| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 5000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.296875, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 6.02, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 5.3902, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.2734375, | |
| "learning_rate": 2.5e-05, | |
| "loss": 4.6611, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 7.71875, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 3.8627, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 2.3529, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4613, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.4453125, | |
| "learning_rate": 4.999672209164081e-05, | |
| "loss": 1.3771, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.5546875, | |
| "learning_rate": 4.998688922613788e-05, | |
| "loss": 1.3205, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.73046875, | |
| "learning_rate": 4.997050398198977e-05, | |
| "loss": 1.2926, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.50390625, | |
| "learning_rate": 4.9947570655942796e-05, | |
| "loss": 1.2837, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 4.991809526186424e-05, | |
| "loss": 1.3392, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.46484375, | |
| "learning_rate": 4.988208552916535e-05, | |
| "loss": 1.187, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.447265625, | |
| "learning_rate": 4.983955090077444e-05, | |
| "loss": 1.2047, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.494140625, | |
| "learning_rate": 4.9790502530660635e-05, | |
| "loss": 1.2062, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.55859375, | |
| "learning_rate": 4.9734953280908904e-05, | |
| "loss": 1.248, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.82421875, | |
| "learning_rate": 4.967291771834727e-05, | |
| "loss": 1.225, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.484375, | |
| "learning_rate": 4.960441211072686e-05, | |
| "loss": 1.2077, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.5078125, | |
| "learning_rate": 4.9529454422455976e-05, | |
| "loss": 1.2046, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.404296875, | |
| "learning_rate": 4.944806430988927e-05, | |
| "loss": 1.2055, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.546875, | |
| "learning_rate": 4.936026311617316e-05, | |
| "loss": 1.2438, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.462890625, | |
| "learning_rate": 4.926607386564898e-05, | |
| "loss": 1.2093, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.50390625, | |
| "learning_rate": 4.916552125781528e-05, | |
| "loss": 1.1535, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.53125, | |
| "learning_rate": 4.9058631660850765e-05, | |
| "loss": 1.2239, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.50390625, | |
| "learning_rate": 4.894543310469968e-05, | |
| "loss": 1.1454, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 4.882595527372152e-05, | |
| "loss": 1.1234, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.486328125, | |
| "learning_rate": 4.870022949890676e-05, | |
| "loss": 1.1888, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 4.856828874966086e-05, | |
| "loss": 1.1476, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.435546875, | |
| "learning_rate": 4.8430167625158595e-05, | |
| "loss": 1.2208, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.49609375, | |
| "learning_rate": 4.828590234527106e-05, | |
| "loss": 1.16, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.40625, | |
| "learning_rate": 4.813553074106761e-05, | |
| "loss": 1.1312, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.53125, | |
| "learning_rate": 4.7979092244895305e-05, | |
| "loss": 1.1732, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.498046875, | |
| "learning_rate": 4.781662788003851e-05, | |
| "loss": 1.1404, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.484375, | |
| "learning_rate": 4.764818024996117e-05, | |
| "loss": 1.1498, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 4.747379352713489e-05, | |
| "loss": 1.148, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.5234375, | |
| "learning_rate": 4.7293513441455364e-05, | |
| "loss": 1.1245, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.49609375, | |
| "learning_rate": 4.710738726825059e-05, | |
| "loss": 1.0975, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 4.69154638158837e-05, | |
| "loss": 1.1204, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.55078125, | |
| "learning_rate": 4.671779341295378e-05, | |
| "loss": 1.1291, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.46484375, | |
| "learning_rate": 4.6514427895098134e-05, | |
| "loss": 1.1382, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 4.630542059139924e-05, | |
| "loss": 1.1861, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.73046875, | |
| "learning_rate": 4.6090826310400116e-05, | |
| "loss": 1.1358, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 4.587070132573178e-05, | |
| "loss": 1.115, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 4.5645103361356415e-05, | |
| "loss": 1.0639, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.51953125, | |
| "learning_rate": 4.541409157643027e-05, | |
| "loss": 1.1185, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 4.517772654979023e-05, | |
| "loss": 1.1038, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.498046875, | |
| "learning_rate": 4.493607026406802e-05, | |
| "loss": 1.0626, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.46484375, | |
| "learning_rate": 4.4689186089436366e-05, | |
| "loss": 1.0829, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 4.443713876699124e-05, | |
| "loss": 1.1554, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.486328125, | |
| "learning_rate": 4.417999439177466e-05, | |
| "loss": 1.0713, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.5078125, | |
| "learning_rate": 4.391782039544238e-05, | |
| "loss": 1.0986, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.474609375, | |
| "learning_rate": 4.365068552858115e-05, | |
| "loss": 1.0185, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 4.337865984268001e-05, | |
| "loss": 1.0955, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 4.3101814671760546e-05, | |
| "loss": 1.0747, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 4.2820222613670736e-05, | |
| "loss": 1.0395, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 4.253395751104748e-05, | |
| "loss": 1.0798, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.828125, | |
| "learning_rate": 4.224309443195261e-05, | |
| "loss": 1.154, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.6015625, | |
| "learning_rate": 4.194770965018758e-05, | |
| "loss": 1.0445, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 4.164788062529203e-05, | |
| "loss": 1.0651, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.5, | |
| "learning_rate": 4.134368598223132e-05, | |
| "loss": 1.1505, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 4.10352054907785e-05, | |
| "loss": 1.085, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 4.072252004459611e-05, | |
| "loss": 1.095, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.8046875, | |
| "learning_rate": 4.0405711640023186e-05, | |
| "loss": 1.0373, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.6015625, | |
| "learning_rate": 4.008486335457312e-05, | |
| "loss": 1.0507, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.578125, | |
| "learning_rate": 3.976005932514807e-05, | |
| "loss": 1.0545, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 3.943138472597549e-05, | |
| "loss": 1.0342, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.609375, | |
| "learning_rate": 3.909892574627266e-05, | |
| "loss": 1.0948, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 3.876276956764509e-05, | |
| "loss": 0.9903, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 3.84230043412246e-05, | |
| "loss": 1.058, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.515625, | |
| "learning_rate": 3.807971916455325e-05, | |
| "loss": 0.9873, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.55859375, | |
| "learning_rate": 3.773300405821908e-05, | |
| "loss": 1.0034, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 3.7382949942249694e-05, | |
| "loss": 1.0152, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.578125, | |
| "learning_rate": 3.702964861227013e-05, | |
| "loss": 1.0289, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 3.6673192715431015e-05, | |
| "loss": 0.9901, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 3.631367572611348e-05, | |
| "loss": 0.9345, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.671875, | |
| "learning_rate": 3.595119192141706e-05, | |
| "loss": 1.035, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 3.5585836356437264e-05, | |
| "loss": 1.0689, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.6015625, | |
| "learning_rate": 3.521770483933891e-05, | |
| "loss": 0.9883, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.51953125, | |
| "learning_rate": 3.484689390623218e-05, | |
| "loss": 1.0279, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 3.447350079585767e-05, | |
| "loss": 1.0602, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 3.409762342408719e-05, | |
| "loss": 1.0178, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 3.3719360358247054e-05, | |
| "loss": 1.0243, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 3.333881079127052e-05, | |
| "loss": 1.0175, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 3.29560745156861e-05, | |
| "loss": 0.921, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 3.2571251897448765e-05, | |
| "loss": 0.9597, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.51171875, | |
| "learning_rate": 3.218444384962071e-05, | |
| "loss": 0.9761, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 3.1795751805908573e-05, | |
| "loss": 0.9706, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 3.1405277694064305e-05, | |
| "loss": 0.932, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.6796875, | |
| "learning_rate": 3.101312390915634e-05, | |
| "loss": 0.9486, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 3.061939328671824e-05, | |
| "loss": 1.011, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 3.0224189075781884e-05, | |
| "loss": 0.9463, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.6796875, | |
| "learning_rate": 2.9827614911802203e-05, | |
| "loss": 0.9989, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.7109375, | |
| "learning_rate": 2.9429774789480575e-05, | |
| "loss": 0.9677, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 2.9030773035493997e-05, | |
| "loss": 0.9739, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 2.863071428113726e-05, | |
| "loss": 1.0254, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.8203125, | |
| "learning_rate": 2.8229703434885163e-05, | |
| "loss": 0.9969, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 2.782784565488211e-05, | |
| "loss": 0.9918, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.58203125, | |
| "learning_rate": 2.7425246321366203e-05, | |
| "loss": 1.0169, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.75, | |
| "learning_rate": 2.7022011009035107e-05, | |
| "loss": 0.9844, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.7265625, | |
| "learning_rate": 2.6618245459360897e-05, | |
| "loss": 1.026, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.671875, | |
| "learning_rate": 2.621405555286121e-05, | |
| "loss": 0.9333, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 2.5809547281333902e-05, | |
| "loss": 1.0336, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 2.540482672006254e-05, | |
| "loss": 0.9375, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.87109375, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.9441, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.7265625, | |
| "learning_rate": 2.4595173279937464e-05, | |
| "loss": 0.9643, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 2.419045271866611e-05, | |
| "loss": 0.9172, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.87109375, | |
| "learning_rate": 2.3785944447138802e-05, | |
| "loss": 0.8813, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.8046875, | |
| "learning_rate": 2.338175454063911e-05, | |
| "loss": 0.9638, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.859375, | |
| "learning_rate": 2.29779889909649e-05, | |
| "loss": 0.9476, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.6796875, | |
| "learning_rate": 2.25747536786338e-05, | |
| "loss": 0.9536, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.77734375, | |
| "learning_rate": 2.2172154345117894e-05, | |
| "loss": 0.9308, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.734375, | |
| "learning_rate": 2.177029656511485e-05, | |
| "loss": 0.9432, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.66015625, | |
| "learning_rate": 2.136928571886275e-05, | |
| "loss": 0.9253, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 2.0969226964506006e-05, | |
| "loss": 0.9301, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 2.0570225210519434e-05, | |
| "loss": 0.9509, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.7421875, | |
| "learning_rate": 2.0172385088197803e-05, | |
| "loss": 0.8995, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.8125, | |
| "learning_rate": 1.9775810924218125e-05, | |
| "loss": 0.8682, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.8203125, | |
| "learning_rate": 1.9380606713281775e-05, | |
| "loss": 0.9384, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.76171875, | |
| "learning_rate": 1.8986876090843667e-05, | |
| "loss": 0.9545, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.74609375, | |
| "learning_rate": 1.859472230593569e-05, | |
| "loss": 0.8595, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.8125, | |
| "learning_rate": 1.820424819409143e-05, | |
| "loss": 0.9636, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.75390625, | |
| "learning_rate": 1.7815556150379298e-05, | |
| "loss": 0.973, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 1.7428748102551237e-05, | |
| "loss": 0.9182, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.85546875, | |
| "learning_rate": 1.704392548431391e-05, | |
| "loss": 0.9419, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 1.666118920872949e-05, | |
| "loss": 0.8826, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.83203125, | |
| "learning_rate": 1.6280639641752942e-05, | |
| "loss": 0.8989, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.8125, | |
| "learning_rate": 1.5902376575912815e-05, | |
| "loss": 0.8946, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 1.552649920414233e-05, | |
| "loss": 0.8636, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.91015625, | |
| "learning_rate": 1.5153106093767827e-05, | |
| "loss": 0.9318, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 1.4782295160661103e-05, | |
| "loss": 0.9496, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.734375, | |
| "learning_rate": 1.4414163643562755e-05, | |
| "loss": 0.8607, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 1.4048808078582942e-05, | |
| "loss": 0.8367, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.83203125, | |
| "learning_rate": 1.368632427388653e-05, | |
| "loss": 0.9584, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.80859375, | |
| "learning_rate": 1.3326807284568984e-05, | |
| "loss": 0.8844, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.87890625, | |
| "learning_rate": 1.2970351387729873e-05, | |
| "loss": 0.9125, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.74609375, | |
| "learning_rate": 1.2617050057750322e-05, | |
| "loss": 0.9229, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 1.2266995941780934e-05, | |
| "loss": 0.9541, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.8359375, | |
| "learning_rate": 1.1920280835446748e-05, | |
| "loss": 0.8816, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.82421875, | |
| "learning_rate": 1.1576995658775405e-05, | |
| "loss": 0.862, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 1.1237230432354912e-05, | |
| "loss": 0.8541, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.8203125, | |
| "learning_rate": 1.0901074253727336e-05, | |
| "loss": 0.8586, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.7890625, | |
| "learning_rate": 1.0568615274024522e-05, | |
| "loss": 0.9033, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.7890625, | |
| "learning_rate": 1.0239940674851941e-05, | |
| "loss": 0.8456, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.91796875, | |
| "learning_rate": 9.915136645426884e-06, | |
| "loss": 0.9165, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.80859375, | |
| "learning_rate": 9.594288359976817e-06, | |
| "loss": 0.8225, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.85546875, | |
| "learning_rate": 9.277479955403887e-06, | |
| "loss": 0.815, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 8.964794509221508e-06, | |
| "loss": 0.8517, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.8125, | |
| "learning_rate": 8.656314017768693e-06, | |
| "loss": 0.9108, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.8671875, | |
| "learning_rate": 8.352119374707978e-06, | |
| "loss": 0.8665, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.8359375, | |
| "learning_rate": 8.052290349812419e-06, | |
| "loss": 0.875, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.8359375, | |
| "learning_rate": 7.756905568047393e-06, | |
| "loss": 0.9181, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.91015625, | |
| "learning_rate": 7.466042488952521e-06, | |
| "loss": 0.8715, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.74609375, | |
| "learning_rate": 7.179777386329276e-06, | |
| "loss": 0.9051, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.796875, | |
| "learning_rate": 6.898185328239468e-06, | |
| "loss": 0.871, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.71875, | |
| "learning_rate": 6.621340157319997e-06, | |
| "loss": 0.8633, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.98046875, | |
| "learning_rate": 6.349314471418849e-06, | |
| "loss": 0.8513, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.81640625, | |
| "learning_rate": 6.082179604557617e-06, | |
| "loss": 0.8063, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 5.820005608225346e-06, | |
| "loss": 0.8652, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.81640625, | |
| "learning_rate": 5.562861233008774e-06, | |
| "loss": 0.872, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.74609375, | |
| "learning_rate": 5.310813910563644e-06, | |
| "loss": 0.849, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.79296875, | |
| "learning_rate": 5.063929735931985e-06, | |
| "loss": 0.8926, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.77734375, | |
| "learning_rate": 4.8222734502097665e-06, | |
| "loss": 0.8093, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.8515625, | |
| "learning_rate": 4.585908423569724e-06, | |
| "loss": 0.8563, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.97265625, | |
| "learning_rate": 4.35489663864359e-06, | |
| "loss": 0.8393, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.8984375, | |
| "learning_rate": 4.129298674268225e-06, | |
| "loss": 0.9031, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.9296875, | |
| "learning_rate": 3.90917368959989e-06, | |
| "loss": 0.8981, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.8828125, | |
| "learning_rate": 3.694579408600771e-06, | |
| "loss": 0.8628, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.796875, | |
| "learning_rate": 3.4855721049018688e-06, | |
| "loss": 0.8707, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.88671875, | |
| "learning_rate": 3.2822065870462217e-06, | |
| "loss": 0.8423, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 3.08453618411631e-06, | |
| "loss": 0.8448, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.8984375, | |
| "learning_rate": 2.892612731749414e-06, | |
| "loss": 0.8743, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.8125, | |
| "learning_rate": 2.7064865585446434e-06, | |
| "loss": 0.8389, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.8046875, | |
| "learning_rate": 2.52620647286512e-06, | |
| "loss": 0.8437, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.92578125, | |
| "learning_rate": 2.351819750038828e-06, | |
| "loss": 0.7811, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.8359375, | |
| "learning_rate": 2.183372119961499e-06, | |
| "loss": 0.8266, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.9296875, | |
| "learning_rate": 2.020907755104698e-06, | |
| "loss": 0.8374, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.80859375, | |
| "learning_rate": 1.864469258932397e-06, | |
| "loss": 0.9058, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.78125, | |
| "learning_rate": 1.7140976547289438e-06, | |
| "loss": 0.8627, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.8359375, | |
| "learning_rate": 1.5698323748414124e-06, | |
| "loss": 0.8706, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.95703125, | |
| "learning_rate": 1.4317112503391432e-06, | |
| "loss": 0.8315, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.80859375, | |
| "learning_rate": 1.2997705010932393e-06, | |
| "loss": 0.791, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.859375, | |
| "learning_rate": 1.1740447262784781e-06, | |
| "loss": 0.8368, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.9375, | |
| "learning_rate": 1.0545668953003241e-06, | |
| "loss": 0.8122, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.84375, | |
| "learning_rate": 9.413683391492456e-07, | |
| "loss": 0.875, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.7265625, | |
| "learning_rate": 8.344787421847217e-07, | |
| "loss": 0.8642, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.90625, | |
| "learning_rate": 7.339261343510206e-07, | |
| "loss": 0.8466, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.78125, | |
| "learning_rate": 6.397368838268497e-07, | |
| "loss": 0.8382, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.83203125, | |
| "learning_rate": 5.519356901107358e-07, | |
| "loss": 0.8325, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.89453125, | |
| "learning_rate": 4.7054557754402373e-07, | |
| "loss": 0.8688, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.859375, | |
| "learning_rate": 3.9558788927314407e-07, | |
| "loss": 0.8879, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.8203125, | |
| "learning_rate": 3.270822816527325e-07, | |
| "loss": 0.7926, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.859375, | |
| "learning_rate": 2.650467190910999e-07, | |
| "loss": 0.8789, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.8203125, | |
| "learning_rate": 2.094974693393731e-07, | |
| "loss": 0.7915, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.8125, | |
| "learning_rate": 1.6044909922555974e-07, | |
| "loss": 0.8365, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.859375, | |
| "learning_rate": 1.1791447083465134e-07, | |
| "loss": 0.8521, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.83203125, | |
| "learning_rate": 8.190473813576572e-08, | |
| "loss": 0.8351, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.87890625, | |
| "learning_rate": 5.242934405720879e-08, | |
| "loss": 0.8468, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.92578125, | |
| "learning_rate": 2.9496018010233274e-08, | |
| "loss": 0.8121, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.9296875, | |
| "learning_rate": 1.3110773862126669e-08, | |
| "loss": 0.8535, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.87109375, | |
| "learning_rate": 3.2779083591949478e-09, | |
| "loss": 0.9272, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.8359375, | |
| "learning_rate": 0.0, | |
| "loss": 0.8806, | |
| "step": 5000 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 9.7705141469184e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |