| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "beit-base-patch16-224-hasta-75-fold4/checkpoint-30", | |
| "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": 0.08333333333333333, | |
| "eval_loss": 2.3240678310394287, | |
| "eval_runtime": 0.1712, | |
| "eval_samples_per_second": 70.075, | |
| "eval_steps_per_second": 5.84, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.08333333333333333, | |
| "eval_loss": 1.8900293111801147, | |
| "eval_runtime": 0.1855, | |
| "eval_samples_per_second": 64.684, | |
| "eval_steps_per_second": 5.39, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3333333333333333, | |
| "eval_loss": 1.1748418807983398, | |
| "eval_runtime": 0.1814, | |
| "eval_samples_per_second": 66.134, | |
| "eval_steps_per_second": 5.511, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.5751119256019592, | |
| "eval_runtime": 0.1769, | |
| "eval_samples_per_second": 67.841, | |
| "eval_steps_per_second": 5.653, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.42243918776512146, | |
| "eval_runtime": 0.1835, | |
| "eval_samples_per_second": 65.396, | |
| "eval_steps_per_second": 5.45, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.3931402266025543, | |
| "eval_runtime": 0.176, | |
| "eval_samples_per_second": 68.184, | |
| "eval_steps_per_second": 5.682, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.36350491642951965, | |
| "eval_runtime": 0.1804, | |
| "eval_samples_per_second": 66.514, | |
| "eval_steps_per_second": 5.543, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.5636505484580994, | |
| "eval_runtime": 0.1786, | |
| "eval_samples_per_second": 67.173, | |
| "eval_steps_per_second": 5.598, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.4256010949611664, | |
| "eval_runtime": 0.1803, | |
| "eval_samples_per_second": 66.56, | |
| "eval_steps_per_second": 5.547, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 2.9971117973327637, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4996, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.2829968333244324, | |
| "eval_runtime": 0.1808, | |
| "eval_samples_per_second": 66.372, | |
| "eval_steps_per_second": 5.531, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.27432435750961304, | |
| "eval_runtime": 0.1821, | |
| "eval_samples_per_second": 65.883, | |
| "eval_steps_per_second": 5.49, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.4504832327365875, | |
| "eval_runtime": 0.1832, | |
| "eval_samples_per_second": 65.49, | |
| "eval_steps_per_second": 5.458, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.3551560342311859, | |
| "eval_runtime": 0.1799, | |
| "eval_samples_per_second": 66.701, | |
| "eval_steps_per_second": 5.558, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.24533440172672272, | |
| "eval_runtime": 0.1786, | |
| "eval_samples_per_second": 67.184, | |
| "eval_steps_per_second": 5.599, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.25282785296440125, | |
| "eval_runtime": 0.1754, | |
| "eval_samples_per_second": 68.41, | |
| "eval_steps_per_second": 5.701, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.292589396238327, | |
| "eval_runtime": 0.1736, | |
| "eval_samples_per_second": 69.116, | |
| "eval_steps_per_second": 5.76, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.3253059685230255, | |
| "eval_runtime": 0.1798, | |
| "eval_samples_per_second": 66.746, | |
| "eval_steps_per_second": 5.562, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.33665966987609863, | |
| "eval_runtime": 0.1802, | |
| "eval_samples_per_second": 66.592, | |
| "eval_steps_per_second": 5.549, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.3681429326534271, | |
| "eval_runtime": 0.1762, | |
| "eval_samples_per_second": 68.114, | |
| "eval_steps_per_second": 5.676, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 3.239417314529419, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.1796, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.26769375801086426, | |
| "eval_runtime": 0.1824, | |
| "eval_samples_per_second": 65.804, | |
| "eval_steps_per_second": 5.484, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.2703898251056671, | |
| "eval_runtime": 0.1838, | |
| "eval_samples_per_second": 65.272, | |
| "eval_steps_per_second": 5.439, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.3115863502025604, | |
| "eval_runtime": 0.1833, | |
| "eval_samples_per_second": 65.477, | |
| "eval_steps_per_second": 5.456, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.36495253443717957, | |
| "eval_runtime": 0.179, | |
| "eval_samples_per_second": 67.023, | |
| "eval_steps_per_second": 5.585, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.21704982221126556, | |
| "eval_runtime": 0.1764, | |
| "eval_samples_per_second": 68.023, | |
| "eval_steps_per_second": 5.669, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.21135270595550537, | |
| "eval_runtime": 0.1851, | |
| "eval_samples_per_second": 64.832, | |
| "eval_steps_per_second": 5.403, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.1976069211959839, | |
| "eval_runtime": 0.1808, | |
| "eval_samples_per_second": 66.38, | |
| "eval_steps_per_second": 5.532, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.16190174221992493, | |
| "eval_runtime": 0.1803, | |
| "eval_samples_per_second": 66.549, | |
| "eval_steps_per_second": 5.546, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.1646103709936142, | |
| "eval_runtime": 0.1783, | |
| "eval_samples_per_second": 67.31, | |
| "eval_steps_per_second": 5.609, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.1431630551815033, | |
| "eval_runtime": 0.1822, | |
| "eval_samples_per_second": 65.851, | |
| "eval_steps_per_second": 5.488, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 2.7249929904937744, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.1179, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.08116643875837326, | |
| "eval_runtime": 0.1826, | |
| "eval_samples_per_second": 65.716, | |
| "eval_steps_per_second": 5.476, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.11628057807683945, | |
| "eval_runtime": 0.1856, | |
| "eval_samples_per_second": 64.665, | |
| "eval_steps_per_second": 5.389, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.08982894569635391, | |
| "eval_runtime": 0.1763, | |
| "eval_samples_per_second": 68.058, | |
| "eval_steps_per_second": 5.672, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.11901328712701797, | |
| "eval_runtime": 0.1805, | |
| "eval_samples_per_second": 66.477, | |
| "eval_steps_per_second": 5.54, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.14636912941932678, | |
| "eval_runtime": 0.1814, | |
| "eval_samples_per_second": 66.154, | |
| "eval_steps_per_second": 5.513, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.11360140889883041, | |
| "eval_runtime": 0.1941, | |
| "eval_samples_per_second": 61.837, | |
| "eval_steps_per_second": 5.153, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.2270035743713379, | |
| "eval_runtime": 0.1821, | |
| "eval_samples_per_second": 65.904, | |
| "eval_steps_per_second": 5.492, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.22648875415325165, | |
| "eval_runtime": 0.1802, | |
| "eval_samples_per_second": 66.606, | |
| "eval_steps_per_second": 5.551, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.09951093047857285, | |
| "eval_runtime": 0.1797, | |
| "eval_samples_per_second": 66.76, | |
| "eval_steps_per_second": 5.563, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.08532660454511642, | |
| "eval_runtime": 0.1843, | |
| "eval_samples_per_second": 65.1, | |
| "eval_steps_per_second": 5.425, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 3.2059624195098877, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1084, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.08578302711248398, | |
| "eval_runtime": 0.1756, | |
| "eval_samples_per_second": 68.341, | |
| "eval_steps_per_second": 5.695, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.09704094380140305, | |
| "eval_runtime": 0.1802, | |
| "eval_samples_per_second": 66.602, | |
| "eval_steps_per_second": 5.55, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.09492971748113632, | |
| "eval_runtime": 0.1799, | |
| "eval_samples_per_second": 66.718, | |
| "eval_steps_per_second": 5.56, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.07086266577243805, | |
| "eval_runtime": 0.1808, | |
| "eval_samples_per_second": 66.372, | |
| "eval_steps_per_second": 5.531, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.08071430027484894, | |
| "eval_runtime": 0.1867, | |
| "eval_samples_per_second": 64.263, | |
| "eval_steps_per_second": 5.355, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.10515321046113968, | |
| "eval_runtime": 0.1877, | |
| "eval_samples_per_second": 63.943, | |
| "eval_steps_per_second": 5.329, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.06287472695112228, | |
| "eval_runtime": 0.176, | |
| "eval_samples_per_second": 68.165, | |
| "eval_steps_per_second": 5.68, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.027201684191823006, | |
| "eval_runtime": 0.189, | |
| "eval_samples_per_second": 63.503, | |
| "eval_steps_per_second": 5.292, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.07752759009599686, | |
| "eval_runtime": 0.1794, | |
| "eval_samples_per_second": 66.892, | |
| "eval_steps_per_second": 5.574, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.11133003234863281, | |
| "eval_runtime": 0.1852, | |
| "eval_samples_per_second": 64.795, | |
| "eval_steps_per_second": 5.4, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "grad_norm": 2.9116437435150146, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0591, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.11887478828430176, | |
| "eval_runtime": 0.1815, | |
| "eval_samples_per_second": 66.12, | |
| "eval_steps_per_second": 5.51, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0526016540825367, | |
| "eval_runtime": 0.1779, | |
| "eval_samples_per_second": 67.464, | |
| "eval_steps_per_second": 5.622, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.026192912831902504, | |
| "eval_runtime": 0.1811, | |
| "eval_samples_per_second": 66.253, | |
| "eval_steps_per_second": 5.521, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.10351991653442383, | |
| "eval_runtime": 0.1826, | |
| "eval_samples_per_second": 65.712, | |
| "eval_steps_per_second": 5.476, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.1508234441280365, | |
| "eval_runtime": 0.1903, | |
| "eval_samples_per_second": 63.065, | |
| "eval_steps_per_second": 5.255, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.12798932194709778, | |
| "eval_runtime": 0.1781, | |
| "eval_samples_per_second": 67.382, | |
| "eval_steps_per_second": 5.615, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.06516266614198685, | |
| "eval_runtime": 0.1865, | |
| "eval_samples_per_second": 64.335, | |
| "eval_steps_per_second": 5.361, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.03566673770546913, | |
| "eval_runtime": 0.1767, | |
| "eval_samples_per_second": 67.903, | |
| "eval_steps_per_second": 5.659, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.04070502147078514, | |
| "eval_runtime": 0.1785, | |
| "eval_samples_per_second": 67.241, | |
| "eval_steps_per_second": 5.603, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.04303682968020439, | |
| "eval_runtime": 0.1828, | |
| "eval_samples_per_second": 65.641, | |
| "eval_steps_per_second": 5.47, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "grad_norm": 3.849208354949951, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0637, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.04676436260342598, | |
| "eval_runtime": 0.1745, | |
| "eval_samples_per_second": 68.757, | |
| "eval_steps_per_second": 5.73, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.09966019541025162, | |
| "eval_runtime": 0.1901, | |
| "eval_samples_per_second": 63.116, | |
| "eval_steps_per_second": 5.26, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.21995067596435547, | |
| "eval_runtime": 0.1812, | |
| "eval_samples_per_second": 66.207, | |
| "eval_steps_per_second": 5.517, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.2979114353656769, | |
| "eval_runtime": 0.1817, | |
| "eval_samples_per_second": 66.049, | |
| "eval_steps_per_second": 5.504, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.31669190526008606, | |
| "eval_runtime": 0.1788, | |
| "eval_samples_per_second": 67.1, | |
| "eval_steps_per_second": 5.592, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.2610935568809509, | |
| "eval_runtime": 0.1781, | |
| "eval_samples_per_second": 67.365, | |
| "eval_steps_per_second": 5.614, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.16972792148590088, | |
| "eval_runtime": 0.1832, | |
| "eval_samples_per_second": 65.49, | |
| "eval_steps_per_second": 5.457, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.06688845902681351, | |
| "eval_runtime": 0.182, | |
| "eval_samples_per_second": 65.951, | |
| "eval_steps_per_second": 5.496, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.03132214397192001, | |
| "eval_runtime": 0.1795, | |
| "eval_samples_per_second": 66.867, | |
| "eval_steps_per_second": 5.572, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.025468146428465843, | |
| "eval_runtime": 0.1766, | |
| "eval_samples_per_second": 67.966, | |
| "eval_steps_per_second": 5.664, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "grad_norm": 1.297845482826233, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0446, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.02426406554877758, | |
| "eval_runtime": 0.1784, | |
| "eval_samples_per_second": 67.269, | |
| "eval_steps_per_second": 5.606, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.01883484609425068, | |
| "eval_runtime": 0.1851, | |
| "eval_samples_per_second": 64.842, | |
| "eval_steps_per_second": 5.404, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.020957307890057564, | |
| "eval_runtime": 0.1781, | |
| "eval_samples_per_second": 67.372, | |
| "eval_steps_per_second": 5.614, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.026050806045532227, | |
| "eval_runtime": 0.1795, | |
| "eval_samples_per_second": 66.857, | |
| "eval_steps_per_second": 5.571, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.037800516933202744, | |
| "eval_runtime": 0.1914, | |
| "eval_samples_per_second": 62.71, | |
| "eval_steps_per_second": 5.226, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.04915888234972954, | |
| "eval_runtime": 0.1801, | |
| "eval_samples_per_second": 66.632, | |
| "eval_steps_per_second": 5.553, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.06793534010648727, | |
| "eval_runtime": 0.1788, | |
| "eval_samples_per_second": 67.109, | |
| "eval_steps_per_second": 5.592, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.09575098752975464, | |
| "eval_runtime": 0.1842, | |
| "eval_samples_per_second": 65.143, | |
| "eval_steps_per_second": 5.429, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.08034069091081619, | |
| "eval_runtime": 0.1823, | |
| "eval_samples_per_second": 65.842, | |
| "eval_steps_per_second": 5.487, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.04547484591603279, | |
| "eval_runtime": 0.187, | |
| "eval_samples_per_second": 64.181, | |
| "eval_steps_per_second": 5.348, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "grad_norm": 2.749316692352295, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0489, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.019428091123700142, | |
| "eval_runtime": 0.1818, | |
| "eval_samples_per_second": 66.004, | |
| "eval_steps_per_second": 5.5, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.01414876151829958, | |
| "eval_runtime": 0.1804, | |
| "eval_samples_per_second": 66.536, | |
| "eval_steps_per_second": 5.545, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.010926567018032074, | |
| "eval_runtime": 0.184, | |
| "eval_samples_per_second": 65.226, | |
| "eval_steps_per_second": 5.435, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.010399104095995426, | |
| "eval_runtime": 0.1795, | |
| "eval_samples_per_second": 66.842, | |
| "eval_steps_per_second": 5.57, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.010837866924703121, | |
| "eval_runtime": 0.1826, | |
| "eval_samples_per_second": 65.7, | |
| "eval_steps_per_second": 5.475, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.012089508585631847, | |
| "eval_runtime": 0.1809, | |
| "eval_samples_per_second": 66.338, | |
| "eval_steps_per_second": 5.528, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.011834497563540936, | |
| "eval_runtime": 0.1796, | |
| "eval_samples_per_second": 66.811, | |
| "eval_steps_per_second": 5.568, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.01087136659771204, | |
| "eval_runtime": 0.1832, | |
| "eval_samples_per_second": 65.487, | |
| "eval_steps_per_second": 5.457, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.010681281797587872, | |
| "eval_runtime": 0.1822, | |
| "eval_samples_per_second": 65.858, | |
| "eval_steps_per_second": 5.488, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.01070683915168047, | |
| "eval_runtime": 0.1833, | |
| "eval_samples_per_second": 65.471, | |
| "eval_steps_per_second": 5.456, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "grad_norm": 2.0978522300720215, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0322, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.010707174427807331, | |
| "eval_runtime": 0.1844, | |
| "eval_samples_per_second": 65.093, | |
| "eval_steps_per_second": 5.424, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.010700911283493042, | |
| "eval_runtime": 0.1814, | |
| "eval_samples_per_second": 66.149, | |
| "eval_steps_per_second": 5.512, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.010619781911373138, | |
| "eval_runtime": 0.1869, | |
| "eval_samples_per_second": 64.213, | |
| "eval_steps_per_second": 5.351, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.010527804493904114, | |
| "eval_runtime": 0.1824, | |
| "eval_samples_per_second": 65.774, | |
| "eval_steps_per_second": 5.481, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.01050546020269394, | |
| "eval_runtime": 0.1744, | |
| "eval_samples_per_second": 68.793, | |
| "eval_steps_per_second": 5.733, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.010545703582465649, | |
| "eval_runtime": 0.1786, | |
| "eval_samples_per_second": 67.174, | |
| "eval_steps_per_second": 5.598, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.010599258355796337, | |
| "eval_runtime": 0.1836, | |
| "eval_samples_per_second": 65.353, | |
| "eval_steps_per_second": 5.446, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.010553344152867794, | |
| "eval_runtime": 0.176, | |
| "eval_samples_per_second": 68.182, | |
| "eval_steps_per_second": 5.682, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.010620239190757275, | |
| "eval_runtime": 0.1846, | |
| "eval_samples_per_second": 65.001, | |
| "eval_steps_per_second": 5.417, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.010768108069896698, | |
| "eval_runtime": 0.179, | |
| "eval_samples_per_second": 67.058, | |
| "eval_steps_per_second": 5.588, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "grad_norm": 1.8535388708114624, | |
| "learning_rate": 0.0, | |
| "loss": 0.0405, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.010857379995286465, | |
| "eval_runtime": 0.1769, | |
| "eval_samples_per_second": 67.841, | |
| "eval_steps_per_second": 5.653, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 100, | |
| "total_flos": 4.802492916781056e+17, | |
| "train_loss": 0.11944382786750793, | |
| "train_runtime": 434.603, | |
| "train_samples_per_second": 14.266, | |
| "train_steps_per_second": 0.23 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.08116643875837326, | |
| "eval_runtime": 0.2193, | |
| "eval_samples_per_second": 54.708, | |
| "eval_steps_per_second": 4.559, | |
| "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 | |
| } | |