| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.230549607423269, | |
| "global_step": 50000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.3999999999999997e-05, | |
| "loss": 0.8845, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.7999999999999994e-05, | |
| "loss": 0.689, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 0.6793121099472046, | |
| "eval_runtime": 2.3939, | |
| "eval_samples_per_second": 959.513, | |
| "eval_steps_per_second": 15.038, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 7.199999999999999e-05, | |
| "loss": 0.6805, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.599999999999999e-05, | |
| "loss": 0.6802, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 0.6786620616912842, | |
| "eval_runtime": 2.1637, | |
| "eval_samples_per_second": 1061.605, | |
| "eval_steps_per_second": 16.638, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.6799, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00014399999999999998, | |
| "loss": 0.6795, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 0.6788004040718079, | |
| "eval_runtime": 2.1379, | |
| "eval_samples_per_second": 1074.407, | |
| "eval_steps_per_second": 16.839, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.000168, | |
| "loss": 0.6791, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00019199999999999998, | |
| "loss": 0.679, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 0.6781774163246155, | |
| "eval_runtime": 2.1652, | |
| "eval_samples_per_second": 1060.868, | |
| "eval_steps_per_second": 16.627, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00021599999999999996, | |
| "loss": 0.6788, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.6787, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 0.6782493591308594, | |
| "eval_runtime": 2.1305, | |
| "eval_samples_per_second": 1078.133, | |
| "eval_steps_per_second": 16.897, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00026399999999999997, | |
| "loss": 0.6786, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00028799999999999995, | |
| "loss": 0.6786, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 0.6780672073364258, | |
| "eval_runtime": 2.1865, | |
| "eval_samples_per_second": 1050.561, | |
| "eval_steps_per_second": 16.465, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.000312, | |
| "loss": 0.6785, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.000336, | |
| "loss": 0.6784, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 0.6781116724014282, | |
| "eval_runtime": 2.1436, | |
| "eval_samples_per_second": 1071.581, | |
| "eval_steps_per_second": 16.794, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00035999999999999997, | |
| "loss": 0.6783, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00038399999999999996, | |
| "loss": 0.6783, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 0.6780590415000916, | |
| "eval_runtime": 2.0716, | |
| "eval_samples_per_second": 1108.795, | |
| "eval_steps_per_second": 17.378, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.000408, | |
| "loss": 0.6783, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00043199999999999993, | |
| "loss": 0.6781, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.677251398563385, | |
| "eval_runtime": 2.0351, | |
| "eval_samples_per_second": 1128.706, | |
| "eval_steps_per_second": 17.69, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00045599999999999997, | |
| "loss": 0.6776, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00047999999999999996, | |
| "loss": 0.6775, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 0.6778020262718201, | |
| "eval_runtime": 2.2347, | |
| "eval_samples_per_second": 1027.899, | |
| "eval_steps_per_second": 16.11, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0005039999999999999, | |
| "loss": 0.6775, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0005279999999999999, | |
| "loss": 0.6775, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 0.6769479513168335, | |
| "eval_runtime": 2.177, | |
| "eval_samples_per_second": 1055.099, | |
| "eval_steps_per_second": 16.536, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.000552, | |
| "loss": 0.6773, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0005759999999999999, | |
| "loss": 0.6773, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 0.6773238182067871, | |
| "eval_runtime": 2.1281, | |
| "eval_samples_per_second": 1079.366, | |
| "eval_steps_per_second": 16.916, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0006, | |
| "loss": 0.6773, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0005999935478721662, | |
| "loss": 0.6774, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 0.677127480506897, | |
| "eval_runtime": 2.1773, | |
| "eval_samples_per_second": 1054.986, | |
| "eval_steps_per_second": 16.534, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.000599974191770902, | |
| "loss": 0.6773, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0005999419325429058, | |
| "loss": 0.6773, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 0.6771531105041504, | |
| "eval_runtime": 2.1173, | |
| "eval_samples_per_second": 1084.86, | |
| "eval_steps_per_second": 17.003, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0005998967715993009, | |
| "loss": 0.6773, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0005998387109155732, | |
| "loss": 0.6773, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 0.6771678924560547, | |
| "eval_runtime": 2.1919, | |
| "eval_samples_per_second": 1047.963, | |
| "eval_steps_per_second": 16.424, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.000599767753031485, | |
| "loss": 0.6773, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0005996839010509641, | |
| "loss": 0.6772, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 0.6776318550109863, | |
| "eval_runtime": 2.199, | |
| "eval_samples_per_second": 1044.559, | |
| "eval_steps_per_second": 16.371, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0005995871586419678, | |
| "loss": 0.6773, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0005994775300363225, | |
| "loss": 0.6773, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.676984429359436, | |
| "eval_runtime": 2.1946, | |
| "eval_samples_per_second": 1046.652, | |
| "eval_steps_per_second": 16.404, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0005993550200295384, | |
| "loss": 0.6772, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0005992196339806002, | |
| "loss": 0.6772, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.6774880290031433, | |
| "eval_runtime": 2.1027, | |
| "eval_samples_per_second": 1092.415, | |
| "eval_steps_per_second": 17.121, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0005990713778117324, | |
| "loss": 0.6773, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0005989102580081398, | |
| "loss": 0.6772, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 0.676984965801239, | |
| "eval_runtime": 2.1686, | |
| "eval_samples_per_second": 1059.223, | |
| "eval_steps_per_second": 16.601, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0005987362816177249, | |
| "loss": 0.6773, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0005985494562507783, | |
| "loss": 0.6774, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 0.6769698262214661, | |
| "eval_runtime": 2.1456, | |
| "eval_samples_per_second": 1070.586, | |
| "eval_steps_per_second": 16.779, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.000598349790079647, | |
| "loss": 0.6773, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.000598137291838376, | |
| "loss": 0.6772, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 0.6761835217475891, | |
| "eval_runtime": 2.1367, | |
| "eval_samples_per_second": 1075.027, | |
| "eval_steps_per_second": 16.848, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.000597911970822327, | |
| "loss": 0.6772, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.000597673836887771, | |
| "loss": 0.6773, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 0.6774830222129822, | |
| "eval_runtime": 2.1107, | |
| "eval_samples_per_second": 1088.282, | |
| "eval_steps_per_second": 17.056, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0005974229004514577, | |
| "loss": 0.6773, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0005971591724901598, | |
| "loss": 0.6773, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 0.6764113903045654, | |
| "eval_runtime": 2.206, | |
| "eval_samples_per_second": 1041.236, | |
| "eval_steps_per_second": 16.319, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0005968826645401927, | |
| "loss": 0.6772, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00059659338869691, | |
| "loss": 0.6772, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 0.6768463253974915, | |
| "eval_runtime": 2.2173, | |
| "eval_samples_per_second": 1035.939, | |
| "eval_steps_per_second": 16.236, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0005962913576141742, | |
| "loss": 0.6773, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.000595976584503803, | |
| "loss": 0.6772, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 0.6769193410873413, | |
| "eval_runtime": 2.2077, | |
| "eval_samples_per_second": 1040.465, | |
| "eval_steps_per_second": 16.307, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0005956490831349923, | |
| "loss": 0.6773, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0005953088678337129, | |
| "loss": 0.6772, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 0.6775402426719666, | |
| "eval_runtime": 2.2094, | |
| "eval_samples_per_second": 1039.671, | |
| "eval_steps_per_second": 16.294, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.0005949559534820841, | |
| "loss": 0.6772, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0005945903555177229, | |
| "loss": 0.6772, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 0.6775718331336975, | |
| "eval_runtime": 2.1372, | |
| "eval_samples_per_second": 1074.76, | |
| "eval_steps_per_second": 16.844, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0005942120899330687, | |
| "loss": 0.6772, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0005938211732746836, | |
| "loss": 0.6772, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 0.6771659255027771, | |
| "eval_runtime": 2.191, | |
| "eval_samples_per_second": 1048.378, | |
| "eval_steps_per_second": 16.431, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0005934176226425286, | |
| "loss": 0.6772, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0005930014556892158, | |
| "loss": 0.6772, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 0.6768732666969299, | |
| "eval_runtime": 2.2912, | |
| "eval_samples_per_second": 1002.553, | |
| "eval_steps_per_second": 15.713, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0005925726906192357, | |
| "loss": 0.6772, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0005921313461881617, | |
| "loss": 0.6773, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_loss": 0.6772350072860718, | |
| "eval_runtime": 2.2465, | |
| "eval_samples_per_second": 1022.498, | |
| "eval_steps_per_second": 16.025, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0005916774417018287, | |
| "loss": 0.6772, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0005912109970154897, | |
| "loss": 0.6772, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 0.6777171492576599, | |
| "eval_runtime": 2.1569, | |
| "eval_samples_per_second": 1064.935, | |
| "eval_steps_per_second": 16.69, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0005907320325329461, | |
| "loss": 0.6772, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0005902405692056561, | |
| "loss": 0.6772, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 0.676947832107544, | |
| "eval_runtime": 2.3119, | |
| "eval_samples_per_second": 993.573, | |
| "eval_steps_per_second": 15.572, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.0005897366285318178, | |
| "loss": 0.6772, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0005892202325554288, | |
| "loss": 0.6773, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 0.6766595840454102, | |
| "eval_runtime": 2.1462, | |
| "eval_samples_per_second": 1070.248, | |
| "eval_steps_per_second": 16.774, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.0005886914038653217, | |
| "loss": 0.6772, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.0005881501655941771, | |
| "loss": 0.677, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 0.6765649914741516, | |
| "eval_runtime": 2.1369, | |
| "eval_samples_per_second": 1074.929, | |
| "eval_steps_per_second": 16.847, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00058759654141751, | |
| "loss": 0.6768, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0005870305555526355, | |
| "loss": 0.6765, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 0.676632821559906, | |
| "eval_runtime": 2.2745, | |
| "eval_samples_per_second": 1009.888, | |
| "eval_steps_per_second": 15.828, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.0005864522327576088, | |
| "loss": 0.6764, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0005858615983301424, | |
| "loss": 0.6763, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 0.6765820980072021, | |
| "eval_runtime": 2.1766, | |
| "eval_samples_per_second": 1055.304, | |
| "eval_steps_per_second": 16.539, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0005852586781064997, | |
| "loss": 0.6763, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0005846434984603645, | |
| "loss": 0.6764, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_loss": 0.6758345365524292, | |
| "eval_runtime": 2.237, | |
| "eval_samples_per_second": 1026.821, | |
| "eval_steps_per_second": 16.093, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0005840160863016872, | |
| "loss": 0.6763, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.0005833764690755083, | |
| "loss": 0.6764, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 0.6762025952339172, | |
| "eval_runtime": 2.1722, | |
| "eval_samples_per_second": 1057.45, | |
| "eval_steps_per_second": 16.573, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.0005827246747607574, | |
| "loss": 0.6765, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0005820607318690293, | |
| "loss": 0.6758, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_loss": 0.6771443486213684, | |
| "eval_runtime": 2.2147, | |
| "eval_samples_per_second": 1037.153, | |
| "eval_steps_per_second": 16.255, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0005813846694433368, | |
| "loss": 0.6773, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.0005806965170568409, | |
| "loss": 0.6772, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_loss": 0.6770426630973816, | |
| "eval_runtime": 2.1711, | |
| "eval_samples_per_second": 1057.979, | |
| "eval_steps_per_second": 16.581, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.0005799963048115559, | |
| "loss": 0.6757, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.0005792840633370341, | |
| "loss": 0.6575, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_loss": 0.6465174555778503, | |
| "eval_runtime": 2.2243, | |
| "eval_samples_per_second": 1032.694, | |
| "eval_steps_per_second": 16.185, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0005785598237890247, | |
| "loss": 0.6461, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0005778236178481119, | |
| "loss": 0.6373, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 0.631793737411499, | |
| "eval_runtime": 2.22, | |
| "eval_samples_per_second": 1034.694, | |
| "eval_steps_per_second": 16.216, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.0005770754777183285, | |
| "loss": 0.6309, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0005763154361257473, | |
| "loss": 0.6257, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.6184197664260864, | |
| "eval_runtime": 2.2848, | |
| "eval_samples_per_second": 1005.32, | |
| "eval_steps_per_second": 15.756, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0005755435263170498, | |
| "loss": 0.623, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.0005747597820580717, | |
| "loss": 0.621, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 0.6136025786399841, | |
| "eval_runtime": 2.2706, | |
| "eval_samples_per_second": 1011.621, | |
| "eval_steps_per_second": 15.855, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.000573964237632326, | |
| "loss": 0.6195, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.0005731569278395029, | |
| "loss": 0.6183, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_loss": 0.6127315163612366, | |
| "eval_runtime": 2.1317, | |
| "eval_samples_per_second": 1077.566, | |
| "eval_steps_per_second": 16.888, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.0005723378879939481, | |
| "loss": 0.6172, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.0005715071539231178, | |
| "loss": 0.6165, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "eval_loss": 0.6103396415710449, | |
| "eval_runtime": 2.1687, | |
| "eval_samples_per_second": 1059.145, | |
| "eval_steps_per_second": 16.6, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.0005706647619660116, | |
| "loss": 0.6155, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.0005698107489715823, | |
| "loss": 0.612, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_loss": 0.6013069748878479, | |
| "eval_runtime": 2.2612, | |
| "eval_samples_per_second": 1015.821, | |
| "eval_steps_per_second": 15.921, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.0005689451522971252, | |
| "loss": 0.6068, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0005680680098066429, | |
| "loss": 0.6037, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_loss": 0.5942632555961609, | |
| "eval_runtime": 2.2238, | |
| "eval_samples_per_second": 1032.912, | |
| "eval_steps_per_second": 16.188, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.0005671793598691895, | |
| "loss": 0.6015, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.0005662792413571921, | |
| "loss": 0.6, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_loss": 0.5915176868438721, | |
| "eval_runtime": 2.2389, | |
| "eval_samples_per_second": 1025.951, | |
| "eval_steps_per_second": 16.079, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.0005653676936447504, | |
| "loss": 0.5986, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.0005644447566059142, | |
| "loss": 0.5973, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "eval_loss": 0.5880685448646545, | |
| "eval_runtime": 2.2056, | |
| "eval_samples_per_second": 1041.459, | |
| "eval_steps_per_second": 16.322, | |
| "step": 50000 | |
| } | |
| ], | |
| "max_steps": 250000, | |
| "num_train_epochs": 12, | |
| "total_flos": 8.008257503646733e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |