| { |
| "best_global_step": 1530, |
| "best_metric": 0.06136542558670044, |
| "best_model_checkpoint": "saves_multiple/ia3/llama-3-8b-instruct/train_copa_42_1760623610/checkpoint-1530", |
| "epoch": 20.0, |
| "eval_steps": 90, |
| "global_step": 1800, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05555555555555555, |
| "grad_norm": 2.2088112831115723, |
| "learning_rate": 1.1111111111111112e-06, |
| "loss": 0.4573, |
| "num_input_tokens_seen": 1600, |
| "step": 5, |
| "train_runtime": 2.9456, |
| "train_tokens_per_second": 543.175 |
| }, |
| { |
| "epoch": 0.1111111111111111, |
| "grad_norm": 4.39024019241333, |
| "learning_rate": 2.5e-06, |
| "loss": 0.5421, |
| "num_input_tokens_seen": 3200, |
| "step": 10, |
| "train_runtime": 3.6773, |
| "train_tokens_per_second": 870.196 |
| }, |
| { |
| "epoch": 0.16666666666666666, |
| "grad_norm": 3.716674327850342, |
| "learning_rate": 3.888888888888889e-06, |
| "loss": 0.6127, |
| "num_input_tokens_seen": 4768, |
| "step": 15, |
| "train_runtime": 4.4116, |
| "train_tokens_per_second": 1080.799 |
| }, |
| { |
| "epoch": 0.2222222222222222, |
| "grad_norm": 4.793196201324463, |
| "learning_rate": 5.277777777777778e-06, |
| "loss": 0.8032, |
| "num_input_tokens_seen": 6336, |
| "step": 20, |
| "train_runtime": 5.1293, |
| "train_tokens_per_second": 1235.252 |
| }, |
| { |
| "epoch": 0.2777777777777778, |
| "grad_norm": 4.469949722290039, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 0.708, |
| "num_input_tokens_seen": 7904, |
| "step": 25, |
| "train_runtime": 5.8465, |
| "train_tokens_per_second": 1351.911 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 3.813312530517578, |
| "learning_rate": 8.055555555555557e-06, |
| "loss": 0.7098, |
| "num_input_tokens_seen": 9504, |
| "step": 30, |
| "train_runtime": 6.5631, |
| "train_tokens_per_second": 1448.106 |
| }, |
| { |
| "epoch": 0.3888888888888889, |
| "grad_norm": 5.289863586425781, |
| "learning_rate": 9.444444444444445e-06, |
| "loss": 0.5975, |
| "num_input_tokens_seen": 11072, |
| "step": 35, |
| "train_runtime": 7.2773, |
| "train_tokens_per_second": 1521.439 |
| }, |
| { |
| "epoch": 0.4444444444444444, |
| "grad_norm": 5.294936656951904, |
| "learning_rate": 1.0833333333333334e-05, |
| "loss": 0.6869, |
| "num_input_tokens_seen": 12672, |
| "step": 40, |
| "train_runtime": 7.9904, |
| "train_tokens_per_second": 1585.904 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 4.334069728851318, |
| "learning_rate": 1.2222222222222222e-05, |
| "loss": 0.5514, |
| "num_input_tokens_seen": 14176, |
| "step": 45, |
| "train_runtime": 8.7025, |
| "train_tokens_per_second": 1628.959 |
| }, |
| { |
| "epoch": 0.5555555555555556, |
| "grad_norm": 3.8888776302337646, |
| "learning_rate": 1.3611111111111111e-05, |
| "loss": 0.5715, |
| "num_input_tokens_seen": 15776, |
| "step": 50, |
| "train_runtime": 9.4207, |
| "train_tokens_per_second": 1674.613 |
| }, |
| { |
| "epoch": 0.6111111111111112, |
| "grad_norm": 3.423602819442749, |
| "learning_rate": 1.5e-05, |
| "loss": 0.7156, |
| "num_input_tokens_seen": 17312, |
| "step": 55, |
| "train_runtime": 10.1344, |
| "train_tokens_per_second": 1708.236 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 5.6678619384765625, |
| "learning_rate": 1.638888888888889e-05, |
| "loss": 0.6582, |
| "num_input_tokens_seen": 18848, |
| "step": 60, |
| "train_runtime": 10.8468, |
| "train_tokens_per_second": 1737.659 |
| }, |
| { |
| "epoch": 0.7222222222222222, |
| "grad_norm": 3.3733015060424805, |
| "learning_rate": 1.777777777777778e-05, |
| "loss": 0.5932, |
| "num_input_tokens_seen": 20448, |
| "step": 65, |
| "train_runtime": 11.5622, |
| "train_tokens_per_second": 1768.529 |
| }, |
| { |
| "epoch": 0.7777777777777778, |
| "grad_norm": 5.003718852996826, |
| "learning_rate": 1.9166666666666667e-05, |
| "loss": 0.6346, |
| "num_input_tokens_seen": 22016, |
| "step": 70, |
| "train_runtime": 12.2783, |
| "train_tokens_per_second": 1793.078 |
| }, |
| { |
| "epoch": 0.8333333333333334, |
| "grad_norm": 5.266268253326416, |
| "learning_rate": 2.0555555555555555e-05, |
| "loss": 0.6911, |
| "num_input_tokens_seen": 23616, |
| "step": 75, |
| "train_runtime": 12.9932, |
| "train_tokens_per_second": 1817.571 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "grad_norm": 3.5122318267822266, |
| "learning_rate": 2.1944444444444445e-05, |
| "loss": 0.6298, |
| "num_input_tokens_seen": 25152, |
| "step": 80, |
| "train_runtime": 13.7078, |
| "train_tokens_per_second": 1834.864 |
| }, |
| { |
| "epoch": 0.9444444444444444, |
| "grad_norm": 2.586906671524048, |
| "learning_rate": 2.3333333333333336e-05, |
| "loss": 0.502, |
| "num_input_tokens_seen": 26688, |
| "step": 85, |
| "train_runtime": 14.4298, |
| "train_tokens_per_second": 1849.51 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 5.285933017730713, |
| "learning_rate": 2.4722222222222223e-05, |
| "loss": 0.6707, |
| "num_input_tokens_seen": 28256, |
| "step": 90, |
| "train_runtime": 15.1724, |
| "train_tokens_per_second": 1862.324 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.5807542204856873, |
| "eval_runtime": 0.5309, |
| "eval_samples_per_second": 75.343, |
| "eval_steps_per_second": 18.836, |
| "num_input_tokens_seen": 28256, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.0555555555555556, |
| "grad_norm": 4.274877548217773, |
| "learning_rate": 2.6111111111111114e-05, |
| "loss": 0.6538, |
| "num_input_tokens_seen": 29824, |
| "step": 95, |
| "train_runtime": 17.2747, |
| "train_tokens_per_second": 1726.451 |
| }, |
| { |
| "epoch": 1.1111111111111112, |
| "grad_norm": 4.135989665985107, |
| "learning_rate": 2.7500000000000004e-05, |
| "loss": 0.6772, |
| "num_input_tokens_seen": 31360, |
| "step": 100, |
| "train_runtime": 17.9993, |
| "train_tokens_per_second": 1742.294 |
| }, |
| { |
| "epoch": 1.1666666666666667, |
| "grad_norm": 4.4399800300598145, |
| "learning_rate": 2.8888888888888888e-05, |
| "loss": 0.6713, |
| "num_input_tokens_seen": 32960, |
| "step": 105, |
| "train_runtime": 18.7241, |
| "train_tokens_per_second": 1760.298 |
| }, |
| { |
| "epoch": 1.2222222222222223, |
| "grad_norm": 4.539364814758301, |
| "learning_rate": 3.0277777777777776e-05, |
| "loss": 0.7478, |
| "num_input_tokens_seen": 34464, |
| "step": 110, |
| "train_runtime": 19.5695, |
| "train_tokens_per_second": 1761.109 |
| }, |
| { |
| "epoch": 1.2777777777777777, |
| "grad_norm": 2.650864601135254, |
| "learning_rate": 3.1666666666666666e-05, |
| "loss": 0.4845, |
| "num_input_tokens_seen": 36032, |
| "step": 115, |
| "train_runtime": 20.2991, |
| "train_tokens_per_second": 1775.058 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 4.143145561218262, |
| "learning_rate": 3.3055555555555553e-05, |
| "loss": 0.6008, |
| "num_input_tokens_seen": 37600, |
| "step": 120, |
| "train_runtime": 21.0254, |
| "train_tokens_per_second": 1788.313 |
| }, |
| { |
| "epoch": 1.3888888888888888, |
| "grad_norm": 3.905705690383911, |
| "learning_rate": 3.444444444444445e-05, |
| "loss": 0.4756, |
| "num_input_tokens_seen": 39168, |
| "step": 125, |
| "train_runtime": 21.7597, |
| "train_tokens_per_second": 1800.026 |
| }, |
| { |
| "epoch": 1.4444444444444444, |
| "grad_norm": 2.9782958030700684, |
| "learning_rate": 3.5833333333333335e-05, |
| "loss": 0.6311, |
| "num_input_tokens_seen": 40736, |
| "step": 130, |
| "train_runtime": 22.4852, |
| "train_tokens_per_second": 1811.679 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 1.8527201414108276, |
| "learning_rate": 3.722222222222222e-05, |
| "loss": 0.3536, |
| "num_input_tokens_seen": 42240, |
| "step": 135, |
| "train_runtime": 23.2063, |
| "train_tokens_per_second": 1820.199 |
| }, |
| { |
| "epoch": 1.5555555555555556, |
| "grad_norm": 2.4050815105438232, |
| "learning_rate": 3.8611111111111116e-05, |
| "loss": 0.2908, |
| "num_input_tokens_seen": 43840, |
| "step": 140, |
| "train_runtime": 23.9311, |
| "train_tokens_per_second": 1831.925 |
| }, |
| { |
| "epoch": 1.6111111111111112, |
| "grad_norm": 4.370201110839844, |
| "learning_rate": 4e-05, |
| "loss": 0.1444, |
| "num_input_tokens_seen": 45408, |
| "step": 145, |
| "train_runtime": 24.6546, |
| "train_tokens_per_second": 1841.766 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 0.18738660216331482, |
| "learning_rate": 4.138888888888889e-05, |
| "loss": 0.1972, |
| "num_input_tokens_seen": 46976, |
| "step": 150, |
| "train_runtime": 25.3788, |
| "train_tokens_per_second": 1850.994 |
| }, |
| { |
| "epoch": 1.7222222222222223, |
| "grad_norm": 0.4951828718185425, |
| "learning_rate": 4.277777777777778e-05, |
| "loss": 0.0597, |
| "num_input_tokens_seen": 48512, |
| "step": 155, |
| "train_runtime": 26.1051, |
| "train_tokens_per_second": 1858.334 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.1515243649482727, |
| "learning_rate": 4.4166666666666665e-05, |
| "loss": 0.0147, |
| "num_input_tokens_seen": 50112, |
| "step": 160, |
| "train_runtime": 26.8225, |
| "train_tokens_per_second": 1868.284 |
| }, |
| { |
| "epoch": 1.8333333333333335, |
| "grad_norm": 0.11960956454277039, |
| "learning_rate": 4.555555555555556e-05, |
| "loss": 0.1213, |
| "num_input_tokens_seen": 51712, |
| "step": 165, |
| "train_runtime": 27.5514, |
| "train_tokens_per_second": 1876.925 |
| }, |
| { |
| "epoch": 1.8888888888888888, |
| "grad_norm": 0.05862782150506973, |
| "learning_rate": 4.6944444444444446e-05, |
| "loss": 0.2448, |
| "num_input_tokens_seen": 53280, |
| "step": 170, |
| "train_runtime": 28.2801, |
| "train_tokens_per_second": 1884.007 |
| }, |
| { |
| "epoch": 1.9444444444444444, |
| "grad_norm": 0.4216754138469696, |
| "learning_rate": 4.8333333333333334e-05, |
| "loss": 0.051, |
| "num_input_tokens_seen": 54880, |
| "step": 175, |
| "train_runtime": 29.0067, |
| "train_tokens_per_second": 1891.977 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.050075557082891464, |
| "learning_rate": 4.972222222222223e-05, |
| "loss": 0.1046, |
| "num_input_tokens_seen": 56480, |
| "step": 180, |
| "train_runtime": 29.7614, |
| "train_tokens_per_second": 1897.76 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.11521875858306885, |
| "eval_runtime": 0.5418, |
| "eval_samples_per_second": 73.822, |
| "eval_steps_per_second": 18.455, |
| "num_input_tokens_seen": 56480, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.0555555555555554, |
| "grad_norm": 0.3309241831302643, |
| "learning_rate": 4.9999247861994194e-05, |
| "loss": 0.0641, |
| "num_input_tokens_seen": 58048, |
| "step": 185, |
| "train_runtime": 31.8276, |
| "train_tokens_per_second": 1823.827 |
| }, |
| { |
| "epoch": 2.111111111111111, |
| "grad_norm": 0.06720643490552902, |
| "learning_rate": 4.9996192378909786e-05, |
| "loss": 0.0257, |
| "num_input_tokens_seen": 59584, |
| "step": 190, |
| "train_runtime": 32.5618, |
| "train_tokens_per_second": 1829.874 |
| }, |
| { |
| "epoch": 2.1666666666666665, |
| "grad_norm": 0.46070975065231323, |
| "learning_rate": 4.999078682916774e-05, |
| "loss": 0.0885, |
| "num_input_tokens_seen": 61216, |
| "step": 195, |
| "train_runtime": 33.2917, |
| "train_tokens_per_second": 1838.775 |
| }, |
| { |
| "epoch": 2.2222222222222223, |
| "grad_norm": 0.796092689037323, |
| "learning_rate": 4.998303172098155e-05, |
| "loss": 0.0881, |
| "num_input_tokens_seen": 62784, |
| "step": 200, |
| "train_runtime": 34.0299, |
| "train_tokens_per_second": 1844.965 |
| }, |
| { |
| "epoch": 2.2777777777777777, |
| "grad_norm": 0.1357884556055069, |
| "learning_rate": 4.997292778346312e-05, |
| "loss": 0.0261, |
| "num_input_tokens_seen": 64352, |
| "step": 205, |
| "train_runtime": 34.7664, |
| "train_tokens_per_second": 1850.985 |
| }, |
| { |
| "epoch": 2.3333333333333335, |
| "grad_norm": 0.033360954374074936, |
| "learning_rate": 4.996047596655418e-05, |
| "loss": 0.0676, |
| "num_input_tokens_seen": 65952, |
| "step": 210, |
| "train_runtime": 35.5584, |
| "train_tokens_per_second": 1854.75 |
| }, |
| { |
| "epoch": 2.388888888888889, |
| "grad_norm": 0.7607372403144836, |
| "learning_rate": 4.994567744093703e-05, |
| "loss": 0.1574, |
| "num_input_tokens_seen": 67552, |
| "step": 215, |
| "train_runtime": 36.2847, |
| "train_tokens_per_second": 1861.723 |
| }, |
| { |
| "epoch": 2.4444444444444446, |
| "grad_norm": 1.0921010971069336, |
| "learning_rate": 4.992853359792444e-05, |
| "loss": 0.1509, |
| "num_input_tokens_seen": 69120, |
| "step": 220, |
| "train_runtime": 37.0158, |
| "train_tokens_per_second": 1867.312 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 0.037158917635679245, |
| "learning_rate": 4.9909046049328846e-05, |
| "loss": 0.1674, |
| "num_input_tokens_seen": 70688, |
| "step": 225, |
| "train_runtime": 37.7412, |
| "train_tokens_per_second": 1872.967 |
| }, |
| { |
| "epoch": 2.5555555555555554, |
| "grad_norm": 0.04759933799505234, |
| "learning_rate": 4.988721662731083e-05, |
| "loss": 0.0838, |
| "num_input_tokens_seen": 72288, |
| "step": 230, |
| "train_runtime": 38.4649, |
| "train_tokens_per_second": 1879.323 |
| }, |
| { |
| "epoch": 2.611111111111111, |
| "grad_norm": 0.03261607512831688, |
| "learning_rate": 4.9863047384206835e-05, |
| "loss": 0.038, |
| "num_input_tokens_seen": 73856, |
| "step": 235, |
| "train_runtime": 39.1892, |
| "train_tokens_per_second": 1884.601 |
| }, |
| { |
| "epoch": 2.6666666666666665, |
| "grad_norm": 0.04402220621705055, |
| "learning_rate": 4.983654059233626e-05, |
| "loss": 0.1015, |
| "num_input_tokens_seen": 75392, |
| "step": 240, |
| "train_runtime": 39.9138, |
| "train_tokens_per_second": 1888.87 |
| }, |
| { |
| "epoch": 2.7222222222222223, |
| "grad_norm": 1.1526827812194824, |
| "learning_rate": 4.9807698743787744e-05, |
| "loss": 0.0368, |
| "num_input_tokens_seen": 76960, |
| "step": 245, |
| "train_runtime": 40.6396, |
| "train_tokens_per_second": 1893.719 |
| }, |
| { |
| "epoch": 2.7777777777777777, |
| "grad_norm": 1.0865987539291382, |
| "learning_rate": 4.9776524550184965e-05, |
| "loss": 0.1612, |
| "num_input_tokens_seen": 78496, |
| "step": 250, |
| "train_runtime": 41.368, |
| "train_tokens_per_second": 1897.507 |
| }, |
| { |
| "epoch": 2.8333333333333335, |
| "grad_norm": 0.0332452766597271, |
| "learning_rate": 4.974302094243164e-05, |
| "loss": 0.0852, |
| "num_input_tokens_seen": 80000, |
| "step": 255, |
| "train_runtime": 42.1021, |
| "train_tokens_per_second": 1900.142 |
| }, |
| { |
| "epoch": 2.888888888888889, |
| "grad_norm": 2.336534261703491, |
| "learning_rate": 4.970719107043595e-05, |
| "loss": 0.1561, |
| "num_input_tokens_seen": 81568, |
| "step": 260, |
| "train_runtime": 42.8216, |
| "train_tokens_per_second": 1904.832 |
| }, |
| { |
| "epoch": 2.9444444444444446, |
| "grad_norm": 2.321704387664795, |
| "learning_rate": 4.966903830281449e-05, |
| "loss": 0.1484, |
| "num_input_tokens_seen": 83168, |
| "step": 265, |
| "train_runtime": 43.5535, |
| "train_tokens_per_second": 1909.561 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 2.2072253227233887, |
| "learning_rate": 4.962856622657541e-05, |
| "loss": 0.218, |
| "num_input_tokens_seen": 84736, |
| "step": 270, |
| "train_runtime": 44.3017, |
| "train_tokens_per_second": 1912.705 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.09266040474176407, |
| "eval_runtime": 0.5311, |
| "eval_samples_per_second": 75.318, |
| "eval_steps_per_second": 18.829, |
| "num_input_tokens_seen": 84736, |
| "step": 270 |
| }, |
| { |
| "epoch": 3.0555555555555554, |
| "grad_norm": 0.04840150848031044, |
| "learning_rate": 4.9585778646781364e-05, |
| "loss": 0.0109, |
| "num_input_tokens_seen": 86304, |
| "step": 275, |
| "train_runtime": 46.6293, |
| "train_tokens_per_second": 1850.855 |
| }, |
| { |
| "epoch": 3.111111111111111, |
| "grad_norm": 1.0470004081726074, |
| "learning_rate": 4.9540679586191605e-05, |
| "loss": 0.1111, |
| "num_input_tokens_seen": 87904, |
| "step": 280, |
| "train_runtime": 47.3578, |
| "train_tokens_per_second": 1856.166 |
| }, |
| { |
| "epoch": 3.1666666666666665, |
| "grad_norm": 0.1631588339805603, |
| "learning_rate": 4.9493273284883854e-05, |
| "loss": 0.082, |
| "num_input_tokens_seen": 89408, |
| "step": 285, |
| "train_runtime": 48.0854, |
| "train_tokens_per_second": 1859.357 |
| }, |
| { |
| "epoch": 3.2222222222222223, |
| "grad_norm": 0.17166022956371307, |
| "learning_rate": 4.9443564199855666e-05, |
| "loss": 0.1572, |
| "num_input_tokens_seen": 91008, |
| "step": 290, |
| "train_runtime": 48.8832, |
| "train_tokens_per_second": 1861.742 |
| }, |
| { |
| "epoch": 3.2777777777777777, |
| "grad_norm": 0.2681538462638855, |
| "learning_rate": 4.939155700460536e-05, |
| "loss": 0.0726, |
| "num_input_tokens_seen": 92512, |
| "step": 295, |
| "train_runtime": 49.6117, |
| "train_tokens_per_second": 1864.72 |
| }, |
| { |
| "epoch": 3.3333333333333335, |
| "grad_norm": 0.024233149364590645, |
| "learning_rate": 4.933725658869267e-05, |
| "loss": 0.0139, |
| "num_input_tokens_seen": 94080, |
| "step": 300, |
| "train_runtime": 50.3418, |
| "train_tokens_per_second": 1868.825 |
| }, |
| { |
| "epoch": 3.388888888888889, |
| "grad_norm": 1.682276964187622, |
| "learning_rate": 4.9280668057279014e-05, |
| "loss": 0.0565, |
| "num_input_tokens_seen": 95680, |
| "step": 305, |
| "train_runtime": 51.0683, |
| "train_tokens_per_second": 1873.569 |
| }, |
| { |
| "epoch": 3.4444444444444446, |
| "grad_norm": 0.29281699657440186, |
| "learning_rate": 4.9221796730647516e-05, |
| "loss": 0.0126, |
| "num_input_tokens_seen": 97248, |
| "step": 310, |
| "train_runtime": 51.7945, |
| "train_tokens_per_second": 1877.573 |
| }, |
| { |
| "epoch": 3.5, |
| "grad_norm": 0.06379231810569763, |
| "learning_rate": 4.916064814370287e-05, |
| "loss": 0.033, |
| "num_input_tokens_seen": 98784, |
| "step": 315, |
| "train_runtime": 52.5174, |
| "train_tokens_per_second": 1880.976 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 1.4467811584472656, |
| "learning_rate": 4.9097228045450864e-05, |
| "loss": 0.1501, |
| "num_input_tokens_seen": 100384, |
| "step": 320, |
| "train_runtime": 53.2424, |
| "train_tokens_per_second": 1885.414 |
| }, |
| { |
| "epoch": 3.611111111111111, |
| "grad_norm": 0.5704734921455383, |
| "learning_rate": 4.9031542398457974e-05, |
| "loss": 0.0704, |
| "num_input_tokens_seen": 101952, |
| "step": 325, |
| "train_runtime": 53.9719, |
| "train_tokens_per_second": 1888.983 |
| }, |
| { |
| "epoch": 3.6666666666666665, |
| "grad_norm": 2.3169894218444824, |
| "learning_rate": 4.896359737829071e-05, |
| "loss": 0.1576, |
| "num_input_tokens_seen": 103520, |
| "step": 330, |
| "train_runtime": 54.6975, |
| "train_tokens_per_second": 1892.592 |
| }, |
| { |
| "epoch": 3.7222222222222223, |
| "grad_norm": 1.74516761302948, |
| "learning_rate": 4.889339937293508e-05, |
| "loss": 0.1599, |
| "num_input_tokens_seen": 105120, |
| "step": 335, |
| "train_runtime": 55.4274, |
| "train_tokens_per_second": 1896.536 |
| }, |
| { |
| "epoch": 3.7777777777777777, |
| "grad_norm": 0.154998779296875, |
| "learning_rate": 4.8820954982195905e-05, |
| "loss": 0.0478, |
| "num_input_tokens_seen": 106720, |
| "step": 340, |
| "train_runtime": 56.1522, |
| "train_tokens_per_second": 1900.55 |
| }, |
| { |
| "epoch": 3.8333333333333335, |
| "grad_norm": 1.1225404739379883, |
| "learning_rate": 4.874627101707644e-05, |
| "loss": 0.0306, |
| "num_input_tokens_seen": 108320, |
| "step": 345, |
| "train_runtime": 56.8749, |
| "train_tokens_per_second": 1904.532 |
| }, |
| { |
| "epoch": 3.888888888888889, |
| "grad_norm": 0.2039882242679596, |
| "learning_rate": 4.8669354499137955e-05, |
| "loss": 0.1915, |
| "num_input_tokens_seen": 109888, |
| "step": 350, |
| "train_runtime": 57.6027, |
| "train_tokens_per_second": 1907.689 |
| }, |
| { |
| "epoch": 3.9444444444444446, |
| "grad_norm": 0.016289830207824707, |
| "learning_rate": 4.859021265983959e-05, |
| "loss": 0.0131, |
| "num_input_tokens_seen": 111424, |
| "step": 355, |
| "train_runtime": 58.327, |
| "train_tokens_per_second": 1910.333 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.05436905845999718, |
| "learning_rate": 4.850885293985853e-05, |
| "loss": 0.1464, |
| "num_input_tokens_seen": 113024, |
| "step": 360, |
| "train_runtime": 59.0796, |
| "train_tokens_per_second": 1913.08 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.0865594819188118, |
| "eval_runtime": 0.5373, |
| "eval_samples_per_second": 74.451, |
| "eval_steps_per_second": 18.613, |
| "num_input_tokens_seen": 113024, |
| "step": 360 |
| }, |
| { |
| "epoch": 4.055555555555555, |
| "grad_norm": 0.26754438877105713, |
| "learning_rate": 4.8425282988390376e-05, |
| "loss": 0.0143, |
| "num_input_tokens_seen": 114624, |
| "step": 365, |
| "train_runtime": 61.1601, |
| "train_tokens_per_second": 1874.164 |
| }, |
| { |
| "epoch": 4.111111111111111, |
| "grad_norm": 1.4411932229995728, |
| "learning_rate": 4.8339510662430046e-05, |
| "loss": 0.0517, |
| "num_input_tokens_seen": 116224, |
| "step": 370, |
| "train_runtime": 61.8991, |
| "train_tokens_per_second": 1877.636 |
| }, |
| { |
| "epoch": 4.166666666666667, |
| "grad_norm": 0.9027936458587646, |
| "learning_rate": 4.825154402603308e-05, |
| "loss": 0.0357, |
| "num_input_tokens_seen": 117760, |
| "step": 375, |
| "train_runtime": 62.634, |
| "train_tokens_per_second": 1880.13 |
| }, |
| { |
| "epoch": 4.222222222222222, |
| "grad_norm": 0.05497714877128601, |
| "learning_rate": 4.816139134955746e-05, |
| "loss": 0.2172, |
| "num_input_tokens_seen": 119360, |
| "step": 380, |
| "train_runtime": 63.3708, |
| "train_tokens_per_second": 1883.518 |
| }, |
| { |
| "epoch": 4.277777777777778, |
| "grad_norm": 0.019861461594700813, |
| "learning_rate": 4.806906110888606e-05, |
| "loss": 0.0508, |
| "num_input_tokens_seen": 120960, |
| "step": 385, |
| "train_runtime": 64.1576, |
| "train_tokens_per_second": 1885.358 |
| }, |
| { |
| "epoch": 4.333333333333333, |
| "grad_norm": 0.0410231314599514, |
| "learning_rate": 4.797456198462979e-05, |
| "loss": 0.0525, |
| "num_input_tokens_seen": 122528, |
| "step": 390, |
| "train_runtime": 64.8796, |
| "train_tokens_per_second": 1888.545 |
| }, |
| { |
| "epoch": 4.388888888888889, |
| "grad_norm": 0.019991597160696983, |
| "learning_rate": 4.7877902861311446e-05, |
| "loss": 0.0366, |
| "num_input_tokens_seen": 124096, |
| "step": 395, |
| "train_runtime": 65.602, |
| "train_tokens_per_second": 1891.651 |
| }, |
| { |
| "epoch": 4.444444444444445, |
| "grad_norm": 0.22315886616706848, |
| "learning_rate": 4.777909282653042e-05, |
| "loss": 0.0932, |
| "num_input_tokens_seen": 125696, |
| "step": 400, |
| "train_runtime": 66.3299, |
| "train_tokens_per_second": 1895.012 |
| }, |
| { |
| "epoch": 4.5, |
| "grad_norm": 0.017999814823269844, |
| "learning_rate": 4.7678141170108345e-05, |
| "loss": 0.0129, |
| "num_input_tokens_seen": 127264, |
| "step": 405, |
| "train_runtime": 67.0642, |
| "train_tokens_per_second": 1897.644 |
| }, |
| { |
| "epoch": 4.555555555555555, |
| "grad_norm": 0.014455858618021011, |
| "learning_rate": 4.757505738321563e-05, |
| "loss": 0.0619, |
| "num_input_tokens_seen": 128832, |
| "step": 410, |
| "train_runtime": 67.8, |
| "train_tokens_per_second": 1900.178 |
| }, |
| { |
| "epoch": 4.611111111111111, |
| "grad_norm": 1.1234349012374878, |
| "learning_rate": 4.7469851157479177e-05, |
| "loss": 0.0666, |
| "num_input_tokens_seen": 130464, |
| "step": 415, |
| "train_runtime": 68.5354, |
| "train_tokens_per_second": 1903.6 |
| }, |
| { |
| "epoch": 4.666666666666667, |
| "grad_norm": 0.1306644231081009, |
| "learning_rate": 4.736253238407119e-05, |
| "loss": 0.021, |
| "num_input_tokens_seen": 132032, |
| "step": 420, |
| "train_runtime": 69.2654, |
| "train_tokens_per_second": 1906.174 |
| }, |
| { |
| "epoch": 4.722222222222222, |
| "grad_norm": 2.1763293743133545, |
| "learning_rate": 4.725311115277924e-05, |
| "loss": 0.124, |
| "num_input_tokens_seen": 133632, |
| "step": 425, |
| "train_runtime": 69.9934, |
| "train_tokens_per_second": 1909.21 |
| }, |
| { |
| "epoch": 4.777777777777778, |
| "grad_norm": 0.031760722398757935, |
| "learning_rate": 4.714159775105765e-05, |
| "loss": 0.0831, |
| "num_input_tokens_seen": 135232, |
| "step": 430, |
| "train_runtime": 70.7244, |
| "train_tokens_per_second": 1912.098 |
| }, |
| { |
| "epoch": 4.833333333333333, |
| "grad_norm": 0.8396589756011963, |
| "learning_rate": 4.70280026630603e-05, |
| "loss": 0.0929, |
| "num_input_tokens_seen": 136768, |
| "step": 435, |
| "train_runtime": 71.4563, |
| "train_tokens_per_second": 1914.009 |
| }, |
| { |
| "epoch": 4.888888888888889, |
| "grad_norm": 0.8139696717262268, |
| "learning_rate": 4.6912336568654925e-05, |
| "loss": 0.0923, |
| "num_input_tokens_seen": 138368, |
| "step": 440, |
| "train_runtime": 72.1877, |
| "train_tokens_per_second": 1916.78 |
| }, |
| { |
| "epoch": 4.944444444444445, |
| "grad_norm": 0.037018146365880966, |
| "learning_rate": 4.679461034241906e-05, |
| "loss": 0.0602, |
| "num_input_tokens_seen": 139904, |
| "step": 445, |
| "train_runtime": 72.9133, |
| "train_tokens_per_second": 1918.772 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.5598136186599731, |
| "learning_rate": 4.667483505261762e-05, |
| "loss": 0.1828, |
| "num_input_tokens_seen": 141440, |
| "step": 450, |
| "train_runtime": 73.6811, |
| "train_tokens_per_second": 1919.625 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.08515938371419907, |
| "eval_runtime": 0.5401, |
| "eval_samples_per_second": 74.06, |
| "eval_steps_per_second": 18.515, |
| "num_input_tokens_seen": 141440, |
| "step": 450 |
| }, |
| { |
| "epoch": 5.055555555555555, |
| "grad_norm": 0.03553323820233345, |
| "learning_rate": 4.655302196016228e-05, |
| "loss": 0.0195, |
| "num_input_tokens_seen": 142976, |
| "step": 455, |
| "train_runtime": 75.8668, |
| "train_tokens_per_second": 1884.567 |
| }, |
| { |
| "epoch": 5.111111111111111, |
| "grad_norm": 0.38880011439323425, |
| "learning_rate": 4.642918251755281e-05, |
| "loss": 0.0529, |
| "num_input_tokens_seen": 144576, |
| "step": 460, |
| "train_runtime": 76.5962, |
| "train_tokens_per_second": 1887.508 |
| }, |
| { |
| "epoch": 5.166666666666667, |
| "grad_norm": 1.82427179813385, |
| "learning_rate": 4.6303328367800284e-05, |
| "loss": 0.0852, |
| "num_input_tokens_seen": 146144, |
| "step": 465, |
| "train_runtime": 77.3337, |
| "train_tokens_per_second": 1889.783 |
| }, |
| { |
| "epoch": 5.222222222222222, |
| "grad_norm": 0.13176696002483368, |
| "learning_rate": 4.6175471343332485e-05, |
| "loss": 0.029, |
| "num_input_tokens_seen": 147712, |
| "step": 470, |
| "train_runtime": 78.0599, |
| "train_tokens_per_second": 1892.29 |
| }, |
| { |
| "epoch": 5.277777777777778, |
| "grad_norm": 0.042600348591804504, |
| "learning_rate": 4.604562346488144e-05, |
| "loss": 0.016, |
| "num_input_tokens_seen": 149248, |
| "step": 475, |
| "train_runtime": 78.8528, |
| "train_tokens_per_second": 1892.743 |
| }, |
| { |
| "epoch": 5.333333333333333, |
| "grad_norm": 0.2647045850753784, |
| "learning_rate": 4.591379694035325e-05, |
| "loss": 0.0317, |
| "num_input_tokens_seen": 150816, |
| "step": 480, |
| "train_runtime": 79.5814, |
| "train_tokens_per_second": 1895.117 |
| }, |
| { |
| "epoch": 5.388888888888889, |
| "grad_norm": 0.010275711305439472, |
| "learning_rate": 4.5780004163680365e-05, |
| "loss": 0.0623, |
| "num_input_tokens_seen": 152352, |
| "step": 485, |
| "train_runtime": 80.307, |
| "train_tokens_per_second": 1897.119 |
| }, |
| { |
| "epoch": 5.444444444444445, |
| "grad_norm": 0.01466486044228077, |
| "learning_rate": 4.5644257713656356e-05, |
| "loss": 0.0467, |
| "num_input_tokens_seen": 153888, |
| "step": 490, |
| "train_runtime": 81.0311, |
| "train_tokens_per_second": 1899.123 |
| }, |
| { |
| "epoch": 5.5, |
| "grad_norm": 0.2574822008609772, |
| "learning_rate": 4.550657035275323e-05, |
| "loss": 0.0727, |
| "num_input_tokens_seen": 155488, |
| "step": 495, |
| "train_runtime": 81.7508, |
| "train_tokens_per_second": 1901.976 |
| }, |
| { |
| "epoch": 5.555555555555555, |
| "grad_norm": 1.9353536367416382, |
| "learning_rate": 4.536695502592162e-05, |
| "loss": 0.1666, |
| "num_input_tokens_seen": 157024, |
| "step": 500, |
| "train_runtime": 82.479, |
| "train_tokens_per_second": 1903.805 |
| }, |
| { |
| "epoch": 5.611111111111111, |
| "grad_norm": 0.1050436869263649, |
| "learning_rate": 4.522542485937369e-05, |
| "loss": 0.0724, |
| "num_input_tokens_seen": 158528, |
| "step": 505, |
| "train_runtime": 83.2079, |
| "train_tokens_per_second": 1905.205 |
| }, |
| { |
| "epoch": 5.666666666666667, |
| "grad_norm": 0.029432374984025955, |
| "learning_rate": 4.5081993159349056e-05, |
| "loss": 0.1272, |
| "num_input_tokens_seen": 160064, |
| "step": 510, |
| "train_runtime": 83.935, |
| "train_tokens_per_second": 1906.999 |
| }, |
| { |
| "epoch": 5.722222222222222, |
| "grad_norm": 0.026064742356538773, |
| "learning_rate": 4.493667341086379e-05, |
| "loss": 0.1286, |
| "num_input_tokens_seen": 161664, |
| "step": 515, |
| "train_runtime": 84.6515, |
| "train_tokens_per_second": 1909.758 |
| }, |
| { |
| "epoch": 5.777777777777778, |
| "grad_norm": 0.04574081301689148, |
| "learning_rate": 4.478947927644258e-05, |
| "loss": 0.1791, |
| "num_input_tokens_seen": 163264, |
| "step": 520, |
| "train_runtime": 85.3662, |
| "train_tokens_per_second": 1912.513 |
| }, |
| { |
| "epoch": 5.833333333333333, |
| "grad_norm": 0.4281242787837982, |
| "learning_rate": 4.464042459483425e-05, |
| "loss": 0.0292, |
| "num_input_tokens_seen": 164864, |
| "step": 525, |
| "train_runtime": 86.0827, |
| "train_tokens_per_second": 1915.182 |
| }, |
| { |
| "epoch": 5.888888888888889, |
| "grad_norm": 0.1832948625087738, |
| "learning_rate": 4.448952337971064e-05, |
| "loss": 0.0392, |
| "num_input_tokens_seen": 166432, |
| "step": 530, |
| "train_runtime": 86.8048, |
| "train_tokens_per_second": 1917.314 |
| }, |
| { |
| "epoch": 5.944444444444445, |
| "grad_norm": 0.8455609083175659, |
| "learning_rate": 4.43367898183491e-05, |
| "loss": 0.0844, |
| "num_input_tokens_seen": 168032, |
| "step": 535, |
| "train_runtime": 87.5225, |
| "train_tokens_per_second": 1919.871 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.29642245173454285, |
| "learning_rate": 4.418223827029867e-05, |
| "loss": 0.0243, |
| "num_input_tokens_seen": 169600, |
| "step": 540, |
| "train_runtime": 88.2761, |
| "train_tokens_per_second": 1921.246 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.0781724601984024, |
| "eval_runtime": 0.534, |
| "eval_samples_per_second": 74.912, |
| "eval_steps_per_second": 18.728, |
| "num_input_tokens_seen": 169600, |
| "step": 540 |
| }, |
| { |
| "epoch": 6.055555555555555, |
| "grad_norm": 0.04110460728406906, |
| "learning_rate": 4.402588326603002e-05, |
| "loss": 0.0079, |
| "num_input_tokens_seen": 171168, |
| "step": 545, |
| "train_runtime": 90.4103, |
| "train_tokens_per_second": 1893.235 |
| }, |
| { |
| "epoch": 6.111111111111111, |
| "grad_norm": 0.7516536116600037, |
| "learning_rate": 4.386773950556931e-05, |
| "loss": 0.0233, |
| "num_input_tokens_seen": 172672, |
| "step": 550, |
| "train_runtime": 91.138, |
| "train_tokens_per_second": 1894.62 |
| }, |
| { |
| "epoch": 6.166666666666667, |
| "grad_norm": 0.054245639592409134, |
| "learning_rate": 4.3707821857116176e-05, |
| "loss": 0.0854, |
| "num_input_tokens_seen": 174240, |
| "step": 555, |
| "train_runtime": 91.8687, |
| "train_tokens_per_second": 1896.619 |
| }, |
| { |
| "epoch": 6.222222222222222, |
| "grad_norm": 0.02101464383304119, |
| "learning_rate": 4.354614535564588e-05, |
| "loss": 0.1191, |
| "num_input_tokens_seen": 175776, |
| "step": 560, |
| "train_runtime": 92.5926, |
| "train_tokens_per_second": 1898.381 |
| }, |
| { |
| "epoch": 6.277777777777778, |
| "grad_norm": 0.41236135363578796, |
| "learning_rate": 4.3382725201495723e-05, |
| "loss": 0.0971, |
| "num_input_tokens_seen": 177376, |
| "step": 565, |
| "train_runtime": 93.3832, |
| "train_tokens_per_second": 1899.442 |
| }, |
| { |
| "epoch": 6.333333333333333, |
| "grad_norm": 0.45961734652519226, |
| "learning_rate": 4.321757675893596e-05, |
| "loss": 0.0352, |
| "num_input_tokens_seen": 178912, |
| "step": 570, |
| "train_runtime": 94.1059, |
| "train_tokens_per_second": 1901.177 |
| }, |
| { |
| "epoch": 6.388888888888889, |
| "grad_norm": 0.3838369846343994, |
| "learning_rate": 4.305071555472534e-05, |
| "loss": 0.0241, |
| "num_input_tokens_seen": 180480, |
| "step": 575, |
| "train_runtime": 94.8324, |
| "train_tokens_per_second": 1903.147 |
| }, |
| { |
| "epoch": 6.444444444444445, |
| "grad_norm": 1.6661782264709473, |
| "learning_rate": 4.288215727665129e-05, |
| "loss": 0.2398, |
| "num_input_tokens_seen": 182048, |
| "step": 580, |
| "train_runtime": 95.5571, |
| "train_tokens_per_second": 1905.123 |
| }, |
| { |
| "epoch": 6.5, |
| "grad_norm": 0.010891405865550041, |
| "learning_rate": 4.2711917772055e-05, |
| "loss": 0.0831, |
| "num_input_tokens_seen": 183648, |
| "step": 585, |
| "train_runtime": 96.272, |
| "train_tokens_per_second": 1907.595 |
| }, |
| { |
| "epoch": 6.555555555555555, |
| "grad_norm": 1.7999361753463745, |
| "learning_rate": 4.254001304634151e-05, |
| "loss": 0.1064, |
| "num_input_tokens_seen": 185248, |
| "step": 590, |
| "train_runtime": 96.9909, |
| "train_tokens_per_second": 1909.952 |
| }, |
| { |
| "epoch": 6.611111111111111, |
| "grad_norm": 0.1158963292837143, |
| "learning_rate": 4.2366459261474933e-05, |
| "loss": 0.0343, |
| "num_input_tokens_seen": 186720, |
| "step": 595, |
| "train_runtime": 97.7079, |
| "train_tokens_per_second": 1911.002 |
| }, |
| { |
| "epoch": 6.666666666666667, |
| "grad_norm": 0.14980565011501312, |
| "learning_rate": 4.2191272734458955e-05, |
| "loss": 0.0058, |
| "num_input_tokens_seen": 188288, |
| "step": 600, |
| "train_runtime": 98.425, |
| "train_tokens_per_second": 1913.01 |
| }, |
| { |
| "epoch": 6.722222222222222, |
| "grad_norm": 0.031336456537246704, |
| "learning_rate": 4.201446993580276e-05, |
| "loss": 0.0557, |
| "num_input_tokens_seen": 189888, |
| "step": 605, |
| "train_runtime": 99.1477, |
| "train_tokens_per_second": 1915.202 |
| }, |
| { |
| "epoch": 6.777777777777778, |
| "grad_norm": 0.10014252364635468, |
| "learning_rate": 4.183606748797251e-05, |
| "loss": 0.0224, |
| "num_input_tokens_seen": 191424, |
| "step": 610, |
| "train_runtime": 99.8674, |
| "train_tokens_per_second": 1916.782 |
| }, |
| { |
| "epoch": 6.833333333333333, |
| "grad_norm": 0.02181674912571907, |
| "learning_rate": 4.1656082163828566e-05, |
| "loss": 0.0818, |
| "num_input_tokens_seen": 193056, |
| "step": 615, |
| "train_runtime": 100.5921, |
| "train_tokens_per_second": 1919.196 |
| }, |
| { |
| "epoch": 6.888888888888889, |
| "grad_norm": 0.392986536026001, |
| "learning_rate": 4.147453088504854e-05, |
| "loss": 0.0517, |
| "num_input_tokens_seen": 194592, |
| "step": 620, |
| "train_runtime": 101.3102, |
| "train_tokens_per_second": 1920.754 |
| }, |
| { |
| "epoch": 6.944444444444445, |
| "grad_norm": 1.3498486280441284, |
| "learning_rate": 4.129143072053638e-05, |
| "loss": 0.0833, |
| "num_input_tokens_seen": 196192, |
| "step": 625, |
| "train_runtime": 102.0313, |
| "train_tokens_per_second": 1922.862 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 0.016840647906064987, |
| "learning_rate": 4.110679888481763e-05, |
| "loss": 0.0427, |
| "num_input_tokens_seen": 197792, |
| "step": 630, |
| "train_runtime": 102.7824, |
| "train_tokens_per_second": 1924.376 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.07322361320257187, |
| "eval_runtime": 0.5374, |
| "eval_samples_per_second": 74.436, |
| "eval_steps_per_second": 18.609, |
| "num_input_tokens_seen": 197792, |
| "step": 630 |
| }, |
| { |
| "epoch": 7.055555555555555, |
| "grad_norm": 0.7116149663925171, |
| "learning_rate": 4.09206527364209e-05, |
| "loss": 0.0141, |
| "num_input_tokens_seen": 199392, |
| "step": 635, |
| "train_runtime": 106.2986, |
| "train_tokens_per_second": 1875.773 |
| }, |
| { |
| "epoch": 7.111111111111111, |
| "grad_norm": 0.010340097360312939, |
| "learning_rate": 4.073300977624594e-05, |
| "loss": 0.0111, |
| "num_input_tokens_seen": 200992, |
| "step": 640, |
| "train_runtime": 107.0352, |
| "train_tokens_per_second": 1877.811 |
| }, |
| { |
| "epoch": 7.166666666666667, |
| "grad_norm": 1.3066519498825073, |
| "learning_rate": 4.054388764591822e-05, |
| "loss": 0.0636, |
| "num_input_tokens_seen": 202592, |
| "step": 645, |
| "train_runtime": 107.763, |
| "train_tokens_per_second": 1879.977 |
| }, |
| { |
| "epoch": 7.222222222222222, |
| "grad_norm": 0.02088622748851776, |
| "learning_rate": 4.035330412613035e-05, |
| "loss": 0.0997, |
| "num_input_tokens_seen": 204064, |
| "step": 650, |
| "train_runtime": 108.496, |
| "train_tokens_per_second": 1880.843 |
| }, |
| { |
| "epoch": 7.277777777777778, |
| "grad_norm": 0.028347406536340714, |
| "learning_rate": 4.0161277134970345e-05, |
| "loss": 0.0063, |
| "num_input_tokens_seen": 205664, |
| "step": 655, |
| "train_runtime": 109.2906, |
| "train_tokens_per_second": 1881.809 |
| }, |
| { |
| "epoch": 7.333333333333333, |
| "grad_norm": 0.39772096276283264, |
| "learning_rate": 3.996782472623705e-05, |
| "loss": 0.1851, |
| "num_input_tokens_seen": 207264, |
| "step": 660, |
| "train_runtime": 110.0122, |
| "train_tokens_per_second": 1884.01 |
| }, |
| { |
| "epoch": 7.388888888888889, |
| "grad_norm": 0.7303412556648254, |
| "learning_rate": 3.977296508774278e-05, |
| "loss": 0.0443, |
| "num_input_tokens_seen": 208832, |
| "step": 665, |
| "train_runtime": 110.7332, |
| "train_tokens_per_second": 1885.902 |
| }, |
| { |
| "epoch": 7.444444444444445, |
| "grad_norm": 1.5940624475479126, |
| "learning_rate": 3.957671653960337e-05, |
| "loss": 0.1003, |
| "num_input_tokens_seen": 210368, |
| "step": 670, |
| "train_runtime": 111.4506, |
| "train_tokens_per_second": 1887.545 |
| }, |
| { |
| "epoch": 7.5, |
| "grad_norm": 0.5533637404441833, |
| "learning_rate": 3.9379097532515725e-05, |
| "loss": 0.0987, |
| "num_input_tokens_seen": 211936, |
| "step": 675, |
| "train_runtime": 112.1701, |
| "train_tokens_per_second": 1889.417 |
| }, |
| { |
| "epoch": 7.555555555555555, |
| "grad_norm": 0.022317882627248764, |
| "learning_rate": 3.918012664602317e-05, |
| "loss": 0.0593, |
| "num_input_tokens_seen": 213536, |
| "step": 680, |
| "train_runtime": 112.8872, |
| "train_tokens_per_second": 1891.587 |
| }, |
| { |
| "epoch": 7.611111111111111, |
| "grad_norm": 0.3806142210960388, |
| "learning_rate": 3.897982258676867e-05, |
| "loss": 0.0728, |
| "num_input_tokens_seen": 215136, |
| "step": 685, |
| "train_runtime": 113.6042, |
| "train_tokens_per_second": 1893.732 |
| }, |
| { |
| "epoch": 7.666666666666667, |
| "grad_norm": 1.6564552783966064, |
| "learning_rate": 3.8778204186736076e-05, |
| "loss": 0.1161, |
| "num_input_tokens_seen": 216736, |
| "step": 690, |
| "train_runtime": 114.3211, |
| "train_tokens_per_second": 1895.853 |
| }, |
| { |
| "epoch": 7.722222222222222, |
| "grad_norm": 0.03356202319264412, |
| "learning_rate": 3.8575290401479586e-05, |
| "loss": 0.0112, |
| "num_input_tokens_seen": 218272, |
| "step": 695, |
| "train_runtime": 115.0384, |
| "train_tokens_per_second": 1897.384 |
| }, |
| { |
| "epoch": 7.777777777777778, |
| "grad_norm": 0.5456864237785339, |
| "learning_rate": 3.837110030834161e-05, |
| "loss": 0.0608, |
| "num_input_tokens_seen": 219808, |
| "step": 700, |
| "train_runtime": 115.752, |
| "train_tokens_per_second": 1898.956 |
| }, |
| { |
| "epoch": 7.833333333333333, |
| "grad_norm": 0.02318716049194336, |
| "learning_rate": 3.8165653104659185e-05, |
| "loss": 0.0097, |
| "num_input_tokens_seen": 221312, |
| "step": 705, |
| "train_runtime": 116.4694, |
| "train_tokens_per_second": 1900.173 |
| }, |
| { |
| "epoch": 7.888888888888889, |
| "grad_norm": 0.13537460565567017, |
| "learning_rate": 3.79589681059591e-05, |
| "loss": 0.0481, |
| "num_input_tokens_seen": 222880, |
| "step": 710, |
| "train_runtime": 117.1878, |
| "train_tokens_per_second": 1901.905 |
| }, |
| { |
| "epoch": 7.944444444444445, |
| "grad_norm": 0.28246793150901794, |
| "learning_rate": 3.775106474414188e-05, |
| "loss": 0.0856, |
| "num_input_tokens_seen": 224416, |
| "step": 715, |
| "train_runtime": 117.9062, |
| "train_tokens_per_second": 1903.343 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.4781140387058258, |
| "learning_rate": 3.75419625656549e-05, |
| "loss": 0.018, |
| "num_input_tokens_seen": 225984, |
| "step": 720, |
| "train_runtime": 118.6553, |
| "train_tokens_per_second": 1904.542 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.07187919318675995, |
| "eval_runtime": 0.5325, |
| "eval_samples_per_second": 75.117, |
| "eval_steps_per_second": 18.779, |
| "num_input_tokens_seen": 225984, |
| "step": 720 |
| }, |
| { |
| "epoch": 8.055555555555555, |
| "grad_norm": 0.024942545220255852, |
| "learning_rate": 3.7331681229654635e-05, |
| "loss": 0.0101, |
| "num_input_tokens_seen": 227552, |
| "step": 725, |
| "train_runtime": 120.7421, |
| "train_tokens_per_second": 1884.612 |
| }, |
| { |
| "epoch": 8.11111111111111, |
| "grad_norm": 0.10381424427032471, |
| "learning_rate": 3.712024050615843e-05, |
| "loss": 0.0972, |
| "num_input_tokens_seen": 229088, |
| "step": 730, |
| "train_runtime": 121.4789, |
| "train_tokens_per_second": 1885.826 |
| }, |
| { |
| "epoch": 8.166666666666666, |
| "grad_norm": 0.13342487812042236, |
| "learning_rate": 3.690766027418573e-05, |
| "loss": 0.0919, |
| "num_input_tokens_seen": 230656, |
| "step": 735, |
| "train_runtime": 122.2116, |
| "train_tokens_per_second": 1887.349 |
| }, |
| { |
| "epoch": 8.222222222222221, |
| "grad_norm": 0.3371022343635559, |
| "learning_rate": 3.6693960519889106e-05, |
| "loss": 0.0366, |
| "num_input_tokens_seen": 232224, |
| "step": 740, |
| "train_runtime": 122.9443, |
| "train_tokens_per_second": 1888.855 |
| }, |
| { |
| "epoch": 8.277777777777779, |
| "grad_norm": 0.0277867391705513, |
| "learning_rate": 3.6479161334675296e-05, |
| "loss": 0.0324, |
| "num_input_tokens_seen": 233792, |
| "step": 745, |
| "train_runtime": 123.6753, |
| "train_tokens_per_second": 1890.369 |
| }, |
| { |
| "epoch": 8.333333333333334, |
| "grad_norm": 0.24517586827278137, |
| "learning_rate": 3.626328291331618e-05, |
| "loss": 0.1219, |
| "num_input_tokens_seen": 235328, |
| "step": 750, |
| "train_runtime": 124.4739, |
| "train_tokens_per_second": 1890.582 |
| }, |
| { |
| "epoch": 8.38888888888889, |
| "grad_norm": 0.1492447555065155, |
| "learning_rate": 3.60463455520502e-05, |
| "loss": 0.0053, |
| "num_input_tokens_seen": 236864, |
| "step": 755, |
| "train_runtime": 125.2052, |
| "train_tokens_per_second": 1891.806 |
| }, |
| { |
| "epoch": 8.444444444444445, |
| "grad_norm": 0.2043927162885666, |
| "learning_rate": 3.582836964667408e-05, |
| "loss": 0.0213, |
| "num_input_tokens_seen": 238368, |
| "step": 760, |
| "train_runtime": 125.9297, |
| "train_tokens_per_second": 1892.865 |
| }, |
| { |
| "epoch": 8.5, |
| "grad_norm": 1.6784281730651855, |
| "learning_rate": 3.560937569062538e-05, |
| "loss": 0.0844, |
| "num_input_tokens_seen": 239936, |
| "step": 765, |
| "train_runtime": 126.6543, |
| "train_tokens_per_second": 1894.416 |
| }, |
| { |
| "epoch": 8.555555555555555, |
| "grad_norm": 0.9631844758987427, |
| "learning_rate": 3.538938427305573e-05, |
| "loss": 0.056, |
| "num_input_tokens_seen": 241536, |
| "step": 770, |
| "train_runtime": 127.3734, |
| "train_tokens_per_second": 1896.282 |
| }, |
| { |
| "epoch": 8.61111111111111, |
| "grad_norm": 1.8858811855316162, |
| "learning_rate": 3.516841607689501e-05, |
| "loss": 0.1102, |
| "num_input_tokens_seen": 243136, |
| "step": 775, |
| "train_runtime": 128.0932, |
| "train_tokens_per_second": 1898.118 |
| }, |
| { |
| "epoch": 8.666666666666666, |
| "grad_norm": 0.04732911288738251, |
| "learning_rate": 3.494649187690695e-05, |
| "loss": 0.0402, |
| "num_input_tokens_seen": 244704, |
| "step": 780, |
| "train_runtime": 128.81, |
| "train_tokens_per_second": 1899.728 |
| }, |
| { |
| "epoch": 8.722222222222221, |
| "grad_norm": 0.5676568150520325, |
| "learning_rate": 3.4723632537735846e-05, |
| "loss": 0.05, |
| "num_input_tokens_seen": 246272, |
| "step": 785, |
| "train_runtime": 129.5253, |
| "train_tokens_per_second": 1901.342 |
| }, |
| { |
| "epoch": 8.777777777777779, |
| "grad_norm": 0.014905107207596302, |
| "learning_rate": 3.449985901194498e-05, |
| "loss": 0.0379, |
| "num_input_tokens_seen": 247808, |
| "step": 790, |
| "train_runtime": 130.2469, |
| "train_tokens_per_second": 1902.603 |
| }, |
| { |
| "epoch": 8.833333333333334, |
| "grad_norm": 0.23896387219429016, |
| "learning_rate": 3.427519233804667e-05, |
| "loss": 0.0577, |
| "num_input_tokens_seen": 249376, |
| "step": 795, |
| "train_runtime": 130.965, |
| "train_tokens_per_second": 1904.142 |
| }, |
| { |
| "epoch": 8.88888888888889, |
| "grad_norm": 0.4831705689430237, |
| "learning_rate": 3.404965363852437e-05, |
| "loss": 0.0611, |
| "num_input_tokens_seen": 250944, |
| "step": 800, |
| "train_runtime": 131.6819, |
| "train_tokens_per_second": 1905.683 |
| }, |
| { |
| "epoch": 8.944444444444445, |
| "grad_norm": 0.32540127635002136, |
| "learning_rate": 3.382326411784672e-05, |
| "loss": 0.0375, |
| "num_input_tokens_seen": 252512, |
| "step": 805, |
| "train_runtime": 132.3995, |
| "train_tokens_per_second": 1907.198 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 0.10771387815475464, |
| "learning_rate": 3.359604506047403e-05, |
| "loss": 0.0989, |
| "num_input_tokens_seen": 254112, |
| "step": 810, |
| "train_runtime": 133.15, |
| "train_tokens_per_second": 1908.465 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.07317575812339783, |
| "eval_runtime": 0.554, |
| "eval_samples_per_second": 72.204, |
| "eval_steps_per_second": 18.051, |
| "num_input_tokens_seen": 254112, |
| "step": 810 |
| }, |
| { |
| "epoch": 9.055555555555555, |
| "grad_norm": 0.1082310676574707, |
| "learning_rate": 3.336801782885712e-05, |
| "loss": 0.0755, |
| "num_input_tokens_seen": 255680, |
| "step": 815, |
| "train_runtime": 135.2209, |
| "train_tokens_per_second": 1890.832 |
| }, |
| { |
| "epoch": 9.11111111111111, |
| "grad_norm": 0.40736010670661926, |
| "learning_rate": 3.313920386142892e-05, |
| "loss": 0.0437, |
| "num_input_tokens_seen": 257216, |
| "step": 820, |
| "train_runtime": 135.9533, |
| "train_tokens_per_second": 1891.943 |
| }, |
| { |
| "epoch": 9.166666666666666, |
| "grad_norm": 0.014512820169329643, |
| "learning_rate": 3.290962467058891e-05, |
| "loss": 0.0275, |
| "num_input_tokens_seen": 258816, |
| "step": 825, |
| "train_runtime": 136.6805, |
| "train_tokens_per_second": 1893.584 |
| }, |
| { |
| "epoch": 9.222222222222221, |
| "grad_norm": 0.8402073383331299, |
| "learning_rate": 3.267930184068057e-05, |
| "loss": 0.1428, |
| "num_input_tokens_seen": 260384, |
| "step": 830, |
| "train_runtime": 137.4096, |
| "train_tokens_per_second": 1894.948 |
| }, |
| { |
| "epoch": 9.277777777777779, |
| "grad_norm": 0.2935343086719513, |
| "learning_rate": 3.244825702596205e-05, |
| "loss": 0.0559, |
| "num_input_tokens_seen": 262048, |
| "step": 835, |
| "train_runtime": 138.1989, |
| "train_tokens_per_second": 1896.166 |
| }, |
| { |
| "epoch": 9.333333333333334, |
| "grad_norm": 0.3444117605686188, |
| "learning_rate": 3.2216511948570374e-05, |
| "loss": 0.0122, |
| "num_input_tokens_seen": 263616, |
| "step": 840, |
| "train_runtime": 138.9225, |
| "train_tokens_per_second": 1897.577 |
| }, |
| { |
| "epoch": 9.38888888888889, |
| "grad_norm": 0.539638340473175, |
| "learning_rate": 3.198408839647911e-05, |
| "loss": 0.0114, |
| "num_input_tokens_seen": 265152, |
| "step": 845, |
| "train_runtime": 139.6464, |
| "train_tokens_per_second": 1898.739 |
| }, |
| { |
| "epoch": 9.444444444444445, |
| "grad_norm": 0.12687230110168457, |
| "learning_rate": 3.1751008221450025e-05, |
| "loss": 0.0371, |
| "num_input_tokens_seen": 266688, |
| "step": 850, |
| "train_runtime": 140.3648, |
| "train_tokens_per_second": 1899.963 |
| }, |
| { |
| "epoch": 9.5, |
| "grad_norm": 0.21428878605365753, |
| "learning_rate": 3.151729333697854e-05, |
| "loss": 0.0334, |
| "num_input_tokens_seen": 268256, |
| "step": 855, |
| "train_runtime": 141.0832, |
| "train_tokens_per_second": 1901.403 |
| }, |
| { |
| "epoch": 9.555555555555555, |
| "grad_norm": 0.2163764238357544, |
| "learning_rate": 3.1282965716233594e-05, |
| "loss": 0.0095, |
| "num_input_tokens_seen": 269824, |
| "step": 860, |
| "train_runtime": 141.8029, |
| "train_tokens_per_second": 1902.811 |
| }, |
| { |
| "epoch": 9.61111111111111, |
| "grad_norm": 1.6254862546920776, |
| "learning_rate": 3.104804738999169e-05, |
| "loss": 0.1594, |
| "num_input_tokens_seen": 271424, |
| "step": 865, |
| "train_runtime": 142.5204, |
| "train_tokens_per_second": 1904.458 |
| }, |
| { |
| "epoch": 9.666666666666666, |
| "grad_norm": 0.29750144481658936, |
| "learning_rate": 3.0812560444565745e-05, |
| "loss": 0.0159, |
| "num_input_tokens_seen": 272960, |
| "step": 870, |
| "train_runtime": 143.2426, |
| "train_tokens_per_second": 1905.578 |
| }, |
| { |
| "epoch": 9.722222222222221, |
| "grad_norm": 0.03307567536830902, |
| "learning_rate": 3.057652701972848e-05, |
| "loss": 0.0186, |
| "num_input_tokens_seen": 274528, |
| "step": 875, |
| "train_runtime": 143.9668, |
| "train_tokens_per_second": 1906.885 |
| }, |
| { |
| "epoch": 9.777777777777779, |
| "grad_norm": 0.3856286406517029, |
| "learning_rate": 3.0339969306631005e-05, |
| "loss": 0.079, |
| "num_input_tokens_seen": 276128, |
| "step": 880, |
| "train_runtime": 144.6918, |
| "train_tokens_per_second": 1908.387 |
| }, |
| { |
| "epoch": 9.833333333333334, |
| "grad_norm": 0.039159130305051804, |
| "learning_rate": 3.0102909545716396e-05, |
| "loss": 0.0675, |
| "num_input_tokens_seen": 277664, |
| "step": 885, |
| "train_runtime": 145.4169, |
| "train_tokens_per_second": 1909.434 |
| }, |
| { |
| "epoch": 9.88888888888889, |
| "grad_norm": 0.31276217103004456, |
| "learning_rate": 2.9865370024628775e-05, |
| "loss": 0.0866, |
| "num_input_tokens_seen": 279232, |
| "step": 890, |
| "train_runtime": 146.1333, |
| "train_tokens_per_second": 1910.804 |
| }, |
| { |
| "epoch": 9.944444444444445, |
| "grad_norm": 0.19623835384845734, |
| "learning_rate": 2.9627373076117863e-05, |
| "loss": 0.1173, |
| "num_input_tokens_seen": 280768, |
| "step": 895, |
| "train_runtime": 146.8573, |
| "train_tokens_per_second": 1911.842 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.009075737558305264, |
| "learning_rate": 2.9388941075939334e-05, |
| "loss": 0.0072, |
| "num_input_tokens_seen": 282368, |
| "step": 900, |
| "train_runtime": 147.6123, |
| "train_tokens_per_second": 1912.904 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.06860806792974472, |
| "eval_runtime": 0.5358, |
| "eval_samples_per_second": 74.655, |
| "eval_steps_per_second": 18.664, |
| "num_input_tokens_seen": 282368, |
| "step": 900 |
| }, |
| { |
| "epoch": 10.055555555555555, |
| "grad_norm": 0.757532000541687, |
| "learning_rate": 2.9150096440751107e-05, |
| "loss": 0.0278, |
| "num_input_tokens_seen": 283936, |
| "step": 905, |
| "train_runtime": 149.7123, |
| "train_tokens_per_second": 1896.544 |
| }, |
| { |
| "epoch": 10.11111111111111, |
| "grad_norm": 0.22894321382045746, |
| "learning_rate": 2.8910861626005776e-05, |
| "loss": 0.023, |
| "num_input_tokens_seen": 285504, |
| "step": 910, |
| "train_runtime": 150.4441, |
| "train_tokens_per_second": 1897.742 |
| }, |
| { |
| "epoch": 10.166666666666666, |
| "grad_norm": 0.018537739291787148, |
| "learning_rate": 2.8671259123839472e-05, |
| "loss": 0.1103, |
| "num_input_tokens_seen": 287072, |
| "step": 915, |
| "train_runtime": 151.1726, |
| "train_tokens_per_second": 1898.968 |
| }, |
| { |
| "epoch": 10.222222222222221, |
| "grad_norm": 0.017388442531228065, |
| "learning_rate": 2.843131146095719e-05, |
| "loss": 0.0086, |
| "num_input_tokens_seen": 288576, |
| "step": 920, |
| "train_runtime": 151.9305, |
| "train_tokens_per_second": 1899.394 |
| }, |
| { |
| "epoch": 10.277777777777779, |
| "grad_norm": 1.3574343919754028, |
| "learning_rate": 2.8191041196514873e-05, |
| "loss": 0.0723, |
| "num_input_tokens_seen": 290144, |
| "step": 925, |
| "train_runtime": 152.6969, |
| "train_tokens_per_second": 1900.13 |
| }, |
| { |
| "epoch": 10.333333333333334, |
| "grad_norm": 0.005878520663827658, |
| "learning_rate": 2.795047091999849e-05, |
| "loss": 0.0798, |
| "num_input_tokens_seen": 291744, |
| "step": 930, |
| "train_runtime": 153.4169, |
| "train_tokens_per_second": 1901.642 |
| }, |
| { |
| "epoch": 10.38888888888889, |
| "grad_norm": 1.1414101123809814, |
| "learning_rate": 2.770962324910027e-05, |
| "loss": 0.0842, |
| "num_input_tokens_seen": 293344, |
| "step": 935, |
| "train_runtime": 154.1374, |
| "train_tokens_per_second": 1903.134 |
| }, |
| { |
| "epoch": 10.444444444444445, |
| "grad_norm": 0.028480498120188713, |
| "learning_rate": 2.7468520827592197e-05, |
| "loss": 0.0096, |
| "num_input_tokens_seen": 294912, |
| "step": 940, |
| "train_runtime": 154.8553, |
| "train_tokens_per_second": 1904.436 |
| }, |
| { |
| "epoch": 10.5, |
| "grad_norm": 0.46967682242393494, |
| "learning_rate": 2.7227186323197162e-05, |
| "loss": 0.0998, |
| "num_input_tokens_seen": 296480, |
| "step": 945, |
| "train_runtime": 155.5729, |
| "train_tokens_per_second": 1905.731 |
| }, |
| { |
| "epoch": 10.555555555555555, |
| "grad_norm": 0.1990341991186142, |
| "learning_rate": 2.6985642425457757e-05, |
| "loss": 0.0329, |
| "num_input_tokens_seen": 298048, |
| "step": 950, |
| "train_runtime": 156.289, |
| "train_tokens_per_second": 1907.031 |
| }, |
| { |
| "epoch": 10.61111111111111, |
| "grad_norm": 0.12564487755298615, |
| "learning_rate": 2.674391184360313e-05, |
| "loss": 0.0243, |
| "num_input_tokens_seen": 299648, |
| "step": 955, |
| "train_runtime": 157.005, |
| "train_tokens_per_second": 1908.525 |
| }, |
| { |
| "epoch": 10.666666666666666, |
| "grad_norm": 0.9219412207603455, |
| "learning_rate": 2.650201730441392e-05, |
| "loss": 0.0245, |
| "num_input_tokens_seen": 301216, |
| "step": 960, |
| "train_runtime": 157.721, |
| "train_tokens_per_second": 1909.802 |
| }, |
| { |
| "epoch": 10.722222222222221, |
| "grad_norm": 0.3017958402633667, |
| "learning_rate": 2.6259981550085504e-05, |
| "loss": 0.045, |
| "num_input_tokens_seen": 302784, |
| "step": 965, |
| "train_runtime": 158.4375, |
| "train_tokens_per_second": 1911.063 |
| }, |
| { |
| "epoch": 10.777777777777779, |
| "grad_norm": 0.06184842064976692, |
| "learning_rate": 2.60178273360899e-05, |
| "loss": 0.0051, |
| "num_input_tokens_seen": 304320, |
| "step": 970, |
| "train_runtime": 159.1528, |
| "train_tokens_per_second": 1912.125 |
| }, |
| { |
| "epoch": 10.833333333333334, |
| "grad_norm": 0.1001506820321083, |
| "learning_rate": 2.5775577429036345e-05, |
| "loss": 0.0531, |
| "num_input_tokens_seen": 305856, |
| "step": 975, |
| "train_runtime": 159.872, |
| "train_tokens_per_second": 1913.131 |
| }, |
| { |
| "epoch": 10.88888888888889, |
| "grad_norm": 1.2442516088485718, |
| "learning_rate": 2.553325460453086e-05, |
| "loss": 0.0839, |
| "num_input_tokens_seen": 307424, |
| "step": 980, |
| "train_runtime": 160.5886, |
| "train_tokens_per_second": 1914.357 |
| }, |
| { |
| "epoch": 10.944444444444445, |
| "grad_norm": 0.007865453138947487, |
| "learning_rate": 2.5290881645034932e-05, |
| "loss": 0.0476, |
| "num_input_tokens_seen": 308992, |
| "step": 985, |
| "train_runtime": 161.3127, |
| "train_tokens_per_second": 1915.484 |
| }, |
| { |
| "epoch": 11.0, |
| "grad_norm": 0.5944153666496277, |
| "learning_rate": 2.504848133772358e-05, |
| "loss": 0.1143, |
| "num_input_tokens_seen": 310560, |
| "step": 990, |
| "train_runtime": 162.0625, |
| "train_tokens_per_second": 1916.298 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 0.06816816329956055, |
| "eval_runtime": 0.5339, |
| "eval_samples_per_second": 74.924, |
| "eval_steps_per_second": 18.731, |
| "num_input_tokens_seen": 310560, |
| "step": 990 |
| }, |
| { |
| "epoch": 11.055555555555555, |
| "grad_norm": 0.38990718126296997, |
| "learning_rate": 2.4806076472342997e-05, |
| "loss": 0.0147, |
| "num_input_tokens_seen": 312160, |
| "step": 995, |
| "train_runtime": 164.1664, |
| "train_tokens_per_second": 1901.485 |
| }, |
| { |
| "epoch": 11.11111111111111, |
| "grad_norm": 0.10253170877695084, |
| "learning_rate": 2.4563689839067913e-05, |
| "loss": 0.0616, |
| "num_input_tokens_seen": 313728, |
| "step": 1000, |
| "train_runtime": 164.9003, |
| "train_tokens_per_second": 1902.532 |
| }, |
| { |
| "epoch": 11.166666666666666, |
| "grad_norm": 0.08587852865457535, |
| "learning_rate": 2.432134422635893e-05, |
| "loss": 0.015, |
| "num_input_tokens_seen": 315264, |
| "step": 1005, |
| "train_runtime": 165.6348, |
| "train_tokens_per_second": 1903.368 |
| }, |
| { |
| "epoch": 11.222222222222221, |
| "grad_norm": 0.022479208186268806, |
| "learning_rate": 2.4079062418820002e-05, |
| "loss": 0.0089, |
| "num_input_tokens_seen": 316864, |
| "step": 1010, |
| "train_runtime": 166.376, |
| "train_tokens_per_second": 1904.505 |
| }, |
| { |
| "epoch": 11.277777777777779, |
| "grad_norm": 0.12377724051475525, |
| "learning_rate": 2.3836867195056335e-05, |
| "loss": 0.0228, |
| "num_input_tokens_seen": 318432, |
| "step": 1015, |
| "train_runtime": 167.1701, |
| "train_tokens_per_second": 1904.838 |
| }, |
| { |
| "epoch": 11.333333333333334, |
| "grad_norm": 0.2768175005912781, |
| "learning_rate": 2.3594781325532784e-05, |
| "loss": 0.0939, |
| "num_input_tokens_seen": 320032, |
| "step": 1020, |
| "train_runtime": 167.8931, |
| "train_tokens_per_second": 1906.165 |
| }, |
| { |
| "epoch": 11.38888888888889, |
| "grad_norm": 0.44363412261009216, |
| "learning_rate": 2.3352827570433036e-05, |
| "loss": 0.0239, |
| "num_input_tokens_seen": 321536, |
| "step": 1025, |
| "train_runtime": 168.6167, |
| "train_tokens_per_second": 1906.904 |
| }, |
| { |
| "epoch": 11.444444444444445, |
| "grad_norm": 0.22889579832553864, |
| "learning_rate": 2.3111028677519804e-05, |
| "loss": 0.0277, |
| "num_input_tokens_seen": 323040, |
| "step": 1030, |
| "train_runtime": 169.3373, |
| "train_tokens_per_second": 1907.672 |
| }, |
| { |
| "epoch": 11.5, |
| "grad_norm": 0.03744177892804146, |
| "learning_rate": 2.2869407379996088e-05, |
| "loss": 0.0354, |
| "num_input_tokens_seen": 324608, |
| "step": 1035, |
| "train_runtime": 170.0547, |
| "train_tokens_per_second": 1908.844 |
| }, |
| { |
| "epoch": 11.555555555555555, |
| "grad_norm": 0.27139776945114136, |
| "learning_rate": 2.2627986394367938e-05, |
| "loss": 0.0294, |
| "num_input_tokens_seen": 326144, |
| "step": 1040, |
| "train_runtime": 170.7721, |
| "train_tokens_per_second": 1909.82 |
| }, |
| { |
| "epoch": 11.61111111111111, |
| "grad_norm": 0.15249714255332947, |
| "learning_rate": 2.238678841830867e-05, |
| "loss": 0.1264, |
| "num_input_tokens_seen": 327712, |
| "step": 1045, |
| "train_runtime": 171.4941, |
| "train_tokens_per_second": 1910.923 |
| }, |
| { |
| "epoch": 11.666666666666666, |
| "grad_norm": 0.1465960144996643, |
| "learning_rate": 2.2145836128524902e-05, |
| "loss": 0.0362, |
| "num_input_tokens_seen": 329248, |
| "step": 1050, |
| "train_runtime": 172.2187, |
| "train_tokens_per_second": 1911.802 |
| }, |
| { |
| "epoch": 11.722222222222221, |
| "grad_norm": 0.30058616399765015, |
| "learning_rate": 2.1905152178624595e-05, |
| "loss": 0.1676, |
| "num_input_tokens_seen": 330816, |
| "step": 1055, |
| "train_runtime": 172.9388, |
| "train_tokens_per_second": 1912.908 |
| }, |
| { |
| "epoch": 11.777777777777779, |
| "grad_norm": 0.12410334497690201, |
| "learning_rate": 2.1664759196987182e-05, |
| "loss": 0.049, |
| "num_input_tokens_seen": 332416, |
| "step": 1060, |
| "train_runtime": 173.661, |
| "train_tokens_per_second": 1914.166 |
| }, |
| { |
| "epoch": 11.833333333333334, |
| "grad_norm": 0.007951710373163223, |
| "learning_rate": 2.1424679784636144e-05, |
| "loss": 0.0453, |
| "num_input_tokens_seen": 334016, |
| "step": 1065, |
| "train_runtime": 174.3868, |
| "train_tokens_per_second": 1915.375 |
| }, |
| { |
| "epoch": 11.88888888888889, |
| "grad_norm": 0.2507447600364685, |
| "learning_rate": 2.118493651311413e-05, |
| "loss": 0.0451, |
| "num_input_tokens_seen": 335616, |
| "step": 1070, |
| "train_runtime": 175.1045, |
| "train_tokens_per_second": 1916.661 |
| }, |
| { |
| "epoch": 11.944444444444445, |
| "grad_norm": 0.25571751594543457, |
| "learning_rate": 2.0945551922360818e-05, |
| "loss": 0.0556, |
| "num_input_tokens_seen": 337152, |
| "step": 1075, |
| "train_runtime": 175.8246, |
| "train_tokens_per_second": 1917.548 |
| }, |
| { |
| "epoch": 12.0, |
| "grad_norm": 0.020534232258796692, |
| "learning_rate": 2.070654851859383e-05, |
| "loss": 0.0457, |
| "num_input_tokens_seen": 338784, |
| "step": 1080, |
| "train_runtime": 176.5722, |
| "train_tokens_per_second": 1918.671 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 0.06687770783901215, |
| "eval_runtime": 0.5323, |
| "eval_samples_per_second": 75.144, |
| "eval_steps_per_second": 18.786, |
| "num_input_tokens_seen": 338784, |
| "step": 1080 |
| }, |
| { |
| "epoch": 12.055555555555555, |
| "grad_norm": 1.2923614978790283, |
| "learning_rate": 2.0467948772192713e-05, |
| "loss": 0.0482, |
| "num_input_tokens_seen": 340288, |
| "step": 1085, |
| "train_runtime": 178.6516, |
| "train_tokens_per_second": 1904.757 |
| }, |
| { |
| "epoch": 12.11111111111111, |
| "grad_norm": 1.6049034595489502, |
| "learning_rate": 2.022977511558638e-05, |
| "loss": 0.083, |
| "num_input_tokens_seen": 341888, |
| "step": 1090, |
| "train_runtime": 179.3776, |
| "train_tokens_per_second": 1905.968 |
| }, |
| { |
| "epoch": 12.166666666666666, |
| "grad_norm": 0.49522802233695984, |
| "learning_rate": 1.9992049941144066e-05, |
| "loss": 0.0925, |
| "num_input_tokens_seen": 343488, |
| "step": 1095, |
| "train_runtime": 180.1027, |
| "train_tokens_per_second": 1907.179 |
| }, |
| { |
| "epoch": 12.222222222222221, |
| "grad_norm": 0.21042613685131073, |
| "learning_rate": 1.9754795599070068e-05, |
| "loss": 0.0725, |
| "num_input_tokens_seen": 344992, |
| "step": 1100, |
| "train_runtime": 180.8284, |
| "train_tokens_per_second": 1907.842 |
| }, |
| { |
| "epoch": 12.277777777777779, |
| "grad_norm": 0.0459279902279377, |
| "learning_rate": 1.9518034395302414e-05, |
| "loss": 0.0175, |
| "num_input_tokens_seen": 346560, |
| "step": 1105, |
| "train_runtime": 181.6209, |
| "train_tokens_per_second": 1908.151 |
| }, |
| { |
| "epoch": 12.333333333333334, |
| "grad_norm": 0.42952170968055725, |
| "learning_rate": 1.9281788589415804e-05, |
| "loss": 0.029, |
| "num_input_tokens_seen": 348160, |
| "step": 1110, |
| "train_runtime": 182.3469, |
| "train_tokens_per_second": 1909.327 |
| }, |
| { |
| "epoch": 12.38888888888889, |
| "grad_norm": 0.00739190774038434, |
| "learning_rate": 1.9046080392528735e-05, |
| "loss": 0.0087, |
| "num_input_tokens_seen": 349760, |
| "step": 1115, |
| "train_runtime": 183.0709, |
| "train_tokens_per_second": 1910.517 |
| }, |
| { |
| "epoch": 12.444444444444445, |
| "grad_norm": 0.7268601655960083, |
| "learning_rate": 1.8810931965215356e-05, |
| "loss": 0.0211, |
| "num_input_tokens_seen": 351328, |
| "step": 1120, |
| "train_runtime": 183.788, |
| "train_tokens_per_second": 1911.593 |
| }, |
| { |
| "epoch": 12.5, |
| "grad_norm": 0.021834464743733406, |
| "learning_rate": 1.857636541542195e-05, |
| "loss": 0.0294, |
| "num_input_tokens_seen": 352896, |
| "step": 1125, |
| "train_runtime": 184.5069, |
| "train_tokens_per_second": 1912.644 |
| }, |
| { |
| "epoch": 12.555555555555555, |
| "grad_norm": 0.1519467979669571, |
| "learning_rate": 1.8342402796388445e-05, |
| "loss": 0.0115, |
| "num_input_tokens_seen": 354464, |
| "step": 1130, |
| "train_runtime": 185.2247, |
| "train_tokens_per_second": 1913.697 |
| }, |
| { |
| "epoch": 12.61111111111111, |
| "grad_norm": 1.5149493217468262, |
| "learning_rate": 1.8109066104575023e-05, |
| "loss": 0.0877, |
| "num_input_tokens_seen": 356032, |
| "step": 1135, |
| "train_runtime": 185.9478, |
| "train_tokens_per_second": 1914.688 |
| }, |
| { |
| "epoch": 12.666666666666666, |
| "grad_norm": 0.12189318984746933, |
| "learning_rate": 1.7876377277594053e-05, |
| "loss": 0.0222, |
| "num_input_tokens_seen": 357632, |
| "step": 1140, |
| "train_runtime": 186.6713, |
| "train_tokens_per_second": 1915.838 |
| }, |
| { |
| "epoch": 12.722222222222221, |
| "grad_norm": 1.7125587463378906, |
| "learning_rate": 1.764435819214762e-05, |
| "loss": 0.1248, |
| "num_input_tokens_seen": 359168, |
| "step": 1145, |
| "train_runtime": 187.4026, |
| "train_tokens_per_second": 1916.558 |
| }, |
| { |
| "epoch": 12.777777777777779, |
| "grad_norm": 1.6973289251327515, |
| "learning_rate": 1.7413030661970742e-05, |
| "loss": 0.0736, |
| "num_input_tokens_seen": 360736, |
| "step": 1150, |
| "train_runtime": 188.1281, |
| "train_tokens_per_second": 1917.501 |
| }, |
| { |
| "epoch": 12.833333333333334, |
| "grad_norm": 0.1838073432445526, |
| "learning_rate": 1.7182416435780454e-05, |
| "loss": 0.0277, |
| "num_input_tokens_seen": 362304, |
| "step": 1155, |
| "train_runtime": 188.8455, |
| "train_tokens_per_second": 1918.52 |
| }, |
| { |
| "epoch": 12.88888888888889, |
| "grad_norm": 0.34476426243782043, |
| "learning_rate": 1.695253719523115e-05, |
| "loss": 0.0162, |
| "num_input_tokens_seen": 363872, |
| "step": 1160, |
| "train_runtime": 189.5628, |
| "train_tokens_per_second": 1919.533 |
| }, |
| { |
| "epoch": 12.944444444444445, |
| "grad_norm": 0.5110657215118408, |
| "learning_rate": 1.672341455287605e-05, |
| "loss": 0.047, |
| "num_input_tokens_seen": 365376, |
| "step": 1165, |
| "train_runtime": 190.2824, |
| "train_tokens_per_second": 1920.178 |
| }, |
| { |
| "epoch": 13.0, |
| "grad_norm": 0.016537530347704887, |
| "learning_rate": 1.649507005013532e-05, |
| "loss": 0.0551, |
| "num_input_tokens_seen": 366944, |
| "step": 1170, |
| "train_runtime": 191.037, |
| "train_tokens_per_second": 1920.801 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_loss": 0.06656987965106964, |
| "eval_runtime": 0.5343, |
| "eval_samples_per_second": 74.869, |
| "eval_steps_per_second": 18.717, |
| "num_input_tokens_seen": 366944, |
| "step": 1170 |
| }, |
| { |
| "epoch": 13.055555555555555, |
| "grad_norm": 0.048492301255464554, |
| "learning_rate": 1.6267525155270773e-05, |
| "loss": 0.0259, |
| "num_input_tokens_seen": 368384, |
| "step": 1175, |
| "train_runtime": 193.1048, |
| "train_tokens_per_second": 1907.689 |
| }, |
| { |
| "epoch": 13.11111111111111, |
| "grad_norm": 0.009170373901724815, |
| "learning_rate": 1.6040801261367493e-05, |
| "loss": 0.0216, |
| "num_input_tokens_seen": 369984, |
| "step": 1180, |
| "train_runtime": 193.8321, |
| "train_tokens_per_second": 1908.786 |
| }, |
| { |
| "epoch": 13.166666666666666, |
| "grad_norm": 1.6876851320266724, |
| "learning_rate": 1.5814919684322545e-05, |
| "loss": 0.1097, |
| "num_input_tokens_seen": 371520, |
| "step": 1185, |
| "train_runtime": 194.5588, |
| "train_tokens_per_second": 1909.552 |
| }, |
| { |
| "epoch": 13.222222222222221, |
| "grad_norm": 0.023002078756690025, |
| "learning_rate": 1.5589901660840896e-05, |
| "loss": 0.0883, |
| "num_input_tokens_seen": 373120, |
| "step": 1190, |
| "train_runtime": 195.2853, |
| "train_tokens_per_second": 1910.64 |
| }, |
| { |
| "epoch": 13.277777777777779, |
| "grad_norm": 0.3338475227355957, |
| "learning_rate": 1.5365768346438797e-05, |
| "loss": 0.023, |
| "num_input_tokens_seen": 374688, |
| "step": 1195, |
| "train_runtime": 196.0748, |
| "train_tokens_per_second": 1910.944 |
| }, |
| { |
| "epoch": 13.333333333333334, |
| "grad_norm": 0.32469648122787476, |
| "learning_rate": 1.5142540813454836e-05, |
| "loss": 0.0364, |
| "num_input_tokens_seen": 376288, |
| "step": 1200, |
| "train_runtime": 196.7963, |
| "train_tokens_per_second": 1912.068 |
| }, |
| { |
| "epoch": 13.38888888888889, |
| "grad_norm": 0.16993819177150726, |
| "learning_rate": 1.4920240049068748e-05, |
| "loss": 0.0063, |
| "num_input_tokens_seen": 377888, |
| "step": 1205, |
| "train_runtime": 197.5237, |
| "train_tokens_per_second": 1913.127 |
| }, |
| { |
| "epoch": 13.444444444444445, |
| "grad_norm": 0.03197206184267998, |
| "learning_rate": 1.4698886953328292e-05, |
| "loss": 0.0037, |
| "num_input_tokens_seen": 379424, |
| "step": 1210, |
| "train_runtime": 198.243, |
| "train_tokens_per_second": 1913.934 |
| }, |
| { |
| "epoch": 13.5, |
| "grad_norm": 0.009404771961271763, |
| "learning_rate": 1.4478502337184274e-05, |
| "loss": 0.072, |
| "num_input_tokens_seen": 380992, |
| "step": 1215, |
| "train_runtime": 198.9608, |
| "train_tokens_per_second": 1914.91 |
| }, |
| { |
| "epoch": 13.555555555555555, |
| "grad_norm": 0.730259895324707, |
| "learning_rate": 1.4259106920533955e-05, |
| "loss": 0.0251, |
| "num_input_tokens_seen": 382592, |
| "step": 1220, |
| "train_runtime": 199.6822, |
| "train_tokens_per_second": 1916.005 |
| }, |
| { |
| "epoch": 13.61111111111111, |
| "grad_norm": 0.23059076070785522, |
| "learning_rate": 1.4040721330273062e-05, |
| "loss": 0.0444, |
| "num_input_tokens_seen": 384192, |
| "step": 1225, |
| "train_runtime": 200.4048, |
| "train_tokens_per_second": 1917.08 |
| }, |
| { |
| "epoch": 13.666666666666666, |
| "grad_norm": 0.990837574005127, |
| "learning_rate": 1.3823366098356487e-05, |
| "loss": 0.0375, |
| "num_input_tokens_seen": 385760, |
| "step": 1230, |
| "train_runtime": 201.1286, |
| "train_tokens_per_second": 1917.977 |
| }, |
| { |
| "epoch": 13.722222222222221, |
| "grad_norm": 0.01306883804500103, |
| "learning_rate": 1.3607061659867892e-05, |
| "loss": 0.0579, |
| "num_input_tokens_seen": 387328, |
| "step": 1235, |
| "train_runtime": 201.8474, |
| "train_tokens_per_second": 1918.915 |
| }, |
| { |
| "epoch": 13.777777777777779, |
| "grad_norm": 0.020695485174655914, |
| "learning_rate": 1.3391828351098578e-05, |
| "loss": 0.0117, |
| "num_input_tokens_seen": 388896, |
| "step": 1240, |
| "train_runtime": 202.5664, |
| "train_tokens_per_second": 1919.845 |
| }, |
| { |
| "epoch": 13.833333333333334, |
| "grad_norm": 0.6323536038398743, |
| "learning_rate": 1.3177686407635417e-05, |
| "loss": 0.0299, |
| "num_input_tokens_seen": 390496, |
| "step": 1245, |
| "train_runtime": 203.284, |
| "train_tokens_per_second": 1920.938 |
| }, |
| { |
| "epoch": 13.88888888888889, |
| "grad_norm": 0.011660303920507431, |
| "learning_rate": 1.29646559624584e-05, |
| "loss": 0.0102, |
| "num_input_tokens_seen": 392064, |
| "step": 1250, |
| "train_runtime": 204.0027, |
| "train_tokens_per_second": 1921.856 |
| }, |
| { |
| "epoch": 13.944444444444445, |
| "grad_norm": 0.35882309079170227, |
| "learning_rate": 1.2752757044047827e-05, |
| "loss": 0.0984, |
| "num_input_tokens_seen": 393632, |
| "step": 1255, |
| "train_runtime": 204.7229, |
| "train_tokens_per_second": 1922.755 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 1.5153825283050537, |
| "learning_rate": 1.2542009574501246e-05, |
| "loss": 0.139, |
| "num_input_tokens_seen": 395104, |
| "step": 1260, |
| "train_runtime": 205.4779, |
| "train_tokens_per_second": 1922.854 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 0.06650747358798981, |
| "eval_runtime": 0.5302, |
| "eval_samples_per_second": 75.448, |
| "eval_steps_per_second": 18.862, |
| "num_input_tokens_seen": 395104, |
| "step": 1260 |
| }, |
| { |
| "epoch": 14.055555555555555, |
| "grad_norm": 0.3795919716358185, |
| "learning_rate": 1.2332433367660442e-05, |
| "loss": 0.0579, |
| "num_input_tokens_seen": 396672, |
| "step": 1265, |
| "train_runtime": 207.563, |
| "train_tokens_per_second": 1911.092 |
| }, |
| { |
| "epoch": 14.11111111111111, |
| "grad_norm": 0.027463024482131004, |
| "learning_rate": 1.2124048127248644e-05, |
| "loss": 0.0444, |
| "num_input_tokens_seen": 398304, |
| "step": 1270, |
| "train_runtime": 208.3001, |
| "train_tokens_per_second": 1912.164 |
| }, |
| { |
| "epoch": 14.166666666666666, |
| "grad_norm": 0.7048236131668091, |
| "learning_rate": 1.1916873445017982e-05, |
| "loss": 0.0254, |
| "num_input_tokens_seen": 399840, |
| "step": 1275, |
| "train_runtime": 209.037, |
| "train_tokens_per_second": 1912.772 |
| }, |
| { |
| "epoch": 14.222222222222221, |
| "grad_norm": 0.009322111494839191, |
| "learning_rate": 1.1710928798907556e-05, |
| "loss": 0.0749, |
| "num_input_tokens_seen": 401440, |
| "step": 1280, |
| "train_runtime": 209.7672, |
| "train_tokens_per_second": 1913.74 |
| }, |
| { |
| "epoch": 14.277777777777779, |
| "grad_norm": 0.01669895090162754, |
| "learning_rate": 1.1506233551212186e-05, |
| "loss": 0.0216, |
| "num_input_tokens_seen": 403040, |
| "step": 1285, |
| "train_runtime": 210.5591, |
| "train_tokens_per_second": 1914.142 |
| }, |
| { |
| "epoch": 14.333333333333334, |
| "grad_norm": 0.504178524017334, |
| "learning_rate": 1.1302806946762004e-05, |
| "loss": 0.0221, |
| "num_input_tokens_seen": 404640, |
| "step": 1290, |
| "train_runtime": 211.281, |
| "train_tokens_per_second": 1915.175 |
| }, |
| { |
| "epoch": 14.38888888888889, |
| "grad_norm": 0.4881063997745514, |
| "learning_rate": 1.1100668111113166e-05, |
| "loss": 0.0227, |
| "num_input_tokens_seen": 406208, |
| "step": 1295, |
| "train_runtime": 212.0164, |
| "train_tokens_per_second": 1915.927 |
| }, |
| { |
| "epoch": 14.444444444444445, |
| "grad_norm": 0.0046058776788413525, |
| "learning_rate": 1.0899836048749645e-05, |
| "loss": 0.0794, |
| "num_input_tokens_seen": 407776, |
| "step": 1300, |
| "train_runtime": 212.743, |
| "train_tokens_per_second": 1916.754 |
| }, |
| { |
| "epoch": 14.5, |
| "grad_norm": 0.3913433849811554, |
| "learning_rate": 1.0700329641296541e-05, |
| "loss": 0.0937, |
| "num_input_tokens_seen": 409312, |
| "step": 1305, |
| "train_runtime": 213.4663, |
| "train_tokens_per_second": 1917.455 |
| }, |
| { |
| "epoch": 14.555555555555555, |
| "grad_norm": 0.04091079160571098, |
| "learning_rate": 1.0502167645744895e-05, |
| "loss": 0.0034, |
| "num_input_tokens_seen": 410816, |
| "step": 1310, |
| "train_runtime": 214.1934, |
| "train_tokens_per_second": 1917.968 |
| }, |
| { |
| "epoch": 14.61111111111111, |
| "grad_norm": 0.7491574883460999, |
| "learning_rate": 1.0305368692688174e-05, |
| "loss": 0.0553, |
| "num_input_tokens_seen": 412416, |
| "step": 1315, |
| "train_runtime": 214.9138, |
| "train_tokens_per_second": 1918.983 |
| }, |
| { |
| "epoch": 14.666666666666666, |
| "grad_norm": 0.09902898222208023, |
| "learning_rate": 1.01099512845707e-05, |
| "loss": 0.0155, |
| "num_input_tokens_seen": 414016, |
| "step": 1320, |
| "train_runtime": 215.6296, |
| "train_tokens_per_second": 1920.034 |
| }, |
| { |
| "epoch": 14.722222222222221, |
| "grad_norm": 0.13095584511756897, |
| "learning_rate": 9.91593379394811e-06, |
| "loss": 0.0518, |
| "num_input_tokens_seen": 415552, |
| "step": 1325, |
| "train_runtime": 216.3457, |
| "train_tokens_per_second": 1920.778 |
| }, |
| { |
| "epoch": 14.777777777777779, |
| "grad_norm": 0.008948145434260368, |
| "learning_rate": 9.723334461760006e-06, |
| "loss": 0.0101, |
| "num_input_tokens_seen": 417088, |
| "step": 1330, |
| "train_runtime": 217.0664, |
| "train_tokens_per_second": 1921.477 |
| }, |
| { |
| "epoch": 14.833333333333334, |
| "grad_norm": 1.4915354251861572, |
| "learning_rate": 9.532171395615036e-06, |
| "loss": 0.127, |
| "num_input_tokens_seen": 418656, |
| "step": 1335, |
| "train_runtime": 217.7857, |
| "train_tokens_per_second": 1922.33 |
| }, |
| { |
| "epoch": 14.88888888888889, |
| "grad_norm": 0.006428571883589029, |
| "learning_rate": 9.342462568088416e-06, |
| "loss": 0.0352, |
| "num_input_tokens_seen": 420256, |
| "step": 1340, |
| "train_runtime": 218.5045, |
| "train_tokens_per_second": 1923.329 |
| }, |
| { |
| "epoch": 14.944444444444445, |
| "grad_norm": 0.2612595856189728, |
| "learning_rate": 9.154225815032242e-06, |
| "loss": 0.0122, |
| "num_input_tokens_seen": 421792, |
| "step": 1345, |
| "train_runtime": 219.2285, |
| "train_tokens_per_second": 1923.984 |
| }, |
| { |
| "epoch": 15.0, |
| "grad_norm": 0.021902482956647873, |
| "learning_rate": 8.967478833898612e-06, |
| "loss": 0.0655, |
| "num_input_tokens_seen": 423360, |
| "step": 1350, |
| "train_runtime": 219.9807, |
| "train_tokens_per_second": 1924.533 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_loss": 0.06403695046901703, |
| "eval_runtime": 0.5355, |
| "eval_samples_per_second": 74.701, |
| "eval_steps_per_second": 18.675, |
| "num_input_tokens_seen": 423360, |
| "step": 1350 |
| }, |
| { |
| "epoch": 15.055555555555555, |
| "grad_norm": 0.0330515094101429, |
| "learning_rate": 8.78223918207575e-06, |
| "loss": 0.0151, |
| "num_input_tokens_seen": 424992, |
| "step": 1355, |
| "train_runtime": 222.0766, |
| "train_tokens_per_second": 1913.718 |
| }, |
| { |
| "epoch": 15.11111111111111, |
| "grad_norm": 0.03642648831009865, |
| "learning_rate": 8.598524275237322e-06, |
| "loss": 0.0554, |
| "num_input_tokens_seen": 426528, |
| "step": 1360, |
| "train_runtime": 222.8019, |
| "train_tokens_per_second": 1914.382 |
| }, |
| { |
| "epoch": 15.166666666666666, |
| "grad_norm": 0.11118751019239426, |
| "learning_rate": 8.41635138570507e-06, |
| "loss": 0.0283, |
| "num_input_tokens_seen": 428096, |
| "step": 1365, |
| "train_runtime": 223.5275, |
| "train_tokens_per_second": 1915.182 |
| }, |
| { |
| "epoch": 15.222222222222221, |
| "grad_norm": 0.015841670334339142, |
| "learning_rate": 8.235737640824908e-06, |
| "loss": 0.0262, |
| "num_input_tokens_seen": 429600, |
| "step": 1370, |
| "train_runtime": 224.256, |
| "train_tokens_per_second": 1915.668 |
| }, |
| { |
| "epoch": 15.277777777777779, |
| "grad_norm": 0.7373225688934326, |
| "learning_rate": 8.056700021356694e-06, |
| "loss": 0.1276, |
| "num_input_tokens_seen": 431200, |
| "step": 1375, |
| "train_runtime": 225.046, |
| "train_tokens_per_second": 1916.053 |
| }, |
| { |
| "epoch": 15.333333333333334, |
| "grad_norm": 0.047713033854961395, |
| "learning_rate": 7.879255359877705e-06, |
| "loss": 0.0159, |
| "num_input_tokens_seen": 432736, |
| "step": 1380, |
| "train_runtime": 225.7705, |
| "train_tokens_per_second": 1916.707 |
| }, |
| { |
| "epoch": 15.38888888888889, |
| "grad_norm": 0.6301924586296082, |
| "learning_rate": 7.703420339200101e-06, |
| "loss": 0.0261, |
| "num_input_tokens_seen": 434336, |
| "step": 1385, |
| "train_runtime": 226.5014, |
| "train_tokens_per_second": 1917.587 |
| }, |
| { |
| "epoch": 15.444444444444445, |
| "grad_norm": 0.19205856323242188, |
| "learning_rate": 7.529211490802498e-06, |
| "loss": 0.0145, |
| "num_input_tokens_seen": 435904, |
| "step": 1390, |
| "train_runtime": 227.2344, |
| "train_tokens_per_second": 1918.301 |
| }, |
| { |
| "epoch": 15.5, |
| "grad_norm": 1.5189799070358276, |
| "learning_rate": 7.3566451932756744e-06, |
| "loss": 0.0874, |
| "num_input_tokens_seen": 437440, |
| "step": 1395, |
| "train_runtime": 227.9626, |
| "train_tokens_per_second": 1918.911 |
| }, |
| { |
| "epoch": 15.555555555555555, |
| "grad_norm": 0.2762519121170044, |
| "learning_rate": 7.185737670782727e-06, |
| "loss": 0.0199, |
| "num_input_tokens_seen": 438976, |
| "step": 1400, |
| "train_runtime": 228.6902, |
| "train_tokens_per_second": 1919.522 |
| }, |
| { |
| "epoch": 15.61111111111111, |
| "grad_norm": 0.03604911267757416, |
| "learning_rate": 7.016504991533726e-06, |
| "loss": 0.0216, |
| "num_input_tokens_seen": 440512, |
| "step": 1405, |
| "train_runtime": 229.4139, |
| "train_tokens_per_second": 1920.163 |
| }, |
| { |
| "epoch": 15.666666666666666, |
| "grad_norm": 0.008183962665498257, |
| "learning_rate": 6.848963066275027e-06, |
| "loss": 0.0666, |
| "num_input_tokens_seen": 442112, |
| "step": 1410, |
| "train_runtime": 230.1355, |
| "train_tokens_per_second": 1921.095 |
| }, |
| { |
| "epoch": 15.722222222222221, |
| "grad_norm": 0.07913227379322052, |
| "learning_rate": 6.683127646793411e-06, |
| "loss": 0.027, |
| "num_input_tokens_seen": 443616, |
| "step": 1415, |
| "train_runtime": 230.8622, |
| "train_tokens_per_second": 1921.562 |
| }, |
| { |
| "epoch": 15.777777777777779, |
| "grad_norm": 0.13029180467128754, |
| "learning_rate": 6.519014324435102e-06, |
| "loss": 0.1112, |
| "num_input_tokens_seen": 445184, |
| "step": 1420, |
| "train_runtime": 231.5771, |
| "train_tokens_per_second": 1922.401 |
| }, |
| { |
| "epoch": 15.833333333333334, |
| "grad_norm": 0.43220093846321106, |
| "learning_rate": 6.356638528639955e-06, |
| "loss": 0.0265, |
| "num_input_tokens_seen": 446752, |
| "step": 1425, |
| "train_runtime": 232.2972, |
| "train_tokens_per_second": 1923.192 |
| }, |
| { |
| "epoch": 15.88888888888889, |
| "grad_norm": 0.008491002023220062, |
| "learning_rate": 6.196015525490825e-06, |
| "loss": 0.0415, |
| "num_input_tokens_seen": 448352, |
| "step": 1430, |
| "train_runtime": 233.0234, |
| "train_tokens_per_second": 1924.064 |
| }, |
| { |
| "epoch": 15.944444444444445, |
| "grad_norm": 0.21576499938964844, |
| "learning_rate": 6.037160416278278e-06, |
| "loss": 0.0316, |
| "num_input_tokens_seen": 449888, |
| "step": 1435, |
| "train_runtime": 233.7414, |
| "train_tokens_per_second": 1924.725 |
| }, |
| { |
| "epoch": 16.0, |
| "grad_norm": 0.010713284835219383, |
| "learning_rate": 5.880088136080814e-06, |
| "loss": 0.0589, |
| "num_input_tokens_seen": 451424, |
| "step": 1440, |
| "train_runtime": 234.4958, |
| "train_tokens_per_second": 1925.084 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_loss": 0.06382830440998077, |
| "eval_runtime": 0.5348, |
| "eval_samples_per_second": 74.794, |
| "eval_steps_per_second": 18.698, |
| "num_input_tokens_seen": 451424, |
| "step": 1440 |
| }, |
| { |
| "epoch": 16.055555555555557, |
| "grad_norm": 0.01984066516160965, |
| "learning_rate": 5.724813452360736e-06, |
| "loss": 0.0216, |
| "num_input_tokens_seen": 452992, |
| "step": 1445, |
| "train_runtime": 236.5497, |
| "train_tokens_per_second": 1914.997 |
| }, |
| { |
| "epoch": 16.11111111111111, |
| "grad_norm": 0.051839593797922134, |
| "learning_rate": 5.571350963575728e-06, |
| "loss": 0.019, |
| "num_input_tokens_seen": 454496, |
| "step": 1450, |
| "train_runtime": 237.277, |
| "train_tokens_per_second": 1915.466 |
| }, |
| { |
| "epoch": 16.166666666666668, |
| "grad_norm": 0.21877069771289825, |
| "learning_rate": 5.4197150978063965e-06, |
| "loss": 0.1096, |
| "num_input_tokens_seen": 456096, |
| "step": 1455, |
| "train_runtime": 238.0039, |
| "train_tokens_per_second": 1916.338 |
| }, |
| { |
| "epoch": 16.22222222222222, |
| "grad_norm": 0.11044277250766754, |
| "learning_rate": 5.269920111399732e-06, |
| "loss": 0.024, |
| "num_input_tokens_seen": 457696, |
| "step": 1460, |
| "train_runtime": 238.7265, |
| "train_tokens_per_second": 1917.24 |
| }, |
| { |
| "epoch": 16.27777777777778, |
| "grad_norm": 0.009204542264342308, |
| "learning_rate": 5.121980087628803e-06, |
| "loss": 0.0034, |
| "num_input_tokens_seen": 459232, |
| "step": 1465, |
| "train_runtime": 239.5225, |
| "train_tokens_per_second": 1917.281 |
| }, |
| { |
| "epoch": 16.333333333333332, |
| "grad_norm": 0.09842357784509659, |
| "learning_rate": 4.975908935368701e-06, |
| "loss": 0.0446, |
| "num_input_tokens_seen": 460832, |
| "step": 1470, |
| "train_runtime": 240.2512, |
| "train_tokens_per_second": 1918.126 |
| }, |
| { |
| "epoch": 16.38888888888889, |
| "grad_norm": 0.02341254986822605, |
| "learning_rate": 4.831720387788827e-06, |
| "loss": 0.0052, |
| "num_input_tokens_seen": 462432, |
| "step": 1475, |
| "train_runtime": 240.9793, |
| "train_tokens_per_second": 1918.97 |
| }, |
| { |
| "epoch": 16.444444444444443, |
| "grad_norm": 0.9226027727127075, |
| "learning_rate": 4.689428001061774e-06, |
| "loss": 0.0307, |
| "num_input_tokens_seen": 464000, |
| "step": 1480, |
| "train_runtime": 241.7004, |
| "train_tokens_per_second": 1919.732 |
| }, |
| { |
| "epoch": 16.5, |
| "grad_norm": 1.7933276891708374, |
| "learning_rate": 4.549045153088813e-06, |
| "loss": 0.1125, |
| "num_input_tokens_seen": 465536, |
| "step": 1485, |
| "train_runtime": 242.4254, |
| "train_tokens_per_second": 1920.326 |
| }, |
| { |
| "epoch": 16.555555555555557, |
| "grad_norm": 0.010659473948180676, |
| "learning_rate": 4.410585042242124e-06, |
| "loss": 0.0177, |
| "num_input_tokens_seen": 467136, |
| "step": 1490, |
| "train_runtime": 243.144, |
| "train_tokens_per_second": 1921.232 |
| }, |
| { |
| "epoch": 16.61111111111111, |
| "grad_norm": 0.09569656848907471, |
| "learning_rate": 4.274060686123959e-06, |
| "loss": 0.0152, |
| "num_input_tokens_seen": 468672, |
| "step": 1495, |
| "train_runtime": 243.8646, |
| "train_tokens_per_second": 1921.853 |
| }, |
| { |
| "epoch": 16.666666666666668, |
| "grad_norm": 1.5692845582962036, |
| "learning_rate": 4.1394849203427284e-06, |
| "loss": 0.0559, |
| "num_input_tokens_seen": 470272, |
| "step": 1500, |
| "train_runtime": 244.5845, |
| "train_tokens_per_second": 1922.738 |
| }, |
| { |
| "epoch": 16.72222222222222, |
| "grad_norm": 0.8992767333984375, |
| "learning_rate": 4.006870397306256e-06, |
| "loss": 0.1462, |
| "num_input_tokens_seen": 471872, |
| "step": 1505, |
| "train_runtime": 245.3043, |
| "train_tokens_per_second": 1923.619 |
| }, |
| { |
| "epoch": 16.77777777777778, |
| "grad_norm": 0.015070810914039612, |
| "learning_rate": 3.876229585032245e-06, |
| "loss": 0.0266, |
| "num_input_tokens_seen": 473440, |
| "step": 1510, |
| "train_runtime": 246.02, |
| "train_tokens_per_second": 1924.397 |
| }, |
| { |
| "epoch": 16.833333333333332, |
| "grad_norm": 0.1533195823431015, |
| "learning_rate": 3.7475747659760502e-06, |
| "loss": 0.0416, |
| "num_input_tokens_seen": 475008, |
| "step": 1515, |
| "train_runtime": 246.7407, |
| "train_tokens_per_second": 1925.13 |
| }, |
| { |
| "epoch": 16.88888888888889, |
| "grad_norm": 0.4271990656852722, |
| "learning_rate": 3.6209180358759394e-06, |
| "loss": 0.0719, |
| "num_input_tokens_seen": 476608, |
| "step": 1520, |
| "train_runtime": 247.4592, |
| "train_tokens_per_second": 1926.006 |
| }, |
| { |
| "epoch": 16.944444444444443, |
| "grad_norm": 0.008633787743747234, |
| "learning_rate": 3.4962713026158694e-06, |
| "loss": 0.0058, |
| "num_input_tokens_seen": 478176, |
| "step": 1525, |
| "train_runtime": 248.1747, |
| "train_tokens_per_second": 1926.772 |
| }, |
| { |
| "epoch": 17.0, |
| "grad_norm": 0.9597387313842773, |
| "learning_rate": 3.373646285105958e-06, |
| "loss": 0.0388, |
| "num_input_tokens_seen": 479744, |
| "step": 1530, |
| "train_runtime": 248.9317, |
| "train_tokens_per_second": 1927.212 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_loss": 0.06136542558670044, |
| "eval_runtime": 0.5322, |
| "eval_samples_per_second": 75.155, |
| "eval_steps_per_second": 18.789, |
| "num_input_tokens_seen": 479744, |
| "step": 1530 |
| }, |
| { |
| "epoch": 17.055555555555557, |
| "grad_norm": 0.025216510519385338, |
| "learning_rate": 3.2530545121807145e-06, |
| "loss": 0.0248, |
| "num_input_tokens_seen": 481344, |
| "step": 1535, |
| "train_runtime": 251.0216, |
| "train_tokens_per_second": 1917.54 |
| }, |
| { |
| "epoch": 17.11111111111111, |
| "grad_norm": 0.8008201718330383, |
| "learning_rate": 3.1345073215151066e-06, |
| "loss": 0.0326, |
| "num_input_tokens_seen": 482944, |
| "step": 1540, |
| "train_runtime": 251.7525, |
| "train_tokens_per_second": 1918.329 |
| }, |
| { |
| "epoch": 17.166666666666668, |
| "grad_norm": 0.010983273386955261, |
| "learning_rate": 3.0180158585586397e-06, |
| "loss": 0.0151, |
| "num_input_tokens_seen": 484480, |
| "step": 1545, |
| "train_runtime": 252.4883, |
| "train_tokens_per_second": 1918.821 |
| }, |
| { |
| "epoch": 17.22222222222222, |
| "grad_norm": 0.6954006552696228, |
| "learning_rate": 2.9035910754875136e-06, |
| "loss": 0.0588, |
| "num_input_tokens_seen": 486016, |
| "step": 1550, |
| "train_runtime": 253.217, |
| "train_tokens_per_second": 1919.366 |
| }, |
| { |
| "epoch": 17.27777777777778, |
| "grad_norm": 0.2412204146385193, |
| "learning_rate": 2.7912437301749026e-06, |
| "loss": 0.0203, |
| "num_input_tokens_seen": 487584, |
| "step": 1555, |
| "train_runtime": 253.9521, |
| "train_tokens_per_second": 1919.984 |
| }, |
| { |
| "epoch": 17.333333333333332, |
| "grad_norm": 0.11864454299211502, |
| "learning_rate": 2.6809843851795357e-06, |
| "loss": 0.0815, |
| "num_input_tokens_seen": 489088, |
| "step": 1560, |
| "train_runtime": 254.7449, |
| "train_tokens_per_second": 1919.913 |
| }, |
| { |
| "epoch": 17.38888888888889, |
| "grad_norm": 0.07409928739070892, |
| "learning_rate": 2.57282340675267e-06, |
| "loss": 0.0082, |
| "num_input_tokens_seen": 490688, |
| "step": 1565, |
| "train_runtime": 255.4649, |
| "train_tokens_per_second": 1920.765 |
| }, |
| { |
| "epoch": 17.444444444444443, |
| "grad_norm": 0.15076597034931183, |
| "learning_rate": 2.4667709638634434e-06, |
| "loss": 0.0798, |
| "num_input_tokens_seen": 492288, |
| "step": 1570, |
| "train_runtime": 256.1878, |
| "train_tokens_per_second": 1921.59 |
| }, |
| { |
| "epoch": 17.5, |
| "grad_norm": 0.7357990741729736, |
| "learning_rate": 2.3628370272428564e-06, |
| "loss": 0.0163, |
| "num_input_tokens_seen": 493824, |
| "step": 1575, |
| "train_runtime": 256.9114, |
| "train_tokens_per_second": 1922.156 |
| }, |
| { |
| "epoch": 17.555555555555557, |
| "grad_norm": 0.37361836433410645, |
| "learning_rate": 2.2610313684463177e-06, |
| "loss": 0.0241, |
| "num_input_tokens_seen": 495456, |
| "step": 1580, |
| "train_runtime": 257.6329, |
| "train_tokens_per_second": 1923.108 |
| }, |
| { |
| "epoch": 17.61111111111111, |
| "grad_norm": 0.2539951801300049, |
| "learning_rate": 2.1613635589349756e-06, |
| "loss": 0.0799, |
| "num_input_tokens_seen": 497024, |
| "step": 1585, |
| "train_runtime": 258.3515, |
| "train_tokens_per_second": 1923.829 |
| }, |
| { |
| "epoch": 17.666666666666668, |
| "grad_norm": 0.278292179107666, |
| "learning_rate": 2.063842969175847e-06, |
| "loss": 0.0776, |
| "num_input_tokens_seen": 498592, |
| "step": 1590, |
| "train_runtime": 259.0701, |
| "train_tokens_per_second": 1924.544 |
| }, |
| { |
| "epoch": 17.72222222222222, |
| "grad_norm": 0.16478262841701508, |
| "learning_rate": 1.968478767760812e-06, |
| "loss": 0.0617, |
| "num_input_tokens_seen": 500128, |
| "step": 1595, |
| "train_runtime": 259.7856, |
| "train_tokens_per_second": 1925.156 |
| }, |
| { |
| "epoch": 17.77777777777778, |
| "grad_norm": 0.0895620584487915, |
| "learning_rate": 1.8752799205445982e-06, |
| "loss": 0.0131, |
| "num_input_tokens_seen": 501696, |
| "step": 1600, |
| "train_runtime": 260.5015, |
| "train_tokens_per_second": 1925.885 |
| }, |
| { |
| "epoch": 17.833333333333332, |
| "grad_norm": 0.46476849913597107, |
| "learning_rate": 1.784255189801895e-06, |
| "loss": 0.0508, |
| "num_input_tokens_seen": 503232, |
| "step": 1605, |
| "train_runtime": 261.2201, |
| "train_tokens_per_second": 1926.467 |
| }, |
| { |
| "epoch": 17.88888888888889, |
| "grad_norm": 0.1637742668390274, |
| "learning_rate": 1.6954131334034922e-06, |
| "loss": 0.0527, |
| "num_input_tokens_seen": 504736, |
| "step": 1610, |
| "train_runtime": 261.9407, |
| "train_tokens_per_second": 1926.909 |
| }, |
| { |
| "epoch": 17.944444444444443, |
| "grad_norm": 0.03226396441459656, |
| "learning_rate": 1.6087621040117157e-06, |
| "loss": 0.0253, |
| "num_input_tokens_seen": 506304, |
| "step": 1615, |
| "train_runtime": 262.6551, |
| "train_tokens_per_second": 1927.638 |
| }, |
| { |
| "epoch": 18.0, |
| "grad_norm": 0.058289699256420135, |
| "learning_rate": 1.524310248295152e-06, |
| "loss": 0.0656, |
| "num_input_tokens_seen": 507872, |
| "step": 1620, |
| "train_runtime": 263.4036, |
| "train_tokens_per_second": 1928.114 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_loss": 0.06606583297252655, |
| "eval_runtime": 0.5352, |
| "eval_samples_per_second": 74.735, |
| "eval_steps_per_second": 18.684, |
| "num_input_tokens_seen": 507872, |
| "step": 1620 |
| }, |
| { |
| "epoch": 18.055555555555557, |
| "grad_norm": 0.4969352185726166, |
| "learning_rate": 1.4420655061626932e-06, |
| "loss": 0.0163, |
| "num_input_tokens_seen": 509408, |
| "step": 1625, |
| "train_runtime": 265.4903, |
| "train_tokens_per_second": 1918.744 |
| }, |
| { |
| "epoch": 18.11111111111111, |
| "grad_norm": 0.008122888393700123, |
| "learning_rate": 1.362035610017079e-06, |
| "loss": 0.0931, |
| "num_input_tokens_seen": 510912, |
| "step": 1630, |
| "train_runtime": 266.224, |
| "train_tokens_per_second": 1919.106 |
| }, |
| { |
| "epoch": 18.166666666666668, |
| "grad_norm": 0.9085597395896912, |
| "learning_rate": 1.2842280840278997e-06, |
| "loss": 0.0386, |
| "num_input_tokens_seen": 512384, |
| "step": 1635, |
| "train_runtime": 266.9589, |
| "train_tokens_per_second": 1919.337 |
| }, |
| { |
| "epoch": 18.22222222222222, |
| "grad_norm": 0.7538381218910217, |
| "learning_rate": 1.2086502434241865e-06, |
| "loss": 0.0215, |
| "num_input_tokens_seen": 513952, |
| "step": 1640, |
| "train_runtime": 267.6859, |
| "train_tokens_per_second": 1919.981 |
| }, |
| { |
| "epoch": 18.27777777777778, |
| "grad_norm": 0.017959676682949066, |
| "learning_rate": 1.1353091938067023e-06, |
| "loss": 0.0395, |
| "num_input_tokens_seen": 515520, |
| "step": 1645, |
| "train_runtime": 268.4843, |
| "train_tokens_per_second": 1920.112 |
| }, |
| { |
| "epoch": 18.333333333333332, |
| "grad_norm": 0.9613012671470642, |
| "learning_rate": 1.0642118304798442e-06, |
| "loss": 0.0392, |
| "num_input_tokens_seen": 517120, |
| "step": 1650, |
| "train_runtime": 269.2113, |
| "train_tokens_per_second": 1920.87 |
| }, |
| { |
| "epoch": 18.38888888888889, |
| "grad_norm": 0.24886614084243774, |
| "learning_rate": 9.95364837803392e-07, |
| "loss": 0.1484, |
| "num_input_tokens_seen": 518688, |
| "step": 1655, |
| "train_runtime": 269.9469, |
| "train_tokens_per_second": 1921.444 |
| }, |
| { |
| "epoch": 18.444444444444443, |
| "grad_norm": 0.0767144188284874, |
| "learning_rate": 9.287746885640603e-07, |
| "loss": 0.064, |
| "num_input_tokens_seen": 520224, |
| "step": 1660, |
| "train_runtime": 270.6677, |
| "train_tokens_per_second": 1922.003 |
| }, |
| { |
| "epoch": 18.5, |
| "grad_norm": 0.028083791956305504, |
| "learning_rate": 8.64447643366953e-07, |
| "loss": 0.0058, |
| "num_input_tokens_seen": 521824, |
| "step": 1665, |
| "train_runtime": 271.3872, |
| "train_tokens_per_second": 1922.802 |
| }, |
| { |
| "epoch": 18.555555555555557, |
| "grad_norm": 0.02712034434080124, |
| "learning_rate": 8.023897500469391e-07, |
| "loss": 0.0357, |
| "num_input_tokens_seen": 523424, |
| "step": 1670, |
| "train_runtime": 272.1108, |
| "train_tokens_per_second": 1923.57 |
| }, |
| { |
| "epoch": 18.61111111111111, |
| "grad_norm": 0.21604163944721222, |
| "learning_rate": 7.426068431000882e-07, |
| "loss": 0.0135, |
| "num_input_tokens_seen": 524960, |
| "step": 1675, |
| "train_runtime": 272.8372, |
| "train_tokens_per_second": 1924.078 |
| }, |
| { |
| "epoch": 18.666666666666668, |
| "grad_norm": 0.018388254567980766, |
| "learning_rate": 6.851045431350927e-07, |
| "loss": 0.0227, |
| "num_input_tokens_seen": 526496, |
| "step": 1680, |
| "train_runtime": 273.564, |
| "train_tokens_per_second": 1924.581 |
| }, |
| { |
| "epoch": 18.72222222222222, |
| "grad_norm": 0.4869348704814911, |
| "learning_rate": 6.298882563448599e-07, |
| "loss": 0.0792, |
| "num_input_tokens_seen": 528064, |
| "step": 1685, |
| "train_runtime": 274.2916, |
| "train_tokens_per_second": 1925.192 |
| }, |
| { |
| "epoch": 18.77777777777778, |
| "grad_norm": 0.8644710779190063, |
| "learning_rate": 5.769631739982267e-07, |
| "loss": 0.0555, |
| "num_input_tokens_seen": 529632, |
| "step": 1690, |
| "train_runtime": 275.017, |
| "train_tokens_per_second": 1925.815 |
| }, |
| { |
| "epoch": 18.833333333333332, |
| "grad_norm": 0.19972096383571625, |
| "learning_rate": 5.263342719518921e-07, |
| "loss": 0.015, |
| "num_input_tokens_seen": 531232, |
| "step": 1695, |
| "train_runtime": 275.7339, |
| "train_tokens_per_second": 1926.611 |
| }, |
| { |
| "epoch": 18.88888888888889, |
| "grad_norm": 0.13014666736125946, |
| "learning_rate": 4.780063101826132e-07, |
| "loss": 0.0051, |
| "num_input_tokens_seen": 532800, |
| "step": 1700, |
| "train_runtime": 276.4579, |
| "train_tokens_per_second": 1927.237 |
| }, |
| { |
| "epoch": 18.944444444444443, |
| "grad_norm": 0.4027363955974579, |
| "learning_rate": 4.319838323396691e-07, |
| "loss": 0.0241, |
| "num_input_tokens_seen": 534400, |
| "step": 1705, |
| "train_runtime": 277.1752, |
| "train_tokens_per_second": 1928.023 |
| }, |
| { |
| "epoch": 19.0, |
| "grad_norm": 0.22673600912094116, |
| "learning_rate": 3.88271165317694e-07, |
| "loss": 0.0614, |
| "num_input_tokens_seen": 535968, |
| "step": 1710, |
| "train_runtime": 277.9233, |
| "train_tokens_per_second": 1928.475 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_loss": 0.06138663738965988, |
| "eval_runtime": 0.5312, |
| "eval_samples_per_second": 75.296, |
| "eval_steps_per_second": 18.824, |
| "num_input_tokens_seen": 535968, |
| "step": 1710 |
| }, |
| { |
| "epoch": 19.055555555555557, |
| "grad_norm": 0.3861265182495117, |
| "learning_rate": 3.468724188498751e-07, |
| "loss": 0.0172, |
| "num_input_tokens_seen": 537536, |
| "step": 1715, |
| "train_runtime": 280.0071, |
| "train_tokens_per_second": 1919.723 |
| }, |
| { |
| "epoch": 19.11111111111111, |
| "grad_norm": 0.4449467957019806, |
| "learning_rate": 3.077914851215585e-07, |
| "loss": 0.0148, |
| "num_input_tokens_seen": 539072, |
| "step": 1720, |
| "train_runtime": 280.754, |
| "train_tokens_per_second": 1920.087 |
| }, |
| { |
| "epoch": 19.166666666666668, |
| "grad_norm": 0.09849676489830017, |
| "learning_rate": 2.71032038404323e-07, |
| "loss": 0.0522, |
| "num_input_tokens_seen": 540608, |
| "step": 1725, |
| "train_runtime": 281.488, |
| "train_tokens_per_second": 1920.537 |
| }, |
| { |
| "epoch": 19.22222222222222, |
| "grad_norm": 0.3086458146572113, |
| "learning_rate": 2.365975347105448e-07, |
| "loss": 0.1071, |
| "num_input_tokens_seen": 542208, |
| "step": 1730, |
| "train_runtime": 282.2214, |
| "train_tokens_per_second": 1921.215 |
| }, |
| { |
| "epoch": 19.27777777777778, |
| "grad_norm": 1.7546472549438477, |
| "learning_rate": 2.0449121146845774e-07, |
| "loss": 0.0479, |
| "num_input_tokens_seen": 543776, |
| "step": 1735, |
| "train_runtime": 283.019, |
| "train_tokens_per_second": 1921.341 |
| }, |
| { |
| "epoch": 19.333333333333332, |
| "grad_norm": 1.386121153831482, |
| "learning_rate": 1.747160872177883e-07, |
| "loss": 0.0542, |
| "num_input_tokens_seen": 545280, |
| "step": 1740, |
| "train_runtime": 283.7447, |
| "train_tokens_per_second": 1921.727 |
| }, |
| { |
| "epoch": 19.38888888888889, |
| "grad_norm": 0.21310308575630188, |
| "learning_rate": 1.472749613259661e-07, |
| "loss": 0.0952, |
| "num_input_tokens_seen": 546848, |
| "step": 1745, |
| "train_runtime": 284.4692, |
| "train_tokens_per_second": 1922.345 |
| }, |
| { |
| "epoch": 19.444444444444443, |
| "grad_norm": 0.484055757522583, |
| "learning_rate": 1.22170413724923e-07, |
| "loss": 0.0119, |
| "num_input_tokens_seen": 548416, |
| "step": 1750, |
| "train_runtime": 285.1914, |
| "train_tokens_per_second": 1922.975 |
| }, |
| { |
| "epoch": 19.5, |
| "grad_norm": 0.11522525548934937, |
| "learning_rate": 9.940480466855417e-08, |
| "loss": 0.0149, |
| "num_input_tokens_seen": 550016, |
| "step": 1755, |
| "train_runtime": 285.9187, |
| "train_tokens_per_second": 1923.68 |
| }, |
| { |
| "epoch": 19.555555555555557, |
| "grad_norm": 0.22439134120941162, |
| "learning_rate": 7.898027451078982e-08, |
| "loss": 0.0109, |
| "num_input_tokens_seen": 551584, |
| "step": 1760, |
| "train_runtime": 286.6439, |
| "train_tokens_per_second": 1924.283 |
| }, |
| { |
| "epoch": 19.61111111111111, |
| "grad_norm": 0.30249354243278503, |
| "learning_rate": 6.089874350439506e-08, |
| "loss": 0.0504, |
| "num_input_tokens_seen": 553152, |
| "step": 1765, |
| "train_runtime": 287.3754, |
| "train_tokens_per_second": 1924.841 |
| }, |
| { |
| "epoch": 19.666666666666668, |
| "grad_norm": 1.4332835674285889, |
| "learning_rate": 4.516191162040051e-08, |
| "loss": 0.0612, |
| "num_input_tokens_seen": 554752, |
| "step": 1770, |
| "train_runtime": 288.1001, |
| "train_tokens_per_second": 1925.553 |
| }, |
| { |
| "epoch": 19.72222222222222, |
| "grad_norm": 0.00620208540931344, |
| "learning_rate": 3.177125838830786e-08, |
| "loss": 0.0222, |
| "num_input_tokens_seen": 556288, |
| "step": 1775, |
| "train_runtime": 288.8278, |
| "train_tokens_per_second": 1926.02 |
| }, |
| { |
| "epoch": 19.77777777777778, |
| "grad_norm": 0.9789679050445557, |
| "learning_rate": 2.0728042756967824e-08, |
| "loss": 0.0446, |
| "num_input_tokens_seen": 557888, |
| "step": 1780, |
| "train_runtime": 289.5544, |
| "train_tokens_per_second": 1926.712 |
| }, |
| { |
| "epoch": 19.833333333333332, |
| "grad_norm": 0.006394943222403526, |
| "learning_rate": 1.2033302976222071e-08, |
| "loss": 0.0178, |
| "num_input_tokens_seen": 559424, |
| "step": 1785, |
| "train_runtime": 290.2832, |
| "train_tokens_per_second": 1927.166 |
| }, |
| { |
| "epoch": 19.88888888888889, |
| "grad_norm": 0.8413034081459045, |
| "learning_rate": 5.687856499297928e-09, |
| "loss": 0.0878, |
| "num_input_tokens_seen": 560960, |
| "step": 1790, |
| "train_runtime": 291.0104, |
| "train_tokens_per_second": 1927.629 |
| }, |
| { |
| "epoch": 19.944444444444443, |
| "grad_norm": 0.5030195116996765, |
| "learning_rate": 1.692299905944883e-09, |
| "loss": 0.0524, |
| "num_input_tokens_seen": 562592, |
| "step": 1795, |
| "train_runtime": 291.7296, |
| "train_tokens_per_second": 1928.471 |
| }, |
| { |
| "epoch": 20.0, |
| "grad_norm": 0.01651857979595661, |
| "learning_rate": 4.700884634611935e-11, |
| "loss": 0.0111, |
| "num_input_tokens_seen": 564096, |
| "step": 1800, |
| "train_runtime": 292.485, |
| "train_tokens_per_second": 1928.632 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_loss": 0.06419730186462402, |
| "eval_runtime": 0.5388, |
| "eval_samples_per_second": 74.238, |
| "eval_steps_per_second": 18.56, |
| "num_input_tokens_seen": 564096, |
| "step": 1800 |
| }, |
| { |
| "epoch": 20.0, |
| "num_input_tokens_seen": 564096, |
| "step": 1800, |
| "total_flos": 2.540165336137728e+16, |
| "train_loss": 0.10145172014832497, |
| "train_runtime": 294.5966, |
| "train_samples_per_second": 24.44, |
| "train_steps_per_second": 6.11 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 1800, |
| "num_input_tokens_seen": 564096, |
| "num_train_epochs": 20, |
| "save_steps": 90, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.540165336137728e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
