| { | |
| "best_metric": 1.375998616218567, | |
| "best_model_checkpoint": "animal_151_types_image_detection/checkpoint-11400", | |
| "epoch": 100.0, | |
| "eval_steps": 500, | |
| "global_step": 11400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.037527593818984545, | |
| "eval_loss": 4.962153434753418, | |
| "eval_runtime": 14.7302, | |
| "eval_samples_per_second": 123.013, | |
| "eval_steps_per_second": 3.87, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.1335540838852097, | |
| "eval_loss": 4.885277271270752, | |
| "eval_runtime": 14.5295, | |
| "eval_samples_per_second": 124.712, | |
| "eval_steps_per_second": 3.923, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3498896247240618, | |
| "eval_loss": 4.794714450836182, | |
| "eval_runtime": 14.7328, | |
| "eval_samples_per_second": 122.99, | |
| "eval_steps_per_second": 3.869, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.576710816777042, | |
| "eval_loss": 4.702880382537842, | |
| "eval_runtime": 15.1167, | |
| "eval_samples_per_second": 119.868, | |
| "eval_steps_per_second": 3.771, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 4.801762114537446e-06, | |
| "loss": 4.8462, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7400662251655629, | |
| "eval_loss": 4.61031436920166, | |
| "eval_runtime": 14.5797, | |
| "eval_samples_per_second": 124.282, | |
| "eval_steps_per_second": 3.91, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8173289183222958, | |
| "eval_loss": 4.516598701477051, | |
| "eval_runtime": 14.6496, | |
| "eval_samples_per_second": 123.689, | |
| "eval_steps_per_second": 3.891, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8559602649006622, | |
| "eval_loss": 4.426823616027832, | |
| "eval_runtime": 14.6782, | |
| "eval_samples_per_second": 123.448, | |
| "eval_steps_per_second": 3.883, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8846578366445916, | |
| "eval_loss": 4.338470935821533, | |
| "eval_runtime": 14.8516, | |
| "eval_samples_per_second": 122.007, | |
| "eval_steps_per_second": 3.838, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 4.581497797356828e-06, | |
| "loss": 4.4139, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8979028697571744, | |
| "eval_loss": 4.253594875335693, | |
| "eval_runtime": 14.9472, | |
| "eval_samples_per_second": 121.226, | |
| "eval_steps_per_second": 3.813, | |
| "step": 1026 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9150110375275938, | |
| "eval_loss": 4.168024063110352, | |
| "eval_runtime": 14.7122, | |
| "eval_samples_per_second": 123.163, | |
| "eval_steps_per_second": 3.874, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9172185430463576, | |
| "eval_loss": 4.086403846740723, | |
| "eval_runtime": 14.7431, | |
| "eval_samples_per_second": 122.905, | |
| "eval_steps_per_second": 3.866, | |
| "step": 1254 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9321192052980133, | |
| "eval_loss": 4.009535789489746, | |
| "eval_runtime": 14.777, | |
| "eval_samples_per_second": 122.623, | |
| "eval_steps_per_second": 3.857, | |
| "step": 1368 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9398454746136865, | |
| "eval_loss": 3.932218313217163, | |
| "eval_runtime": 14.842, | |
| "eval_samples_per_second": 122.086, | |
| "eval_steps_per_second": 3.84, | |
| "step": 1482 | |
| }, | |
| { | |
| "epoch": 13.16, | |
| "learning_rate": 4.361233480176212e-06, | |
| "loss": 4.0075, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9420529801324503, | |
| "eval_loss": 3.859485149383545, | |
| "eval_runtime": 14.5871, | |
| "eval_samples_per_second": 124.219, | |
| "eval_steps_per_second": 3.908, | |
| "step": 1596 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9442604856512141, | |
| "eval_loss": 3.7879128456115723, | |
| "eval_runtime": 14.6963, | |
| "eval_samples_per_second": 123.296, | |
| "eval_steps_per_second": 3.879, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9464679911699779, | |
| "eval_loss": 3.7172069549560547, | |
| "eval_runtime": 14.7356, | |
| "eval_samples_per_second": 122.968, | |
| "eval_steps_per_second": 3.868, | |
| "step": 1824 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.9481236203090507, | |
| "eval_loss": 3.6492252349853516, | |
| "eval_runtime": 20.1559, | |
| "eval_samples_per_second": 89.899, | |
| "eval_steps_per_second": 2.828, | |
| "step": 1938 | |
| }, | |
| { | |
| "epoch": 17.54, | |
| "learning_rate": 4.140969162995595e-06, | |
| "loss": 3.6551, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9503311258278145, | |
| "eval_loss": 3.5814554691314697, | |
| "eval_runtime": 17.2491, | |
| "eval_samples_per_second": 105.049, | |
| "eval_steps_per_second": 3.305, | |
| "step": 2052 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.9514348785871964, | |
| "eval_loss": 3.517028331756592, | |
| "eval_runtime": 14.8364, | |
| "eval_samples_per_second": 122.132, | |
| "eval_steps_per_second": 3.842, | |
| "step": 2166 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9503311258278145, | |
| "eval_loss": 3.4523494243621826, | |
| "eval_runtime": 14.9385, | |
| "eval_samples_per_second": 121.297, | |
| "eval_steps_per_second": 3.816, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.9541942604856513, | |
| "eval_loss": 3.390517234802246, | |
| "eval_runtime": 14.7336, | |
| "eval_samples_per_second": 122.984, | |
| "eval_steps_per_second": 3.869, | |
| "step": 2394 | |
| }, | |
| { | |
| "epoch": 21.93, | |
| "learning_rate": 3.920704845814978e-06, | |
| "loss": 3.34, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.9558498896247241, | |
| "eval_loss": 3.3292999267578125, | |
| "eval_runtime": 14.7422, | |
| "eval_samples_per_second": 122.913, | |
| "eval_steps_per_second": 3.866, | |
| "step": 2508 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.9552980132450332, | |
| "eval_loss": 3.2692325115203857, | |
| "eval_runtime": 14.916, | |
| "eval_samples_per_second": 121.48, | |
| "eval_steps_per_second": 3.821, | |
| "step": 2622 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.9564017660044151, | |
| "eval_loss": 3.2137107849121094, | |
| "eval_runtime": 14.7629, | |
| "eval_samples_per_second": 122.74, | |
| "eval_steps_per_second": 3.861, | |
| "step": 2736 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.9575055187637969, | |
| "eval_loss": 3.156517267227173, | |
| "eval_runtime": 14.7516, | |
| "eval_samples_per_second": 122.834, | |
| "eval_steps_per_second": 3.864, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.9591611479028698, | |
| "eval_loss": 3.1020307540893555, | |
| "eval_runtime": 14.6198, | |
| "eval_samples_per_second": 123.942, | |
| "eval_steps_per_second": 3.899, | |
| "step": 2964 | |
| }, | |
| { | |
| "epoch": 26.32, | |
| "learning_rate": 3.7004405286343614e-06, | |
| "loss": 3.062, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.9580573951434879, | |
| "eval_loss": 3.047849178314209, | |
| "eval_runtime": 14.747, | |
| "eval_samples_per_second": 122.872, | |
| "eval_steps_per_second": 3.865, | |
| "step": 3078 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.9597130242825607, | |
| "eval_loss": 2.9951817989349365, | |
| "eval_runtime": 14.6085, | |
| "eval_samples_per_second": 124.038, | |
| "eval_steps_per_second": 3.902, | |
| "step": 3192 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.9608167770419426, | |
| "eval_loss": 2.9445724487304688, | |
| "eval_runtime": 14.744, | |
| "eval_samples_per_second": 122.897, | |
| "eval_steps_per_second": 3.866, | |
| "step": 3306 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.9641280353200883, | |
| "eval_loss": 2.8922934532165527, | |
| "eval_runtime": 14.7257, | |
| "eval_samples_per_second": 123.05, | |
| "eval_steps_per_second": 3.871, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 30.7, | |
| "learning_rate": 3.4801762114537445e-06, | |
| "loss": 2.8103, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.9635761589403974, | |
| "eval_loss": 2.8442115783691406, | |
| "eval_runtime": 14.5837, | |
| "eval_samples_per_second": 124.248, | |
| "eval_steps_per_second": 3.908, | |
| "step": 3534 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.9624724061810155, | |
| "eval_loss": 2.7976019382476807, | |
| "eval_runtime": 14.8078, | |
| "eval_samples_per_second": 122.368, | |
| "eval_steps_per_second": 3.849, | |
| "step": 3648 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.9663355408388521, | |
| "eval_loss": 2.749441623687744, | |
| "eval_runtime": 14.8845, | |
| "eval_samples_per_second": 121.737, | |
| "eval_steps_per_second": 3.829, | |
| "step": 3762 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.9646799116997793, | |
| "eval_loss": 2.702268600463867, | |
| "eval_runtime": 14.6998, | |
| "eval_samples_per_second": 123.267, | |
| "eval_steps_per_second": 3.878, | |
| "step": 3876 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.9646799116997793, | |
| "eval_loss": 2.656121253967285, | |
| "eval_runtime": 14.9899, | |
| "eval_samples_per_second": 120.881, | |
| "eval_steps_per_second": 3.803, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 35.09, | |
| "learning_rate": 3.259911894273128e-06, | |
| "loss": 2.5826, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.9657836644591612, | |
| "eval_loss": 2.613430976867676, | |
| "eval_runtime": 14.4375, | |
| "eval_samples_per_second": 125.507, | |
| "eval_steps_per_second": 3.948, | |
| "step": 4104 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.9663355408388521, | |
| "eval_loss": 2.5684773921966553, | |
| "eval_runtime": 14.8268, | |
| "eval_samples_per_second": 122.212, | |
| "eval_steps_per_second": 3.844, | |
| "step": 4218 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.9685430463576159, | |
| "eval_loss": 2.5256078243255615, | |
| "eval_runtime": 14.6038, | |
| "eval_samples_per_second": 124.078, | |
| "eval_steps_per_second": 3.903, | |
| "step": 4332 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.9696467991169978, | |
| "eval_loss": 2.4859821796417236, | |
| "eval_runtime": 14.7498, | |
| "eval_samples_per_second": 122.849, | |
| "eval_steps_per_second": 3.864, | |
| "step": 4446 | |
| }, | |
| { | |
| "epoch": 39.47, | |
| "learning_rate": 3.039647577092511e-06, | |
| "loss": 2.3758, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.967439293598234, | |
| "eval_loss": 2.4448373317718506, | |
| "eval_runtime": 14.4892, | |
| "eval_samples_per_second": 125.058, | |
| "eval_steps_per_second": 3.934, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.9707505518763797, | |
| "eval_loss": 2.4062910079956055, | |
| "eval_runtime": 14.5027, | |
| "eval_samples_per_second": 124.943, | |
| "eval_steps_per_second": 3.93, | |
| "step": 4674 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.9696467991169978, | |
| "eval_loss": 2.366445302963257, | |
| "eval_runtime": 14.5967, | |
| "eval_samples_per_second": 124.138, | |
| "eval_steps_per_second": 3.905, | |
| "step": 4788 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.9696467991169978, | |
| "eval_loss": 2.3301877975463867, | |
| "eval_runtime": 15.4794, | |
| "eval_samples_per_second": 117.059, | |
| "eval_steps_per_second": 3.682, | |
| "step": 4902 | |
| }, | |
| { | |
| "epoch": 43.86, | |
| "learning_rate": 2.819383259911895e-06, | |
| "loss": 2.1901, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.9685430463576159, | |
| "eval_loss": 2.292541980743408, | |
| "eval_runtime": 14.8646, | |
| "eval_samples_per_second": 121.9, | |
| "eval_steps_per_second": 3.835, | |
| "step": 5016 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.9713024282560706, | |
| "eval_loss": 2.258281707763672, | |
| "eval_runtime": 14.6506, | |
| "eval_samples_per_second": 123.681, | |
| "eval_steps_per_second": 3.891, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.9718543046357616, | |
| "eval_loss": 2.2219057083129883, | |
| "eval_runtime": 14.6119, | |
| "eval_samples_per_second": 124.009, | |
| "eval_steps_per_second": 3.901, | |
| "step": 5244 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.9713024282560706, | |
| "eval_loss": 2.1887381076812744, | |
| "eval_runtime": 14.7799, | |
| "eval_samples_per_second": 122.599, | |
| "eval_steps_per_second": 3.857, | |
| "step": 5358 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.9724061810154525, | |
| "eval_loss": 2.15564227104187, | |
| "eval_runtime": 14.5803, | |
| "eval_samples_per_second": 124.277, | |
| "eval_steps_per_second": 3.909, | |
| "step": 5472 | |
| }, | |
| { | |
| "epoch": 48.25, | |
| "learning_rate": 2.599118942731278e-06, | |
| "loss": 2.0234, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.9718543046357616, | |
| "eval_loss": 2.1227617263793945, | |
| "eval_runtime": 14.678, | |
| "eval_samples_per_second": 123.45, | |
| "eval_steps_per_second": 3.883, | |
| "step": 5586 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.9718543046357616, | |
| "eval_loss": 2.0911219120025635, | |
| "eval_runtime": 14.5634, | |
| "eval_samples_per_second": 124.421, | |
| "eval_steps_per_second": 3.914, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.9718543046357616, | |
| "eval_loss": 2.058539628982544, | |
| "eval_runtime": 14.5546, | |
| "eval_samples_per_second": 124.497, | |
| "eval_steps_per_second": 3.916, | |
| "step": 5814 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.9724061810154525, | |
| "eval_loss": 2.030808448791504, | |
| "eval_runtime": 14.7159, | |
| "eval_samples_per_second": 123.132, | |
| "eval_steps_per_second": 3.873, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 52.63, | |
| "learning_rate": 2.378854625550661e-06, | |
| "loss": 1.876, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.9729580573951435, | |
| "eval_loss": 1.999698281288147, | |
| "eval_runtime": 14.624, | |
| "eval_samples_per_second": 123.906, | |
| "eval_steps_per_second": 3.898, | |
| "step": 6042 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.9729580573951435, | |
| "eval_loss": 1.9714460372924805, | |
| "eval_runtime": 14.8384, | |
| "eval_samples_per_second": 122.116, | |
| "eval_steps_per_second": 3.841, | |
| "step": 6156 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.9724061810154525, | |
| "eval_loss": 1.944514274597168, | |
| "eval_runtime": 14.5863, | |
| "eval_samples_per_second": 124.226, | |
| "eval_steps_per_second": 3.908, | |
| "step": 6270 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.9718543046357616, | |
| "eval_loss": 1.9172853231430054, | |
| "eval_runtime": 14.6007, | |
| "eval_samples_per_second": 124.103, | |
| "eval_steps_per_second": 3.904, | |
| "step": 6384 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.9724061810154525, | |
| "eval_loss": 1.8919694423675537, | |
| "eval_runtime": 14.4525, | |
| "eval_samples_per_second": 125.377, | |
| "eval_steps_per_second": 3.944, | |
| "step": 6498 | |
| }, | |
| { | |
| "epoch": 57.02, | |
| "learning_rate": 2.1585903083700445e-06, | |
| "loss": 1.7451, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.9740618101545254, | |
| "eval_loss": 1.8659210205078125, | |
| "eval_runtime": 14.7567, | |
| "eval_samples_per_second": 122.791, | |
| "eval_steps_per_second": 3.863, | |
| "step": 6612 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.9729580573951435, | |
| "eval_loss": 1.842057704925537, | |
| "eval_runtime": 14.733, | |
| "eval_samples_per_second": 122.989, | |
| "eval_steps_per_second": 3.869, | |
| "step": 6726 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.9746136865342163, | |
| "eval_loss": 1.8180880546569824, | |
| "eval_runtime": 14.5204, | |
| "eval_samples_per_second": 124.79, | |
| "eval_steps_per_second": 3.926, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.9735099337748344, | |
| "eval_loss": 1.7939091920852661, | |
| "eval_runtime": 14.6724, | |
| "eval_samples_per_second": 123.497, | |
| "eval_steps_per_second": 3.885, | |
| "step": 6954 | |
| }, | |
| { | |
| "epoch": 61.4, | |
| "learning_rate": 1.9383259911894276e-06, | |
| "loss": 1.6286, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.9729580573951435, | |
| "eval_loss": 1.7723444700241089, | |
| "eval_runtime": 14.599, | |
| "eval_samples_per_second": 124.118, | |
| "eval_steps_per_second": 3.904, | |
| "step": 7068 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.9740618101545254, | |
| "eval_loss": 1.7489854097366333, | |
| "eval_runtime": 14.5258, | |
| "eval_samples_per_second": 124.743, | |
| "eval_steps_per_second": 3.924, | |
| "step": 7182 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.9757174392935982, | |
| "eval_loss": 1.7285088300704956, | |
| "eval_runtime": 14.4828, | |
| "eval_samples_per_second": 125.114, | |
| "eval_steps_per_second": 3.936, | |
| "step": 7296 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.9740618101545254, | |
| "eval_loss": 1.7077668905258179, | |
| "eval_runtime": 14.7222, | |
| "eval_samples_per_second": 123.079, | |
| "eval_steps_per_second": 3.872, | |
| "step": 7410 | |
| }, | |
| { | |
| "epoch": 65.79, | |
| "learning_rate": 1.7180616740088108e-06, | |
| "loss": 1.5281, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.9746136865342163, | |
| "eval_loss": 1.6885572671890259, | |
| "eval_runtime": 14.7611, | |
| "eval_samples_per_second": 122.755, | |
| "eval_steps_per_second": 3.862, | |
| "step": 7524 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.9740618101545254, | |
| "eval_loss": 1.6697474718093872, | |
| "eval_runtime": 14.5138, | |
| "eval_samples_per_second": 124.846, | |
| "eval_steps_per_second": 3.927, | |
| "step": 7638 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.9746136865342163, | |
| "eval_loss": 1.6512248516082764, | |
| "eval_runtime": 14.4806, | |
| "eval_samples_per_second": 125.133, | |
| "eval_steps_per_second": 3.936, | |
| "step": 7752 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.9735099337748344, | |
| "eval_loss": 1.6349101066589355, | |
| "eval_runtime": 14.6474, | |
| "eval_samples_per_second": 123.708, | |
| "eval_steps_per_second": 3.891, | |
| "step": 7866 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.9729580573951435, | |
| "eval_loss": 1.6167147159576416, | |
| "eval_runtime": 14.5436, | |
| "eval_samples_per_second": 124.591, | |
| "eval_steps_per_second": 3.919, | |
| "step": 7980 | |
| }, | |
| { | |
| "epoch": 70.18, | |
| "learning_rate": 1.497797356828194e-06, | |
| "loss": 1.4403, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.9729580573951435, | |
| "eval_loss": 1.600691556930542, | |
| "eval_runtime": 14.4531, | |
| "eval_samples_per_second": 125.371, | |
| "eval_steps_per_second": 3.944, | |
| "step": 8094 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.9746136865342163, | |
| "eval_loss": 1.5854783058166504, | |
| "eval_runtime": 14.6051, | |
| "eval_samples_per_second": 124.067, | |
| "eval_steps_per_second": 3.903, | |
| "step": 8208 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.9751655629139073, | |
| "eval_loss": 1.5697646141052246, | |
| "eval_runtime": 14.7222, | |
| "eval_samples_per_second": 123.079, | |
| "eval_steps_per_second": 3.872, | |
| "step": 8322 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.9735099337748344, | |
| "eval_loss": 1.5558655261993408, | |
| "eval_runtime": 14.7278, | |
| "eval_samples_per_second": 123.033, | |
| "eval_steps_per_second": 3.87, | |
| "step": 8436 | |
| }, | |
| { | |
| "epoch": 74.56, | |
| "learning_rate": 1.2775330396475772e-06, | |
| "loss": 1.3684, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.9746136865342163, | |
| "eval_loss": 1.5405701398849487, | |
| "eval_runtime": 14.4937, | |
| "eval_samples_per_second": 125.02, | |
| "eval_steps_per_second": 3.933, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.9735099337748344, | |
| "eval_loss": 1.52810537815094, | |
| "eval_runtime": 14.5545, | |
| "eval_samples_per_second": 124.497, | |
| "eval_steps_per_second": 3.916, | |
| "step": 8664 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.9735099337748344, | |
| "eval_loss": 1.5153011083602905, | |
| "eval_runtime": 14.6637, | |
| "eval_samples_per_second": 123.57, | |
| "eval_steps_per_second": 3.887, | |
| "step": 8778 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.9746136865342163, | |
| "eval_loss": 1.5028570890426636, | |
| "eval_runtime": 14.5939, | |
| "eval_samples_per_second": 124.162, | |
| "eval_steps_per_second": 3.906, | |
| "step": 8892 | |
| }, | |
| { | |
| "epoch": 78.95, | |
| "learning_rate": 1.0572687224669604e-06, | |
| "loss": 1.3041, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.9740618101545254, | |
| "eval_loss": 1.4909206628799438, | |
| "eval_runtime": 14.5501, | |
| "eval_samples_per_second": 124.535, | |
| "eval_steps_per_second": 3.918, | |
| "step": 9006 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.9740618101545254, | |
| "eval_loss": 1.4797635078430176, | |
| "eval_runtime": 14.5945, | |
| "eval_samples_per_second": 124.157, | |
| "eval_steps_per_second": 3.906, | |
| "step": 9120 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.9751655629139073, | |
| "eval_loss": 1.469772219657898, | |
| "eval_runtime": 14.868, | |
| "eval_samples_per_second": 121.873, | |
| "eval_steps_per_second": 3.834, | |
| "step": 9234 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.9740618101545254, | |
| "eval_loss": 1.4597550630569458, | |
| "eval_runtime": 14.5863, | |
| "eval_samples_per_second": 124.226, | |
| "eval_steps_per_second": 3.908, | |
| "step": 9348 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.9746136865342163, | |
| "eval_loss": 1.4507455825805664, | |
| "eval_runtime": 14.5654, | |
| "eval_samples_per_second": 124.404, | |
| "eval_steps_per_second": 3.913, | |
| "step": 9462 | |
| }, | |
| { | |
| "epoch": 83.33, | |
| "learning_rate": 8.370044052863437e-07, | |
| "loss": 1.2554, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.9735099337748344, | |
| "eval_loss": 1.4420080184936523, | |
| "eval_runtime": 14.7476, | |
| "eval_samples_per_second": 122.868, | |
| "eval_steps_per_second": 3.865, | |
| "step": 9576 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.9740618101545254, | |
| "eval_loss": 1.433323860168457, | |
| "eval_runtime": 14.5881, | |
| "eval_samples_per_second": 124.211, | |
| "eval_steps_per_second": 3.907, | |
| "step": 9690 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.9740618101545254, | |
| "eval_loss": 1.4266729354858398, | |
| "eval_runtime": 14.6204, | |
| "eval_samples_per_second": 123.937, | |
| "eval_steps_per_second": 3.899, | |
| "step": 9804 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.9746136865342163, | |
| "eval_loss": 1.419144630432129, | |
| "eval_runtime": 14.7023, | |
| "eval_samples_per_second": 123.246, | |
| "eval_steps_per_second": 3.877, | |
| "step": 9918 | |
| }, | |
| { | |
| "epoch": 87.72, | |
| "learning_rate": 6.16740088105727e-07, | |
| "loss": 1.2166, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.9746136865342163, | |
| "eval_loss": 1.41357421875, | |
| "eval_runtime": 14.7197, | |
| "eval_samples_per_second": 123.101, | |
| "eval_steps_per_second": 3.872, | |
| "step": 10032 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.9751655629139073, | |
| "eval_loss": 1.4069515466690063, | |
| "eval_runtime": 14.5913, | |
| "eval_samples_per_second": 124.184, | |
| "eval_steps_per_second": 3.906, | |
| "step": 10146 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.9751655629139073, | |
| "eval_loss": 1.4011104106903076, | |
| "eval_runtime": 14.4858, | |
| "eval_samples_per_second": 125.088, | |
| "eval_steps_per_second": 3.935, | |
| "step": 10260 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.9751655629139073, | |
| "eval_loss": 1.396867036819458, | |
| "eval_runtime": 14.4869, | |
| "eval_samples_per_second": 125.079, | |
| "eval_steps_per_second": 3.935, | |
| "step": 10374 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.9751655629139073, | |
| "eval_loss": 1.3927924633026123, | |
| "eval_runtime": 14.9674, | |
| "eval_samples_per_second": 121.063, | |
| "eval_steps_per_second": 3.808, | |
| "step": 10488 | |
| }, | |
| { | |
| "epoch": 92.11, | |
| "learning_rate": 3.964757709251102e-07, | |
| "loss": 1.1885, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.9740618101545254, | |
| "eval_loss": 1.3884556293487549, | |
| "eval_runtime": 15.051, | |
| "eval_samples_per_second": 120.39, | |
| "eval_steps_per_second": 3.787, | |
| "step": 10602 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.9740618101545254, | |
| "eval_loss": 1.3855311870574951, | |
| "eval_runtime": 14.5082, | |
| "eval_samples_per_second": 124.895, | |
| "eval_steps_per_second": 3.929, | |
| "step": 10716 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.9746136865342163, | |
| "eval_loss": 1.3824039697647095, | |
| "eval_runtime": 14.8975, | |
| "eval_samples_per_second": 121.631, | |
| "eval_steps_per_second": 3.826, | |
| "step": 10830 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.9746136865342163, | |
| "eval_loss": 1.3800771236419678, | |
| "eval_runtime": 14.7571, | |
| "eval_samples_per_second": 122.788, | |
| "eval_steps_per_second": 3.863, | |
| "step": 10944 | |
| }, | |
| { | |
| "epoch": 96.49, | |
| "learning_rate": 1.7621145374449343e-07, | |
| "loss": 1.1703, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.9746136865342163, | |
| "eval_loss": 1.378131628036499, | |
| "eval_runtime": 14.7894, | |
| "eval_samples_per_second": 122.52, | |
| "eval_steps_per_second": 3.854, | |
| "step": 11058 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.9746136865342163, | |
| "eval_loss": 1.3769623041152954, | |
| "eval_runtime": 14.5124, | |
| "eval_samples_per_second": 124.858, | |
| "eval_steps_per_second": 3.928, | |
| "step": 11172 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.9746136865342163, | |
| "eval_loss": 1.3762928247451782, | |
| "eval_runtime": 14.7379, | |
| "eval_samples_per_second": 122.948, | |
| "eval_steps_per_second": 3.868, | |
| "step": 11286 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.9746136865342163, | |
| "eval_loss": 1.375998616218567, | |
| "eval_runtime": 15.1012, | |
| "eval_samples_per_second": 119.991, | |
| "eval_steps_per_second": 3.775, | |
| "step": 11400 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 11400, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "total_flos": 5.624120064761856e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |