| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "beit-base-patch16-224-hasta-75-fold1/checkpoint-18", | |
| "epoch": 100.0, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 2.2077012062072754, | |
| "eval_runtime": 0.1832, | |
| "eval_samples_per_second": 65.496, | |
| "eval_steps_per_second": 5.458, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 1.7828108072280884, | |
| "eval_runtime": 0.181, | |
| "eval_samples_per_second": 66.304, | |
| "eval_steps_per_second": 5.525, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3333333333333333, | |
| "eval_loss": 1.0542601346969604, | |
| "eval_runtime": 0.181, | |
| "eval_samples_per_second": 66.296, | |
| "eval_steps_per_second": 5.525, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.4304567277431488, | |
| "eval_runtime": 0.1804, | |
| "eval_samples_per_second": 66.504, | |
| "eval_steps_per_second": 5.542, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.26718705892562866, | |
| "eval_runtime": 0.1816, | |
| "eval_samples_per_second": 66.078, | |
| "eval_steps_per_second": 5.506, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.3206009566783905, | |
| "eval_runtime": 0.1785, | |
| "eval_samples_per_second": 67.21, | |
| "eval_steps_per_second": 5.601, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.3317834734916687, | |
| "eval_runtime": 0.1781, | |
| "eval_samples_per_second": 67.376, | |
| "eval_steps_per_second": 5.615, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.30066391825675964, | |
| "eval_runtime": 0.1822, | |
| "eval_samples_per_second": 65.88, | |
| "eval_steps_per_second": 5.49, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.32681936025619507, | |
| "eval_runtime": 0.1797, | |
| "eval_samples_per_second": 66.776, | |
| "eval_steps_per_second": 5.565, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 4.443905830383301, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4863, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.3424707353115082, | |
| "eval_runtime": 0.1796, | |
| "eval_samples_per_second": 66.82, | |
| "eval_steps_per_second": 5.568, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.2905902564525604, | |
| "eval_runtime": 0.1813, | |
| "eval_samples_per_second": 66.201, | |
| "eval_steps_per_second": 5.517, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.26393598318099976, | |
| "eval_runtime": 0.1806, | |
| "eval_samples_per_second": 66.428, | |
| "eval_steps_per_second": 5.536, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.29621657729148865, | |
| "eval_runtime": 0.1827, | |
| "eval_samples_per_second": 65.665, | |
| "eval_steps_per_second": 5.472, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.444223016500473, | |
| "eval_runtime": 0.1832, | |
| "eval_samples_per_second": 65.485, | |
| "eval_steps_per_second": 5.457, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.3107624351978302, | |
| "eval_runtime": 0.1828, | |
| "eval_samples_per_second": 65.656, | |
| "eval_steps_per_second": 5.471, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.2321174144744873, | |
| "eval_runtime": 0.18, | |
| "eval_samples_per_second": 66.659, | |
| "eval_steps_per_second": 5.555, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.23090867698192596, | |
| "eval_runtime": 0.1791, | |
| "eval_samples_per_second": 67.013, | |
| "eval_steps_per_second": 5.584, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.24317891895771027, | |
| "eval_runtime": 0.1826, | |
| "eval_samples_per_second": 65.703, | |
| "eval_steps_per_second": 5.475, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.22404837608337402, | |
| "eval_runtime": 0.1858, | |
| "eval_samples_per_second": 64.581, | |
| "eval_steps_per_second": 5.382, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 2.4318888187408447, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.1603, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.16075477004051208, | |
| "eval_runtime": 0.1738, | |
| "eval_samples_per_second": 69.059, | |
| "eval_steps_per_second": 5.755, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.1274556964635849, | |
| "eval_runtime": 0.1768, | |
| "eval_samples_per_second": 67.881, | |
| "eval_steps_per_second": 5.657, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.11907526105642319, | |
| "eval_runtime": 0.1807, | |
| "eval_samples_per_second": 66.408, | |
| "eval_steps_per_second": 5.534, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.10295626521110535, | |
| "eval_runtime": 0.1785, | |
| "eval_samples_per_second": 67.233, | |
| "eval_steps_per_second": 5.603, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.10096978396177292, | |
| "eval_runtime": 0.184, | |
| "eval_samples_per_second": 65.212, | |
| "eval_steps_per_second": 5.434, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.08157830685377121, | |
| "eval_runtime": 0.1815, | |
| "eval_samples_per_second": 66.129, | |
| "eval_steps_per_second": 5.511, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.1813768893480301, | |
| "eval_runtime": 0.1773, | |
| "eval_samples_per_second": 67.673, | |
| "eval_steps_per_second": 5.639, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.16538240015506744, | |
| "eval_runtime": 0.1785, | |
| "eval_samples_per_second": 67.215, | |
| "eval_steps_per_second": 5.601, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.09447892755270004, | |
| "eval_runtime": 0.1866, | |
| "eval_samples_per_second": 64.315, | |
| "eval_steps_per_second": 5.36, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.08471832424402237, | |
| "eval_runtime": 0.178, | |
| "eval_samples_per_second": 67.43, | |
| "eval_steps_per_second": 5.619, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 2.647221088409424, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.1007, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.15657053887844086, | |
| "eval_runtime": 0.1773, | |
| "eval_samples_per_second": 67.666, | |
| "eval_steps_per_second": 5.639, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0818849727511406, | |
| "eval_runtime": 0.1805, | |
| "eval_samples_per_second": 66.482, | |
| "eval_steps_per_second": 5.54, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.07821951806545258, | |
| "eval_runtime": 0.1819, | |
| "eval_samples_per_second": 65.982, | |
| "eval_steps_per_second": 5.498, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0781416967511177, | |
| "eval_runtime": 0.1816, | |
| "eval_samples_per_second": 66.073, | |
| "eval_steps_per_second": 5.506, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.06351720541715622, | |
| "eval_runtime": 0.1762, | |
| "eval_samples_per_second": 68.092, | |
| "eval_steps_per_second": 5.674, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.06752466410398483, | |
| "eval_runtime": 0.1843, | |
| "eval_samples_per_second": 65.122, | |
| "eval_steps_per_second": 5.427, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.1137080118060112, | |
| "eval_runtime": 0.1789, | |
| "eval_samples_per_second": 67.069, | |
| "eval_steps_per_second": 5.589, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.12665808200836182, | |
| "eval_runtime": 0.1849, | |
| "eval_samples_per_second": 64.894, | |
| "eval_steps_per_second": 5.408, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.1438184678554535, | |
| "eval_runtime": 0.1772, | |
| "eval_samples_per_second": 67.727, | |
| "eval_steps_per_second": 5.644, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.1301492154598236, | |
| "eval_runtime": 0.1815, | |
| "eval_samples_per_second": 66.113, | |
| "eval_steps_per_second": 5.509, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 2.206031560897827, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0573, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.11228451877832413, | |
| "eval_runtime": 0.1755, | |
| "eval_samples_per_second": 68.382, | |
| "eval_steps_per_second": 5.699, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0673147514462471, | |
| "eval_runtime": 0.1793, | |
| "eval_samples_per_second": 66.913, | |
| "eval_steps_per_second": 5.576, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.026470685377717018, | |
| "eval_runtime": 0.1912, | |
| "eval_samples_per_second": 62.752, | |
| "eval_steps_per_second": 5.229, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.031682901084423065, | |
| "eval_runtime": 0.1799, | |
| "eval_samples_per_second": 66.702, | |
| "eval_steps_per_second": 5.558, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.04610493779182434, | |
| "eval_runtime": 0.1797, | |
| "eval_samples_per_second": 66.786, | |
| "eval_steps_per_second": 5.566, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.03257732838392258, | |
| "eval_runtime": 0.1852, | |
| "eval_samples_per_second": 64.791, | |
| "eval_steps_per_second": 5.399, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.022052617743611336, | |
| "eval_runtime": 0.1804, | |
| "eval_samples_per_second": 66.535, | |
| "eval_steps_per_second": 5.545, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.022693796083331108, | |
| "eval_runtime": 0.1857, | |
| "eval_samples_per_second": 64.616, | |
| "eval_steps_per_second": 5.385, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.021375102922320366, | |
| "eval_runtime": 0.1811, | |
| "eval_samples_per_second": 66.277, | |
| "eval_steps_per_second": 5.523, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.017641151323914528, | |
| "eval_runtime": 0.1792, | |
| "eval_samples_per_second": 66.969, | |
| "eval_steps_per_second": 5.581, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "grad_norm": 2.6644582748413086, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0566, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.014967289753258228, | |
| "eval_runtime": 0.1798, | |
| "eval_samples_per_second": 66.749, | |
| "eval_steps_per_second": 5.562, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.015390962362289429, | |
| "eval_runtime": 0.1849, | |
| "eval_samples_per_second": 64.898, | |
| "eval_steps_per_second": 5.408, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.013894349336624146, | |
| "eval_runtime": 0.1828, | |
| "eval_samples_per_second": 65.644, | |
| "eval_steps_per_second": 5.47, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.009721777401864529, | |
| "eval_runtime": 0.183, | |
| "eval_samples_per_second": 65.56, | |
| "eval_steps_per_second": 5.463, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.01429061684757471, | |
| "eval_runtime": 0.1805, | |
| "eval_samples_per_second": 66.473, | |
| "eval_steps_per_second": 5.539, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.027167662978172302, | |
| "eval_runtime": 0.1829, | |
| "eval_samples_per_second": 65.604, | |
| "eval_steps_per_second": 5.467, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.04265804961323738, | |
| "eval_runtime": 0.1773, | |
| "eval_samples_per_second": 67.682, | |
| "eval_steps_per_second": 5.64, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.03430110216140747, | |
| "eval_runtime": 0.1781, | |
| "eval_samples_per_second": 67.383, | |
| "eval_steps_per_second": 5.615, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.028985222801566124, | |
| "eval_runtime": 0.1797, | |
| "eval_samples_per_second": 66.762, | |
| "eval_steps_per_second": 5.563, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.05569181963801384, | |
| "eval_runtime": 0.1795, | |
| "eval_samples_per_second": 66.845, | |
| "eval_steps_per_second": 5.57, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "grad_norm": 1.0558639764785767, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0242, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0904507040977478, | |
| "eval_runtime": 0.1778, | |
| "eval_samples_per_second": 67.489, | |
| "eval_steps_per_second": 5.624, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.1373545080423355, | |
| "eval_runtime": 0.1803, | |
| "eval_samples_per_second": 66.553, | |
| "eval_steps_per_second": 5.546, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.17625844478607178, | |
| "eval_runtime": 0.1822, | |
| "eval_samples_per_second": 65.851, | |
| "eval_steps_per_second": 5.488, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.179295614361763, | |
| "eval_runtime": 0.1819, | |
| "eval_samples_per_second": 65.963, | |
| "eval_steps_per_second": 5.497, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.1639540046453476, | |
| "eval_runtime": 0.1821, | |
| "eval_samples_per_second": 65.893, | |
| "eval_steps_per_second": 5.491, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.14449164271354675, | |
| "eval_runtime": 0.1825, | |
| "eval_samples_per_second": 65.738, | |
| "eval_steps_per_second": 5.478, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.10922203212976456, | |
| "eval_runtime": 0.1776, | |
| "eval_samples_per_second": 67.567, | |
| "eval_steps_per_second": 5.631, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.09147190302610397, | |
| "eval_runtime": 0.1777, | |
| "eval_samples_per_second": 67.527, | |
| "eval_steps_per_second": 5.627, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.06401555240154266, | |
| "eval_runtime": 0.1867, | |
| "eval_samples_per_second": 64.265, | |
| "eval_steps_per_second": 5.355, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.03757796436548233, | |
| "eval_runtime": 0.1798, | |
| "eval_samples_per_second": 66.739, | |
| "eval_steps_per_second": 5.562, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "grad_norm": 1.6899287700653076, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0339, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.02968785911798477, | |
| "eval_runtime": 0.1748, | |
| "eval_samples_per_second": 68.654, | |
| "eval_steps_per_second": 5.721, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.023778622969985008, | |
| "eval_runtime": 0.1792, | |
| "eval_samples_per_second": 66.955, | |
| "eval_steps_per_second": 5.58, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.01778542995452881, | |
| "eval_runtime": 0.1836, | |
| "eval_samples_per_second": 65.367, | |
| "eval_steps_per_second": 5.447, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.01042032241821289, | |
| "eval_runtime": 0.1791, | |
| "eval_samples_per_second": 67.01, | |
| "eval_steps_per_second": 5.584, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0063457731157541275, | |
| "eval_runtime": 0.178, | |
| "eval_samples_per_second": 67.432, | |
| "eval_steps_per_second": 5.619, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.004192787688225508, | |
| "eval_runtime": 0.18, | |
| "eval_samples_per_second": 66.67, | |
| "eval_steps_per_second": 5.556, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.003145643277093768, | |
| "eval_runtime": 0.1809, | |
| "eval_samples_per_second": 66.32, | |
| "eval_steps_per_second": 5.527, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0028521008789539337, | |
| "eval_runtime": 0.1833, | |
| "eval_samples_per_second": 65.45, | |
| "eval_steps_per_second": 5.454, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.003350273473188281, | |
| "eval_runtime": 0.1814, | |
| "eval_samples_per_second": 66.157, | |
| "eval_steps_per_second": 5.513, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0035124036949127913, | |
| "eval_runtime": 0.1822, | |
| "eval_samples_per_second": 65.852, | |
| "eval_steps_per_second": 5.488, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "grad_norm": 5.092667579650879, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0532, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0035463341046124697, | |
| "eval_runtime": 0.1807, | |
| "eval_samples_per_second": 66.392, | |
| "eval_steps_per_second": 5.533, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0038894719909876585, | |
| "eval_runtime": 0.1814, | |
| "eval_samples_per_second": 66.14, | |
| "eval_steps_per_second": 5.512, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.005399493966251612, | |
| "eval_runtime": 0.1807, | |
| "eval_samples_per_second": 66.412, | |
| "eval_steps_per_second": 5.534, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.010995940305292606, | |
| "eval_runtime": 0.1792, | |
| "eval_samples_per_second": 66.972, | |
| "eval_steps_per_second": 5.581, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.025468939915299416, | |
| "eval_runtime": 0.1831, | |
| "eval_samples_per_second": 65.53, | |
| "eval_steps_per_second": 5.461, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.05003314092755318, | |
| "eval_runtime": 0.1803, | |
| "eval_samples_per_second": 66.549, | |
| "eval_steps_per_second": 5.546, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.08439437299966812, | |
| "eval_runtime": 0.1773, | |
| "eval_samples_per_second": 67.674, | |
| "eval_steps_per_second": 5.64, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.11905407905578613, | |
| "eval_runtime": 0.1855, | |
| "eval_samples_per_second": 64.702, | |
| "eval_steps_per_second": 5.392, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.14367732405662537, | |
| "eval_runtime": 0.1795, | |
| "eval_samples_per_second": 66.857, | |
| "eval_steps_per_second": 5.571, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.15639398992061615, | |
| "eval_runtime": 0.1833, | |
| "eval_samples_per_second": 65.456, | |
| "eval_steps_per_second": 5.455, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "grad_norm": 1.2882177829742432, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0316, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.15441086888313293, | |
| "eval_runtime": 0.1825, | |
| "eval_samples_per_second": 65.747, | |
| "eval_steps_per_second": 5.479, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.1454831212759018, | |
| "eval_runtime": 0.1777, | |
| "eval_samples_per_second": 67.533, | |
| "eval_steps_per_second": 5.628, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.13830962777137756, | |
| "eval_runtime": 0.1799, | |
| "eval_samples_per_second": 66.706, | |
| "eval_steps_per_second": 5.559, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.11936721205711365, | |
| "eval_runtime": 0.1803, | |
| "eval_samples_per_second": 66.542, | |
| "eval_steps_per_second": 5.545, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.10268055647611618, | |
| "eval_runtime": 0.1808, | |
| "eval_samples_per_second": 66.384, | |
| "eval_steps_per_second": 5.532, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.08746868371963501, | |
| "eval_runtime": 0.1911, | |
| "eval_samples_per_second": 62.805, | |
| "eval_steps_per_second": 5.234, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.07148657739162445, | |
| "eval_runtime": 0.1759, | |
| "eval_samples_per_second": 68.224, | |
| "eval_steps_per_second": 5.685, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.060756634920835495, | |
| "eval_runtime": 0.1821, | |
| "eval_samples_per_second": 65.899, | |
| "eval_steps_per_second": 5.492, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.05189364030957222, | |
| "eval_runtime": 0.1845, | |
| "eval_samples_per_second": 65.035, | |
| "eval_steps_per_second": 5.42, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.04678298905491829, | |
| "eval_runtime": 0.182, | |
| "eval_samples_per_second": 65.937, | |
| "eval_steps_per_second": 5.495, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "grad_norm": 3.1393415927886963, | |
| "learning_rate": 0.0, | |
| "loss": 0.0299, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.04420096054673195, | |
| "eval_runtime": 0.1774, | |
| "eval_samples_per_second": 67.659, | |
| "eval_steps_per_second": 5.638, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 100, | |
| "total_flos": 4.802492916781056e+17, | |
| "train_loss": 0.10338099300861359, | |
| "train_runtime": 420.0817, | |
| "train_samples_per_second": 14.759, | |
| "train_steps_per_second": 0.238 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.24317891895771027, | |
| "eval_runtime": 0.2414, | |
| "eval_samples_per_second": 49.711, | |
| "eval_steps_per_second": 4.143, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.802492916781056e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |