| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.275652862041678, | |
| "global_step": 100000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 6.6159, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 5.667357444763184, | |
| "eval_runtime": 77.1533, | |
| "eval_samples_per_second": 53.413, | |
| "eval_steps_per_second": 3.344, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 3.8828, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 5.533279895782471, | |
| "eval_runtime": 76.0378, | |
| "eval_samples_per_second": 54.197, | |
| "eval_steps_per_second": 3.393, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.5e-05, | |
| "loss": 3.571, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 5.119894504547119, | |
| "eval_runtime": 76.0046, | |
| "eval_samples_per_second": 54.22, | |
| "eval_steps_per_second": 3.395, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 3.4645, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 5.038773536682129, | |
| "eval_runtime": 75.6611, | |
| "eval_samples_per_second": 54.467, | |
| "eval_steps_per_second": 3.41, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 3.3826, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 4.901891708374023, | |
| "eval_runtime": 76.8157, | |
| "eval_samples_per_second": 53.648, | |
| "eval_steps_per_second": 3.359, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3503, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 5.015623092651367, | |
| "eval_runtime": 76.5299, | |
| "eval_samples_per_second": 53.848, | |
| "eval_steps_per_second": 3.371, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.9727594660855354e-05, | |
| "loss": 3.3038, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 4.954394340515137, | |
| "eval_runtime": 76.8379, | |
| "eval_samples_per_second": 53.632, | |
| "eval_steps_per_second": 3.358, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.9455189321710707e-05, | |
| "loss": 3.2411, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 4.890042304992676, | |
| "eval_runtime": 76.8834, | |
| "eval_samples_per_second": 53.601, | |
| "eval_steps_per_second": 3.356, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.918278398256606e-05, | |
| "loss": 3.1958, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 5.015548229217529, | |
| "eval_runtime": 76.9729, | |
| "eval_samples_per_second": 53.538, | |
| "eval_steps_per_second": 3.352, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.891037864342141e-05, | |
| "loss": 3.1856, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 4.8613457679748535, | |
| "eval_runtime": 76.9767, | |
| "eval_samples_per_second": 53.536, | |
| "eval_steps_per_second": 3.352, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.863797330427677e-05, | |
| "loss": 3.1836, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 4.832852840423584, | |
| "eval_runtime": 76.9463, | |
| "eval_samples_per_second": 53.557, | |
| "eval_steps_per_second": 3.353, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.836556796513212e-05, | |
| "loss": 3.1566, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 4.755970001220703, | |
| "eval_runtime": 76.8635, | |
| "eval_samples_per_second": 53.615, | |
| "eval_steps_per_second": 3.357, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.809316262598747e-05, | |
| "loss": 3.1046, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 4.7649054527282715, | |
| "eval_runtime": 76.531, | |
| "eval_samples_per_second": 53.847, | |
| "eval_steps_per_second": 3.371, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.7820757286842826e-05, | |
| "loss": 3.109, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 4.723949909210205, | |
| "eval_runtime": 76.9877, | |
| "eval_samples_per_second": 53.528, | |
| "eval_steps_per_second": 3.351, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.754835194769818e-05, | |
| "loss": 3.0862, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 4.741213321685791, | |
| "eval_runtime": 77.0649, | |
| "eval_samples_per_second": 53.474, | |
| "eval_steps_per_second": 3.348, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.727594660855353e-05, | |
| "loss": 3.0713, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 4.756562232971191, | |
| "eval_runtime": 72.732, | |
| "eval_samples_per_second": 56.66, | |
| "eval_steps_per_second": 3.547, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.700354126940888e-05, | |
| "loss": 3.052, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 4.908087730407715, | |
| "eval_runtime": 71.9667, | |
| "eval_samples_per_second": 57.263, | |
| "eval_steps_per_second": 3.585, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.6731135930264234e-05, | |
| "loss": 3.0546, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 4.8161492347717285, | |
| "eval_runtime": 72.0137, | |
| "eval_samples_per_second": 57.225, | |
| "eval_steps_per_second": 3.583, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.6458730591119586e-05, | |
| "loss": 3.0308, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 4.948371410369873, | |
| "eval_runtime": 72.0349, | |
| "eval_samples_per_second": 57.208, | |
| "eval_steps_per_second": 3.582, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 4.6186325251974945e-05, | |
| "loss": 2.864, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 4.853775978088379, | |
| "eval_runtime": 72.0568, | |
| "eval_samples_per_second": 57.191, | |
| "eval_steps_per_second": 3.581, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.59139199128303e-05, | |
| "loss": 2.8339, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 4.888705730438232, | |
| "eval_runtime": 72.0694, | |
| "eval_samples_per_second": 57.181, | |
| "eval_steps_per_second": 3.58, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.564151457368564e-05, | |
| "loss": 2.8388, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 4.920900344848633, | |
| "eval_runtime": 72.0696, | |
| "eval_samples_per_second": 57.181, | |
| "eval_steps_per_second": 3.58, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 4.5369109234541e-05, | |
| "loss": 2.852, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 4.990002632141113, | |
| "eval_runtime": 72.0496, | |
| "eval_samples_per_second": 57.197, | |
| "eval_steps_per_second": 3.581, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 4.509670389539635e-05, | |
| "loss": 2.8415, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 4.912019729614258, | |
| "eval_runtime": 72.0569, | |
| "eval_samples_per_second": 57.191, | |
| "eval_steps_per_second": 3.581, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 4.4824298556251705e-05, | |
| "loss": 2.8435, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 4.905246257781982, | |
| "eval_runtime": 72.0554, | |
| "eval_samples_per_second": 57.192, | |
| "eval_steps_per_second": 3.581, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 4.455189321710706e-05, | |
| "loss": 2.832, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_loss": 5.011730194091797, | |
| "eval_runtime": 72.047, | |
| "eval_samples_per_second": 57.199, | |
| "eval_steps_per_second": 3.581, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 4.427948787796241e-05, | |
| "loss": 2.8509, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 5.078315734863281, | |
| "eval_runtime": 72.0913, | |
| "eval_samples_per_second": 57.164, | |
| "eval_steps_per_second": 3.579, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 4.400708253881776e-05, | |
| "loss": 2.8436, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 4.865673542022705, | |
| "eval_runtime": 72.0906, | |
| "eval_samples_per_second": 57.164, | |
| "eval_steps_per_second": 3.579, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 4.373467719967311e-05, | |
| "loss": 2.8558, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 4.83981990814209, | |
| "eval_runtime": 72.0594, | |
| "eval_samples_per_second": 57.189, | |
| "eval_steps_per_second": 3.58, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 4.346227186052847e-05, | |
| "loss": 2.8324, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 4.96191930770874, | |
| "eval_runtime": 72.0431, | |
| "eval_samples_per_second": 57.202, | |
| "eval_steps_per_second": 3.581, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.318986652138382e-05, | |
| "loss": 2.8234, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 4.830244541168213, | |
| "eval_runtime": 72.1429, | |
| "eval_samples_per_second": 57.123, | |
| "eval_steps_per_second": 3.576, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.291746118223917e-05, | |
| "loss": 2.8155, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 4.835384845733643, | |
| "eval_runtime": 72.0429, | |
| "eval_samples_per_second": 57.202, | |
| "eval_steps_per_second": 3.581, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 4.264505584309453e-05, | |
| "loss": 2.8422, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_loss": 5.029502868652344, | |
| "eval_runtime": 72.0029, | |
| "eval_samples_per_second": 57.234, | |
| "eval_steps_per_second": 3.583, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 4.237265050394988e-05, | |
| "loss": 2.8192, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 5.054713249206543, | |
| "eval_runtime": 72.0962, | |
| "eval_samples_per_second": 57.16, | |
| "eval_steps_per_second": 3.579, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 4.210024516480523e-05, | |
| "loss": 2.839, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 5.000535488128662, | |
| "eval_runtime": 72.0721, | |
| "eval_samples_per_second": 57.179, | |
| "eval_steps_per_second": 3.58, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 4.1827839825660584e-05, | |
| "loss": 2.803, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_loss": 4.954083442687988, | |
| "eval_runtime": 72.0788, | |
| "eval_samples_per_second": 57.174, | |
| "eval_steps_per_second": 3.579, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 4.1555434486515936e-05, | |
| "loss": 2.8096, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 5.285138130187988, | |
| "eval_runtime": 72.0675, | |
| "eval_samples_per_second": 57.182, | |
| "eval_steps_per_second": 3.58, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.128302914737129e-05, | |
| "loss": 2.7969, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 5.253526210784912, | |
| "eval_runtime": 72.067, | |
| "eval_samples_per_second": 57.183, | |
| "eval_steps_per_second": 3.58, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 4.101062380822665e-05, | |
| "loss": 2.61, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 5.254916667938232, | |
| "eval_runtime": 72.0845, | |
| "eval_samples_per_second": 57.169, | |
| "eval_steps_per_second": 3.579, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 4.073821846908199e-05, | |
| "loss": 2.6062, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_loss": 5.293761730194092, | |
| "eval_runtime": 72.1279, | |
| "eval_samples_per_second": 57.135, | |
| "eval_steps_per_second": 3.577, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 4.0465813129937345e-05, | |
| "loss": 2.6025, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 5.301900863647461, | |
| "eval_runtime": 77.2131, | |
| "eval_samples_per_second": 53.372, | |
| "eval_steps_per_second": 3.341, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 4.0193407790792704e-05, | |
| "loss": 2.5983, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 5.322200775146484, | |
| "eval_runtime": 76.5314, | |
| "eval_samples_per_second": 53.847, | |
| "eval_steps_per_second": 3.371, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 3.9921002451648056e-05, | |
| "loss": 2.6204, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 4.960803031921387, | |
| "eval_runtime": 76.6466, | |
| "eval_samples_per_second": 53.766, | |
| "eval_steps_per_second": 3.366, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 3.964859711250341e-05, | |
| "loss": 2.6199, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 5.222067832946777, | |
| "eval_runtime": 76.1563, | |
| "eval_samples_per_second": 54.112, | |
| "eval_steps_per_second": 3.388, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 3.937619177335876e-05, | |
| "loss": 2.6125, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 5.104248046875, | |
| "eval_runtime": 76.1947, | |
| "eval_samples_per_second": 54.085, | |
| "eval_steps_per_second": 3.386, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 3.910378643421411e-05, | |
| "loss": 2.621, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_loss": 5.0914106369018555, | |
| "eval_runtime": 76.1296, | |
| "eval_samples_per_second": 54.131, | |
| "eval_steps_per_second": 3.389, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 3.8831381095069464e-05, | |
| "loss": 2.6215, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "eval_loss": 5.066018104553223, | |
| "eval_runtime": 76.0097, | |
| "eval_samples_per_second": 54.217, | |
| "eval_steps_per_second": 3.394, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 3.855897575592482e-05, | |
| "loss": 2.6388, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 5.130795001983643, | |
| "eval_runtime": 76.0566, | |
| "eval_samples_per_second": 54.183, | |
| "eval_steps_per_second": 3.392, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 3.828657041678017e-05, | |
| "loss": 2.6328, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_loss": 5.16806173324585, | |
| "eval_runtime": 76.22, | |
| "eval_samples_per_second": 54.067, | |
| "eval_steps_per_second": 3.385, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.801416507763552e-05, | |
| "loss": 2.6462, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 5.09861946105957, | |
| "eval_runtime": 81.8993, | |
| "eval_samples_per_second": 50.965, | |
| "eval_steps_per_second": 3.187, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.774175973849088e-05, | |
| "loss": 2.6489, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "eval_loss": 5.686895847320557, | |
| "eval_runtime": 81.88, | |
| "eval_samples_per_second": 50.977, | |
| "eval_steps_per_second": 3.188, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 3.746935439934623e-05, | |
| "loss": 2.6487, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "eval_loss": 5.235321998596191, | |
| "eval_runtime": 81.927, | |
| "eval_samples_per_second": 50.948, | |
| "eval_steps_per_second": 3.186, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.719694906020158e-05, | |
| "loss": 2.6291, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 5.161744594573975, | |
| "eval_runtime": 81.9025, | |
| "eval_samples_per_second": 50.963, | |
| "eval_steps_per_second": 3.187, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 3.6924543721056935e-05, | |
| "loss": 2.6168, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "eval_loss": 5.017256259918213, | |
| "eval_runtime": 81.8942, | |
| "eval_samples_per_second": 50.968, | |
| "eval_steps_per_second": 3.187, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 3.665213838191229e-05, | |
| "loss": 2.6478, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_loss": 4.907939434051514, | |
| "eval_runtime": 81.992, | |
| "eval_samples_per_second": 50.907, | |
| "eval_steps_per_second": 3.183, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 3.637973304276764e-05, | |
| "loss": 2.636, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "eval_loss": 5.104933261871338, | |
| "eval_runtime": 81.9752, | |
| "eval_samples_per_second": 50.918, | |
| "eval_steps_per_second": 3.184, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.6107327703623e-05, | |
| "loss": 2.6014, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "eval_loss": 5.3848161697387695, | |
| "eval_runtime": 80.9116, | |
| "eval_samples_per_second": 51.587, | |
| "eval_steps_per_second": 3.226, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 3.583492236447834e-05, | |
| "loss": 2.4145, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "eval_loss": 5.649404048919678, | |
| "eval_runtime": 78.1589, | |
| "eval_samples_per_second": 53.404, | |
| "eval_steps_per_second": 3.339, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 3.5562517025333695e-05, | |
| "loss": 2.4236, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "eval_loss": 5.877135276794434, | |
| "eval_runtime": 78.2014, | |
| "eval_samples_per_second": 53.375, | |
| "eval_steps_per_second": 3.338, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 3.5290111686189054e-05, | |
| "loss": 2.448, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "eval_loss": 5.5254974365234375, | |
| "eval_runtime": 78.286, | |
| "eval_samples_per_second": 53.317, | |
| "eval_steps_per_second": 3.334, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 3.5017706347044406e-05, | |
| "loss": 2.4516, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "eval_loss": 5.600991249084473, | |
| "eval_runtime": 78.1753, | |
| "eval_samples_per_second": 53.393, | |
| "eval_steps_per_second": 3.339, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 3.474530100789976e-05, | |
| "loss": 2.4536, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "eval_loss": 5.542355537414551, | |
| "eval_runtime": 78.3728, | |
| "eval_samples_per_second": 53.258, | |
| "eval_steps_per_second": 3.33, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 3.447289566875511e-05, | |
| "loss": 2.4595, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "eval_loss": 5.826052188873291, | |
| "eval_runtime": 78.1666, | |
| "eval_samples_per_second": 53.399, | |
| "eval_steps_per_second": 3.339, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 3.420049032961046e-05, | |
| "loss": 2.4539, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "eval_loss": 5.755754470825195, | |
| "eval_runtime": 78.124, | |
| "eval_samples_per_second": 53.428, | |
| "eval_steps_per_second": 3.341, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 3.3928084990465814e-05, | |
| "loss": 2.4511, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "eval_loss": 5.6875505447387695, | |
| "eval_runtime": 78.2257, | |
| "eval_samples_per_second": 53.358, | |
| "eval_steps_per_second": 3.336, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 3.3655679651321166e-05, | |
| "loss": 2.463, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "eval_loss": 5.699981689453125, | |
| "eval_runtime": 78.274, | |
| "eval_samples_per_second": 53.325, | |
| "eval_steps_per_second": 3.334, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 3.338327431217652e-05, | |
| "loss": 2.4678, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "eval_loss": 5.762045383453369, | |
| "eval_runtime": 78.2031, | |
| "eval_samples_per_second": 53.374, | |
| "eval_steps_per_second": 3.337, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 3.311086897303187e-05, | |
| "loss": 2.4753, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "eval_loss": 5.77708101272583, | |
| "eval_runtime": 78.2487, | |
| "eval_samples_per_second": 53.343, | |
| "eval_steps_per_second": 3.336, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 3.283846363388722e-05, | |
| "loss": 2.4713, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "eval_loss": 5.61986780166626, | |
| "eval_runtime": 78.1013, | |
| "eval_samples_per_second": 53.443, | |
| "eval_steps_per_second": 3.342, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 3.256605829474258e-05, | |
| "loss": 2.5024, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "eval_loss": 5.585144996643066, | |
| "eval_runtime": 78.2816, | |
| "eval_samples_per_second": 53.32, | |
| "eval_steps_per_second": 3.334, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 3.2293652955597933e-05, | |
| "loss": 2.4772, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "eval_loss": 5.567023277282715, | |
| "eval_runtime": 78.3144, | |
| "eval_samples_per_second": 53.298, | |
| "eval_steps_per_second": 3.333, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 3.202124761645328e-05, | |
| "loss": 2.4989, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "eval_loss": 5.388617038726807, | |
| "eval_runtime": 78.311, | |
| "eval_samples_per_second": 53.3, | |
| "eval_steps_per_second": 3.333, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 3.174884227730864e-05, | |
| "loss": 2.4908, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "eval_loss": 5.46661901473999, | |
| "eval_runtime": 78.3042, | |
| "eval_samples_per_second": 53.305, | |
| "eval_steps_per_second": 3.333, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 3.147643693816399e-05, | |
| "loss": 2.4975, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "eval_loss": 5.72676944732666, | |
| "eval_runtime": 78.4025, | |
| "eval_samples_per_second": 53.238, | |
| "eval_steps_per_second": 3.329, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 3.120403159901934e-05, | |
| "loss": 2.4983, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "eval_loss": 5.200565814971924, | |
| "eval_runtime": 78.2961, | |
| "eval_samples_per_second": 53.31, | |
| "eval_steps_per_second": 3.333, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 3.0931626259874694e-05, | |
| "loss": 2.4595, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "eval_loss": 5.285388946533203, | |
| "eval_runtime": 77.5634, | |
| "eval_samples_per_second": 53.814, | |
| "eval_steps_per_second": 3.365, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 3.0659220920730046e-05, | |
| "loss": 2.2848, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "eval_loss": 5.081736087799072, | |
| "eval_runtime": 77.374, | |
| "eval_samples_per_second": 53.946, | |
| "eval_steps_per_second": 3.373, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 3.0386815581585398e-05, | |
| "loss": 2.3182, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "eval_loss": 5.363966464996338, | |
| "eval_runtime": 77.4691, | |
| "eval_samples_per_second": 53.88, | |
| "eval_steps_per_second": 3.369, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 3.0114410242440753e-05, | |
| "loss": 2.2998, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "eval_loss": 5.359724044799805, | |
| "eval_runtime": 77.9931, | |
| "eval_samples_per_second": 53.518, | |
| "eval_steps_per_second": 3.346, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 2.9842004903296105e-05, | |
| "loss": 2.3085, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "eval_loss": 5.6501922607421875, | |
| "eval_runtime": 77.8375, | |
| "eval_samples_per_second": 53.625, | |
| "eval_steps_per_second": 3.353, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 2.9569599564151457e-05, | |
| "loss": 2.2716, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "eval_loss": 5.682339668273926, | |
| "eval_runtime": 78.1512, | |
| "eval_samples_per_second": 53.409, | |
| "eval_steps_per_second": 3.34, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 2.9297194225006813e-05, | |
| "loss": 2.2716, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "eval_loss": 5.677391052246094, | |
| "eval_runtime": 78.1619, | |
| "eval_samples_per_second": 53.402, | |
| "eval_steps_per_second": 3.339, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 2.9024788885862165e-05, | |
| "loss": 2.284, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "eval_loss": 5.525763988494873, | |
| "eval_runtime": 78.1139, | |
| "eval_samples_per_second": 53.435, | |
| "eval_steps_per_second": 3.341, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 2.8752383546717514e-05, | |
| "loss": 2.2916, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "eval_loss": 5.277717590332031, | |
| "eval_runtime": 78.1112, | |
| "eval_samples_per_second": 53.437, | |
| "eval_steps_per_second": 3.341, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 2.8479978207572872e-05, | |
| "loss": 2.2978, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "eval_loss": 5.4305100440979, | |
| "eval_runtime": 78.0088, | |
| "eval_samples_per_second": 53.507, | |
| "eval_steps_per_second": 3.346, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 2.820757286842822e-05, | |
| "loss": 2.3053, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "eval_loss": 5.21947717666626, | |
| "eval_runtime": 77.9992, | |
| "eval_samples_per_second": 53.513, | |
| "eval_steps_per_second": 3.346, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 2.7935167529283573e-05, | |
| "loss": 2.3057, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "eval_loss": 5.573265075683594, | |
| "eval_runtime": 78.0097, | |
| "eval_samples_per_second": 53.506, | |
| "eval_steps_per_second": 3.346, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 2.766276219013893e-05, | |
| "loss": 2.321, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "eval_loss": 5.401345252990723, | |
| "eval_runtime": 77.9848, | |
| "eval_samples_per_second": 53.523, | |
| "eval_steps_per_second": 3.347, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 2.739035685099428e-05, | |
| "loss": 2.3067, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "eval_loss": 5.604618072509766, | |
| "eval_runtime": 77.7786, | |
| "eval_samples_per_second": 53.665, | |
| "eval_steps_per_second": 3.356, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 2.7117951511849633e-05, | |
| "loss": 2.317, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "eval_loss": 5.823883533477783, | |
| "eval_runtime": 77.9289, | |
| "eval_samples_per_second": 53.562, | |
| "eval_steps_per_second": 3.349, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 2.6845546172704988e-05, | |
| "loss": 2.3356, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "eval_loss": 5.789203643798828, | |
| "eval_runtime": 78.1796, | |
| "eval_samples_per_second": 53.39, | |
| "eval_steps_per_second": 3.338, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 2.657314083356034e-05, | |
| "loss": 2.3301, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "eval_loss": 5.643290996551514, | |
| "eval_runtime": 78.4214, | |
| "eval_samples_per_second": 53.225, | |
| "eval_steps_per_second": 3.328, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 2.630073549441569e-05, | |
| "loss": 2.3475, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "eval_loss": 5.742900848388672, | |
| "eval_runtime": 78.38, | |
| "eval_samples_per_second": 53.253, | |
| "eval_steps_per_second": 3.33, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 2.6028330155271048e-05, | |
| "loss": 2.3237, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "eval_loss": 5.759471416473389, | |
| "eval_runtime": 78.3893, | |
| "eval_samples_per_second": 53.247, | |
| "eval_steps_per_second": 3.33, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 2.5755924816126396e-05, | |
| "loss": 2.2959, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "eval_loss": 5.965908050537109, | |
| "eval_runtime": 78.3426, | |
| "eval_samples_per_second": 53.279, | |
| "eval_steps_per_second": 3.332, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 2.548351947698175e-05, | |
| "loss": 2.192, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "eval_loss": 5.630726337432861, | |
| "eval_runtime": 78.3297, | |
| "eval_samples_per_second": 53.288, | |
| "eval_steps_per_second": 3.332, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 2.5211114137837104e-05, | |
| "loss": 2.1869, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "eval_loss": 5.92326545715332, | |
| "eval_runtime": 78.461, | |
| "eval_samples_per_second": 53.198, | |
| "eval_steps_per_second": 3.326, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 2.4938708798692456e-05, | |
| "loss": 2.203, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "eval_loss": 5.989378929138184, | |
| "eval_runtime": 78.6971, | |
| "eval_samples_per_second": 53.039, | |
| "eval_steps_per_second": 3.317, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 2.4666303459547808e-05, | |
| "loss": 2.2222, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "eval_loss": 5.885297775268555, | |
| "eval_runtime": 78.4475, | |
| "eval_samples_per_second": 53.208, | |
| "eval_steps_per_second": 3.327, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 2.439389812040316e-05, | |
| "loss": 2.225, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "eval_loss": 5.9232964515686035, | |
| "eval_runtime": 78.1906, | |
| "eval_samples_per_second": 53.382, | |
| "eval_steps_per_second": 3.338, | |
| "step": 100000 | |
| } | |
| ], | |
| "max_steps": 189550, | |
| "num_train_epochs": 10, | |
| "total_flos": 2.5166251732608e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |