.0004, | |
| "step": 221053 | |
| }, | |
| { | |
| "epoch": 16.2, | |
| "learning_rate": 2.108488351385044e-05, | |
| "loss": 0.0004, | |
| "step": 222426 | |
| }, | |
| { | |
| "epoch": 16.3, | |
| "learning_rate": 2.0529166059546362e-05, | |
| "loss": 0.0004, | |
| "step": 223799 | |
| }, | |
| { | |
| "epoch": 16.4, | |
| "learning_rate": 1.9973448605242282e-05, | |
| "loss": 0.0004, | |
| "step": 225172 | |
| }, | |
| { | |
| "epoch": 16.5, | |
| "learning_rate": 1.9417731150938205e-05, | |
| "loss": 0.0004, | |
| "step": 226545 | |
| }, | |
| { | |
| "epoch": 16.6, | |
| "learning_rate": 1.8862013696634125e-05, | |
| "loss": 0.0004, | |
| "step": 227918 | |
| }, | |
| { | |
| "epoch": 16.7, | |
| "learning_rate": 1.8306296242330048e-05, | |
| "loss": 0.0004, | |
| "step": 229291 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 1.775057878802597e-05, | |
| "loss": 0.0004, | |
| "step": 230664 | |
| }, | |
| { | |
| "epoch": 16.9, | |
| "learning_rate": 1.719486133372189e-05, | |
| "loss": 0.0004, | |
| "step": 232037 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.015850957483053207, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 12.7459, | |
| "eval_samples_per_second": 21.026, | |
| "eval_steps_per_second": 1.412, | |
| "step": 233342 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 1.663914387941781e-05, | |
| "loss": 0.0004, | |
| "step": 233410 | |
| }, | |
| { | |
| "epoch": 17.1, | |
| "learning_rate": 1.6083426425113734e-05, | |
| "loss": 0.0004, | |
| "step": 234783 | |
| }, | |
| { | |
| "epoch": 17.21, | |
| "learning_rate": 1.5527708970809657e-05, | |
| "loss": 0.0004, | |
| "step": 236156 | |
| }, | |
| { | |
| "epoch": 17.31, | |
| "learning_rate": 1.4971991516505579e-05, | |
| "loss": 0.0004, | |
| "step": 237529 | |
| }, | |
| { | |
| "epoch": 17.41, | |
| "learning_rate": 1.4416274062201499e-05, | |
| "loss": 0.0005, | |
| "step": 238902 | |
| }, | |
| { | |
| "epoch": 17.51, | |
| "learning_rate": 1.386055660789742e-05, | |
| "loss": 0.0004, | |
| "step": 240275 | |
| }, | |
| { | |
| "epoch": 17.61, | |
| "learning_rate": 1.3304839153593343e-05, | |
| "loss": 0.0004, | |
| "step": 241648 | |
| }, | |
| { | |
| "epoch": 17.71, | |
| "learning_rate": 1.2749121699289265e-05, | |
| "loss": 0.0004, | |
| "step": 243021 | |
| }, | |
| { | |
| "epoch": 17.81, | |
| "learning_rate": 1.2193404244985186e-05, | |
| "loss": 0.0004, | |
| "step": 244394 | |
| }, | |
| { | |
| "epoch": 17.91, | |
| "learning_rate": 1.1637686790681108e-05, | |
| "loss": 0.0004, | |
| "step": 245767 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.016846980899572372, | |
| "eval_max_distance": 2, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 14.3322, | |
| "eval_samples_per_second": 18.699, | |
| "eval_steps_per_second": 1.256, | |
| "step": 247068 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 1.1081969336377031e-05, | |
| "loss": 0.0004, | |
| "step": 247140 | |
| }, | |
| { | |
| "epoch": 18.11, | |
| "learning_rate": 1.0526251882072952e-05, | |
| "loss": 0.0004, | |
| "step": 248513 | |
| }, | |
| { | |
| "epoch": 18.21, | |
| "learning_rate": 9.970534427768874e-06, | |
| "loss": 0.0004, | |
| "step": 249886 | |
| }, | |
| { | |
| "epoch": 18.31, | |
| "learning_rate": 9.414816973464795e-06, | |
| "loss": 0.0003, | |
| "step": 251259 | |
| }, | |
| { | |
| "epoch": 18.41, | |
| "learning_rate": 8.859099519160717e-06, | |
| "loss": 0.0004, | |
| "step": 252632 | |
| }, | |
| { | |
| "epoch": 18.51, | |
| "learning_rate": 8.30338206485664e-06, | |
| "loss": 0.0004, | |
| "step": 254005 | |
| }, | |
| { | |
| "epoch": 18.61, | |
| "learning_rate": 7.74766461055256e-06, | |
| "loss": 0.0004, | |
| "step": 255378 | |
| }, | |
| { | |
| "epoch": 18.71, | |
| "learning_rate": 7.191947156248482e-06, | |
| "loss": 0.0004, | |
| "step": 256751 | |
| }, | |
| { | |
| "epoch": 18.81, | |
| "learning_rate": 6.636229701944405e-06, | |
| "loss": 0.0003, | |
| "step": 258124 | |
| }, | |
| { | |
| "epoch": 18.91, | |
| "learning_rate": 6.080512247640326e-06, | |
| "loss": 0.0004, | |
| "step": 259497 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.01681215688586235, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 12.5068, | |
| "eval_samples_per_second": 21.428, | |
| "eval_steps_per_second": 1.439, | |
| "step": 260794 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 5.524794793336248e-06, | |
| "loss": 0.0004, | |
| "step": 260870 | |
| }, | |
| { | |
| "epoch": 19.11, | |
| "learning_rate": 4.969077339032169e-06, | |
| "loss": 0.0004, | |
| "step": 262243 | |
| }, | |
| { | |
| "epoch": 19.21, | |
| "learning_rate": 4.4133598847280914e-06, | |
| "loss": 0.0004, | |
| "step": 263616 | |
| }, | |
| { | |
| "epoch": 19.31, | |
| "learning_rate": 3.857642430424013e-06, | |
| "loss": 0.0004, | |
| "step": 264989 | |
| }, | |
| { | |
| "epoch": 19.41, | |
| "learning_rate": 3.301924976119935e-06, | |
| "loss": 0.0004, | |
| "step": 266362 | |
| }, | |
| { | |
| "epoch": 19.51, | |
| "learning_rate": 2.7462075218158563e-06, | |
| "loss": 0.0004, | |
| "step": 267735 | |
| }, | |
| { | |
| "epoch": 19.61, | |
| "learning_rate": 2.1904900675117783e-06, | |
| "loss": 0.0003, | |
| "step": 269108 | |
| }, | |
| { | |
| "epoch": 19.71, | |
| "learning_rate": 1.6347726132077e-06, | |
| "loss": 0.0004, | |
| "step": 270481 | |
| }, | |
| { | |
| "epoch": 19.81, | |
| "learning_rate": 1.0790551589036217e-06, | |
| "loss": 0.0003, | |
| "step": 271854 | |
| }, | |
| { | |
| "epoch": 19.91, | |
| "learning_rate": 5.233377045995435e-07, | |
| "loss": 0.0004, | |
| "step": 273227 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.016863718628883362, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 12.4816, | |
| "eval_samples_per_second": 21.472, | |
| "eval_steps_per_second": 1.442, | |
| "step": 274520 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 274520, | |
| "total_flos": 7.204011364904141e+16, | |
| "train_loss": 2.2036947758330143e-05, | |
| "train_runtime": 1601.2933, | |
| "train_samples_per_second": 2571.434, | |
| "train_steps_per_second": 171.436 | |
| } | |
| ], | |
| "logging_steps": 1373, | |
| "max_steps": 274520, | |
| "num_train_epochs": 20, | |
| "save_steps": 2746, | |
| "total_flos": 7.204011364904141e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |