| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.9938916950546224, | |
| "eval_steps": 500, | |
| "global_step": 34000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.4679976512037582e-06, | |
| "loss": 0.412, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 0.06404077261686325, | |
| "eval_runtime": 119.6505, | |
| "eval_samples_per_second": 54.676, | |
| "eval_steps_per_second": 6.837, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.9359953024075165e-06, | |
| "loss": 0.0572, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 0.033456169068813324, | |
| "eval_runtime": 119.4711, | |
| "eval_samples_per_second": 54.758, | |
| "eval_steps_per_second": 6.847, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.403992953611275e-06, | |
| "loss": 0.0392, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 0.027742423117160797, | |
| "eval_runtime": 119.6338, | |
| "eval_samples_per_second": 54.684, | |
| "eval_steps_per_second": 6.838, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 5.871990604815033e-06, | |
| "loss": 0.0339, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 0.024982118979096413, | |
| "eval_runtime": 119.4896, | |
| "eval_samples_per_second": 54.75, | |
| "eval_steps_per_second": 6.846, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.33998825601879e-06, | |
| "loss": 0.0321, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 0.02286355197429657, | |
| "eval_runtime": 119.7537, | |
| "eval_samples_per_second": 54.629, | |
| "eval_steps_per_second": 6.831, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.80798590722255e-06, | |
| "loss": 0.0286, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 0.02225133590400219, | |
| "eval_runtime": 115.351, | |
| "eval_samples_per_second": 56.714, | |
| "eval_steps_per_second": 7.091, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.969327155256804e-06, | |
| "loss": 0.0265, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 0.02050725743174553, | |
| "eval_runtime": 115.364, | |
| "eval_samples_per_second": 56.707, | |
| "eval_steps_per_second": 7.091, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.806173725771716e-06, | |
| "loss": 0.026, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 0.020657476037740707, | |
| "eval_runtime": 118.0643, | |
| "eval_samples_per_second": 55.41, | |
| "eval_steps_per_second": 6.928, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.64302029628663e-06, | |
| "loss": 0.0238, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 0.019942762330174446, | |
| "eval_runtime": 119.4625, | |
| "eval_samples_per_second": 54.762, | |
| "eval_steps_per_second": 6.847, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.479866866801542e-06, | |
| "loss": 0.0251, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 0.020365213975310326, | |
| "eval_runtime": 119.5062, | |
| "eval_samples_per_second": 54.742, | |
| "eval_steps_per_second": 6.845, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.316713437316454e-06, | |
| "loss": 0.0244, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 0.02077455259859562, | |
| "eval_runtime": 119.2739, | |
| "eval_samples_per_second": 54.849, | |
| "eval_steps_per_second": 6.858, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.153560007831366e-06, | |
| "loss": 0.0235, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 0.019606556743383408, | |
| "eval_runtime": 119.4635, | |
| "eval_samples_per_second": 54.761, | |
| "eval_steps_per_second": 6.847, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 8.990406578346278e-06, | |
| "loss": 0.0232, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.01969091035425663, | |
| "eval_runtime": 119.7331, | |
| "eval_samples_per_second": 54.638, | |
| "eval_steps_per_second": 6.832, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.82725314886119e-06, | |
| "loss": 0.0225, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 0.019132908433675766, | |
| "eval_runtime": 119.5514, | |
| "eval_samples_per_second": 54.721, | |
| "eval_steps_per_second": 6.842, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 8.664099719376103e-06, | |
| "loss": 0.0212, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 0.018609512597322464, | |
| "eval_runtime": 119.4541, | |
| "eval_samples_per_second": 54.766, | |
| "eval_steps_per_second": 6.848, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 8.500946289891015e-06, | |
| "loss": 0.0225, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 0.018011104315519333, | |
| "eval_runtime": 116.0368, | |
| "eval_samples_per_second": 56.379, | |
| "eval_steps_per_second": 7.049, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 8.337792860405927e-06, | |
| "loss": 0.0231, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.01797027327120304, | |
| "eval_runtime": 115.2093, | |
| "eval_samples_per_second": 56.784, | |
| "eval_steps_per_second": 7.1, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 8.174639430920839e-06, | |
| "loss": 0.018, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 0.018307719379663467, | |
| "eval_runtime": 116.9177, | |
| "eval_samples_per_second": 55.954, | |
| "eval_steps_per_second": 6.996, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 8.01148600143575e-06, | |
| "loss": 0.0178, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 0.018220532685518265, | |
| "eval_runtime": 119.4643, | |
| "eval_samples_per_second": 54.761, | |
| "eval_steps_per_second": 6.847, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 7.848332571950663e-06, | |
| "loss": 0.0173, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_loss": 0.018342604860663414, | |
| "eval_runtime": 119.7353, | |
| "eval_samples_per_second": 54.637, | |
| "eval_steps_per_second": 6.832, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 7.685179142465575e-06, | |
| "loss": 0.0176, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 0.01870131492614746, | |
| "eval_runtime": 119.9453, | |
| "eval_samples_per_second": 54.542, | |
| "eval_steps_per_second": 6.82, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 7.5220257129804875e-06, | |
| "loss": 0.0177, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 0.018137916922569275, | |
| "eval_runtime": 119.817, | |
| "eval_samples_per_second": 54.6, | |
| "eval_steps_per_second": 6.827, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 7.358872283495399e-06, | |
| "loss": 0.0171, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 0.018740132451057434, | |
| "eval_runtime": 119.4709, | |
| "eval_samples_per_second": 54.758, | |
| "eval_steps_per_second": 6.847, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 7.195718854010312e-06, | |
| "loss": 0.019, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 0.018057728186249733, | |
| "eval_runtime": 119.9707, | |
| "eval_samples_per_second": 54.53, | |
| "eval_steps_per_second": 6.818, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 7.032565424525224e-06, | |
| "loss": 0.0174, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 0.018135011196136475, | |
| "eval_runtime": 119.6311, | |
| "eval_samples_per_second": 54.685, | |
| "eval_steps_per_second": 6.838, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 6.869411995040136e-06, | |
| "loss": 0.0179, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 0.017942175269126892, | |
| "eval_runtime": 117.6519, | |
| "eval_samples_per_second": 55.605, | |
| "eval_steps_per_second": 6.953, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 6.706258565555048e-06, | |
| "loss": 0.0166, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 0.01796996220946312, | |
| "eval_runtime": 115.4295, | |
| "eval_samples_per_second": 56.675, | |
| "eval_steps_per_second": 7.087, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 6.543105136069961e-06, | |
| "loss": 0.0174, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 0.018622903153300285, | |
| "eval_runtime": 116.043, | |
| "eval_samples_per_second": 56.376, | |
| "eval_steps_per_second": 7.049, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 6.379951706584873e-06, | |
| "loss": 0.0162, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 0.017875785008072853, | |
| "eval_runtime": 119.775, | |
| "eval_samples_per_second": 54.619, | |
| "eval_steps_per_second": 6.829, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 6.216798277099785e-06, | |
| "loss": 0.0163, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 0.018203964456915855, | |
| "eval_runtime": 119.7603, | |
| "eval_samples_per_second": 54.626, | |
| "eval_steps_per_second": 6.83, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 6.0536448476146966e-06, | |
| "loss": 0.0168, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_loss": 0.017764363437891006, | |
| "eval_runtime": 119.5774, | |
| "eval_samples_per_second": 54.709, | |
| "eval_steps_per_second": 6.841, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 5.890491418129609e-06, | |
| "loss": 0.0178, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 0.017852840945124626, | |
| "eval_runtime": 119.5232, | |
| "eval_samples_per_second": 54.734, | |
| "eval_steps_per_second": 6.844, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 5.727337988644521e-06, | |
| "loss": 0.0168, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_loss": 0.017764879390597343, | |
| "eval_runtime": 119.6082, | |
| "eval_samples_per_second": 54.695, | |
| "eval_steps_per_second": 6.839, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 5.564184559159433e-06, | |
| "loss": 0.0168, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.017377818003296852, | |
| "eval_runtime": 119.6291, | |
| "eval_samples_per_second": 54.686, | |
| "eval_steps_per_second": 6.838, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 5.401031129674347e-06, | |
| "loss": 0.0143, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 0.017800554633140564, | |
| "eval_runtime": 119.9539, | |
| "eval_samples_per_second": 54.538, | |
| "eval_steps_per_second": 6.819, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 5.237877700189259e-06, | |
| "loss": 0.014, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_loss": 0.0179632306098938, | |
| "eval_runtime": 118.0782, | |
| "eval_samples_per_second": 55.404, | |
| "eval_steps_per_second": 6.928, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 5.074724270704171e-06, | |
| "loss": 0.0143, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_loss": 0.018571963533759117, | |
| "eval_runtime": 115.3792, | |
| "eval_samples_per_second": 56.7, | |
| "eval_steps_per_second": 7.09, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 4.911570841219083e-06, | |
| "loss": 0.0137, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "eval_loss": 0.018732914701104164, | |
| "eval_runtime": 116.2594, | |
| "eval_samples_per_second": 56.271, | |
| "eval_steps_per_second": 7.036, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 4.748417411733995e-06, | |
| "loss": 0.0131, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "eval_loss": 0.018157465383410454, | |
| "eval_runtime": 119.6325, | |
| "eval_samples_per_second": 54.684, | |
| "eval_steps_per_second": 6.838, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 4.585263982248907e-06, | |
| "loss": 0.0134, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "eval_loss": 0.01858236826956272, | |
| "eval_runtime": 119.626, | |
| "eval_samples_per_second": 54.687, | |
| "eval_steps_per_second": 6.838, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 4.42211055276382e-06, | |
| "loss": 0.0131, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_loss": 0.01760929264128208, | |
| "eval_runtime": 119.8276, | |
| "eval_samples_per_second": 54.595, | |
| "eval_steps_per_second": 6.826, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 4.258957123278732e-06, | |
| "loss": 0.0138, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_loss": 0.01776733435690403, | |
| "eval_runtime": 119.5072, | |
| "eval_samples_per_second": 54.741, | |
| "eval_steps_per_second": 6.845, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.095803693793644e-06, | |
| "loss": 0.0131, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 0.018140822649002075, | |
| "eval_runtime": 119.8335, | |
| "eval_samples_per_second": 54.592, | |
| "eval_steps_per_second": 6.826, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 3.932650264308556e-06, | |
| "loss": 0.0139, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "eval_loss": 0.018083902075886726, | |
| "eval_runtime": 120.1704, | |
| "eval_samples_per_second": 54.439, | |
| "eval_steps_per_second": 6.807, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.7694968348234683e-06, | |
| "loss": 0.0139, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 0.018096571788191795, | |
| "eval_runtime": 119.7812, | |
| "eval_samples_per_second": 54.616, | |
| "eval_steps_per_second": 6.829, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 3.6063434053383807e-06, | |
| "loss": 0.0133, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 0.01770329661667347, | |
| "eval_runtime": 118.2737, | |
| "eval_samples_per_second": 55.312, | |
| "eval_steps_per_second": 6.916, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 3.4431899758532926e-06, | |
| "loss": 0.0135, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 0.01808938756585121, | |
| "eval_runtime": 115.7874, | |
| "eval_samples_per_second": 56.5, | |
| "eval_steps_per_second": 7.065, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 3.280036546368205e-06, | |
| "loss": 0.0131, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "eval_loss": 0.017787907272577286, | |
| "eval_runtime": 115.8567, | |
| "eval_samples_per_second": 56.466, | |
| "eval_steps_per_second": 7.06, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 3.116883116883117e-06, | |
| "loss": 0.0137, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_loss": 0.017733994871377945, | |
| "eval_runtime": 120.2603, | |
| "eval_samples_per_second": 54.399, | |
| "eval_steps_per_second": 6.802, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 2.9537296873980292e-06, | |
| "loss": 0.0133, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_loss": 0.017949102446436882, | |
| "eval_runtime": 119.971, | |
| "eval_samples_per_second": 54.53, | |
| "eval_steps_per_second": 6.818, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 2.7905762579129416e-06, | |
| "loss": 0.0136, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.017474107444286346, | |
| "eval_runtime": 119.96, | |
| "eval_samples_per_second": 54.535, | |
| "eval_steps_per_second": 6.819, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 2.6274228284278535e-06, | |
| "loss": 0.0124, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_loss": 0.018201593309640884, | |
| "eval_runtime": 119.9656, | |
| "eval_samples_per_second": 54.532, | |
| "eval_steps_per_second": 6.819, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 2.464269398942766e-06, | |
| "loss": 0.0121, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "eval_loss": 0.01811986044049263, | |
| "eval_runtime": 119.7914, | |
| "eval_samples_per_second": 54.612, | |
| "eval_steps_per_second": 6.829, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 2.3011159694576783e-06, | |
| "loss": 0.012, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "eval_loss": 0.018191542476415634, | |
| "eval_runtime": 119.8265, | |
| "eval_samples_per_second": 54.596, | |
| "eval_steps_per_second": 6.827, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 2.13796253997259e-06, | |
| "loss": 0.0115, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "eval_loss": 0.018120231106877327, | |
| "eval_runtime": 119.6169, | |
| "eval_samples_per_second": 54.691, | |
| "eval_steps_per_second": 6.839, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 1.9748091104875025e-06, | |
| "loss": 0.0117, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "eval_loss": 0.017889145761728287, | |
| "eval_runtime": 118.9939, | |
| "eval_samples_per_second": 54.978, | |
| "eval_steps_per_second": 6.874, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 1.811655681002415e-06, | |
| "loss": 0.0113, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "eval_loss": 0.017741482704877853, | |
| "eval_runtime": 115.6814, | |
| "eval_samples_per_second": 56.552, | |
| "eval_steps_per_second": 7.071, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 1.648502251517327e-06, | |
| "loss": 0.0124, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "eval_loss": 0.017794128507375717, | |
| "eval_runtime": 115.7328, | |
| "eval_samples_per_second": 56.527, | |
| "eval_steps_per_second": 7.068, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 1.4853488220322392e-06, | |
| "loss": 0.012, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "eval_loss": 0.018301891162991524, | |
| "eval_runtime": 119.5898, | |
| "eval_samples_per_second": 54.704, | |
| "eval_steps_per_second": 6.84, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 1.3221953925471516e-06, | |
| "loss": 0.0119, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "eval_loss": 0.01817336678504944, | |
| "eval_runtime": 120.0384, | |
| "eval_samples_per_second": 54.499, | |
| "eval_steps_per_second": 6.814, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 1.1590419630620637e-06, | |
| "loss": 0.0115, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "eval_loss": 0.018085774034261703, | |
| "eval_runtime": 119.7931, | |
| "eval_samples_per_second": 54.611, | |
| "eval_steps_per_second": 6.828, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 9.958885335769758e-07, | |
| "loss": 0.012, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "eval_loss": 0.017980104312300682, | |
| "eval_runtime": 119.8348, | |
| "eval_samples_per_second": 54.592, | |
| "eval_steps_per_second": 6.826, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 8.327351040918881e-07, | |
| "loss": 0.0116, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "eval_loss": 0.0181511789560318, | |
| "eval_runtime": 119.9569, | |
| "eval_samples_per_second": 54.536, | |
| "eval_steps_per_second": 6.819, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 6.695816746068002e-07, | |
| "loss": 0.0108, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "eval_loss": 0.018154002726078033, | |
| "eval_runtime": 119.8401, | |
| "eval_samples_per_second": 54.589, | |
| "eval_steps_per_second": 6.826, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 5.064282451217125e-07, | |
| "loss": 0.0118, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "eval_loss": 0.01812034100294113, | |
| "eval_runtime": 120.1728, | |
| "eval_samples_per_second": 54.438, | |
| "eval_steps_per_second": 6.807, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 3.4327481563662475e-07, | |
| "loss": 0.0114, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "eval_loss": 0.018135515972971916, | |
| "eval_runtime": 119.8212, | |
| "eval_samples_per_second": 54.598, | |
| "eval_steps_per_second": 6.827, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 1.801213861515369e-07, | |
| "loss": 0.0121, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_loss": 0.01807536743581295, | |
| "eval_runtime": 115.6623, | |
| "eval_samples_per_second": 56.561, | |
| "eval_steps_per_second": 7.072, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 1.6967956666449132e-08, | |
| "loss": 0.0112, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_loss": 0.01807805709540844, | |
| "eval_runtime": 115.5079, | |
| "eval_samples_per_second": 56.637, | |
| "eval_steps_per_second": 7.082, | |
| "step": 34000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 34052, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 3.237991334295552e+16, | |
| "train_batch_size": 18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |