| { | |
| "best_metric": 0.016573524102568626, | |
| "best_model_checkpoint": "/gpfs/gibbs/pi/dijk/BrainLM_runs/2023-11-17-17_37_00/checkpoint-4400", | |
| "epoch": 19.292899505226252, | |
| "global_step": 4600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0, | |
| "learning_rate": 2.100840336134454e-05, | |
| "loss": 0.0205, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0, | |
| "eval_loss": 0.020380878821015358, | |
| "eval_mae": 0.10914861410856247, | |
| "eval_mse": 0.020377445966005325, | |
| "eval_r2": 0.08699230219766863, | |
| "eval_runtime": 65.4495, | |
| "eval_samples_per_second": 6.112, | |
| "eval_steps_per_second": 3.056, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0, | |
| "learning_rate": 4.201680672268908e-05, | |
| "loss": 0.0195, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0, | |
| "eval_loss": 0.01993260346353054, | |
| "eval_mae": 0.10798273980617523, | |
| "eval_mse": 0.019940046593546867, | |
| "eval_r2": 0.10634720488402916, | |
| "eval_runtime": 82.6009, | |
| "eval_samples_per_second": 4.843, | |
| "eval_steps_per_second": 2.421, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0, | |
| "learning_rate": 6.302521008403361e-05, | |
| "loss": 0.0191, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0, | |
| "eval_loss": 0.01966927945613861, | |
| "eval_mae": 0.10720709711313248, | |
| "eval_mse": 0.019672850146889687, | |
| "eval_r2": 0.1188939908583877, | |
| "eval_runtime": 273.6405, | |
| "eval_samples_per_second": 1.462, | |
| "eval_steps_per_second": 0.731, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0, | |
| "learning_rate": 8.403361344537815e-05, | |
| "loss": 0.0189, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0, | |
| "eval_loss": 0.019402366131544113, | |
| "eval_mae": 0.10650211572647095, | |
| "eval_mse": 0.01940837688744068, | |
| "eval_r2": 0.1273264644968536, | |
| "eval_runtime": 65.4954, | |
| "eval_samples_per_second": 6.107, | |
| "eval_steps_per_second": 3.054, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1, | |
| "learning_rate": 9.999826244478293e-05, | |
| "loss": 0.0187, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1, | |
| "eval_loss": 0.019103730097413063, | |
| "eval_mae": 0.10563357919454575, | |
| "eval_mse": 0.01910446584224701, | |
| "eval_r2": 0.14288129156056273, | |
| "eval_runtime": 67.6226, | |
| "eval_samples_per_second": 5.915, | |
| "eval_steps_per_second": 2.958, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1, | |
| "learning_rate": 9.995362383107962e-05, | |
| "loss": 0.0183, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1, | |
| "eval_loss": 0.0188433900475502, | |
| "eval_mae": 0.1049303263425827, | |
| "eval_mse": 0.018846124410629272, | |
| "eval_r2": 0.15557466279282905, | |
| "eval_runtime": 63.0108, | |
| "eval_samples_per_second": 6.348, | |
| "eval_steps_per_second": 3.174, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1, | |
| "learning_rate": 9.98487151097676e-05, | |
| "loss": 0.0181, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1, | |
| "eval_loss": 0.018534274771809578, | |
| "eval_mae": 0.10398274660110474, | |
| "eval_mse": 0.018525807186961174, | |
| "eval_r2": 0.16440368152546336, | |
| "eval_runtime": 63.6126, | |
| "eval_samples_per_second": 6.288, | |
| "eval_steps_per_second": 3.144, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1, | |
| "learning_rate": 9.968366285544619e-05, | |
| "loss": 0.0179, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1, | |
| "eval_loss": 0.01846296340227127, | |
| "eval_mae": 0.10383900254964828, | |
| "eval_mse": 0.018469005823135376, | |
| "eval_r2": 0.17126507792798895, | |
| "eval_runtime": 64.4338, | |
| "eval_samples_per_second": 6.208, | |
| "eval_steps_per_second": 3.104, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1, | |
| "learning_rate": 9.945866620716411e-05, | |
| "loss": 0.0177, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1, | |
| "eval_loss": 0.01835346780717373, | |
| "eval_mae": 0.10348159074783325, | |
| "eval_mse": 0.018356231972575188, | |
| "eval_r2": 0.1812631242910432, | |
| "eval_runtime": 63.7952, | |
| "eval_samples_per_second": 6.27, | |
| "eval_steps_per_second": 3.135, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2, | |
| "learning_rate": 9.917399662815391e-05, | |
| "loss": 0.0176, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2, | |
| "eval_loss": 0.018152762204408646, | |
| "eval_mae": 0.10292253643274307, | |
| "eval_mse": 0.018158329650759697, | |
| "eval_r2": 0.18455260254083927, | |
| "eval_runtime": 62.2123, | |
| "eval_samples_per_second": 6.43, | |
| "eval_steps_per_second": 3.215, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2, | |
| "learning_rate": 9.882999757830588e-05, | |
| "loss": 0.0175, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2, | |
| "eval_loss": 0.018096117302775383, | |
| "eval_mae": 0.10270749032497406, | |
| "eval_mse": 0.01808706857264042, | |
| "eval_r2": 0.1878013710016545, | |
| "eval_runtime": 62.45, | |
| "eval_samples_per_second": 6.405, | |
| "eval_steps_per_second": 3.203, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2, | |
| "learning_rate": 9.842708409977635e-05, | |
| "loss": 0.0174, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2, | |
| "eval_loss": 0.018007792532444, | |
| "eval_mae": 0.10250235348939896, | |
| "eval_mse": 0.01801513321697712, | |
| "eval_r2": 0.19156642781886424, | |
| "eval_runtime": 62.617, | |
| "eval_samples_per_second": 6.388, | |
| "eval_steps_per_second": 3.194, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2, | |
| "learning_rate": 9.796574231623055e-05, | |
| "loss": 0.0173, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2, | |
| "eval_loss": 0.017887134104967117, | |
| "eval_mae": 0.10214251279830933, | |
| "eval_mse": 0.017883572727441788, | |
| "eval_r2": 0.19610529281414957, | |
| "eval_runtime": 63.0647, | |
| "eval_samples_per_second": 6.343, | |
| "eval_steps_per_second": 3.171, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2, | |
| "learning_rate": 9.744652884632406e-05, | |
| "loss": 0.0173, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2, | |
| "eval_loss": 0.017843402922153473, | |
| "eval_mae": 0.10201350599527359, | |
| "eval_mse": 0.017849572002887726, | |
| "eval_r2": 0.20036411183239422, | |
| "eval_runtime": 63.1964, | |
| "eval_samples_per_second": 6.329, | |
| "eval_steps_per_second": 3.165, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3, | |
| "learning_rate": 9.687007013213063e-05, | |
| "loss": 0.0172, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3, | |
| "eval_loss": 0.017804041504859924, | |
| "eval_mae": 0.10189322382211685, | |
| "eval_mse": 0.01781976968050003, | |
| "eval_r2": 0.20562580407293896, | |
| "eval_runtime": 63.7696, | |
| "eval_samples_per_second": 6.273, | |
| "eval_steps_per_second": 3.136, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3, | |
| "learning_rate": 9.623706168332645e-05, | |
| "loss": 0.0171, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3, | |
| "eval_loss": 0.017708342522382736, | |
| "eval_mae": 0.10164093226194382, | |
| "eval_mse": 0.017712706699967384, | |
| "eval_r2": 0.20602592052107038, | |
| "eval_runtime": 63.456, | |
| "eval_samples_per_second": 6.304, | |
| "eval_steps_per_second": 3.152, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3, | |
| "learning_rate": 9.554826723804303e-05, | |
| "loss": 0.017, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3, | |
| "eval_loss": 0.017668385058641434, | |
| "eval_mae": 0.10145936906337738, | |
| "eval_mse": 0.017669973894953728, | |
| "eval_r2": 0.20682701060142172, | |
| "eval_runtime": 63.5861, | |
| "eval_samples_per_second": 6.291, | |
| "eval_steps_per_second": 3.145, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3, | |
| "learning_rate": 9.480451784140091e-05, | |
| "loss": 0.017, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3, | |
| "eval_loss": 0.017553946003317833, | |
| "eval_mae": 0.10114699602127075, | |
| "eval_mse": 0.01755087450146675, | |
| "eval_r2": 0.2111549450823803, | |
| "eval_runtime": 62.7965, | |
| "eval_samples_per_second": 6.37, | |
| "eval_steps_per_second": 3.185, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3, | |
| "learning_rate": 9.400671084283607e-05, | |
| "loss": 0.017, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3, | |
| "eval_loss": 0.017535727471113205, | |
| "eval_mae": 0.10109320282936096, | |
| "eval_mse": 0.017534563317894936, | |
| "eval_r2": 0.21152867082641214, | |
| "eval_runtime": 62.081, | |
| "eval_samples_per_second": 6.443, | |
| "eval_steps_per_second": 3.222, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 4, | |
| "learning_rate": 9.315580881342876e-05, | |
| "loss": 0.0168, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4, | |
| "eval_loss": 0.01751740463078022, | |
| "eval_mae": 0.10102058947086334, | |
| "eval_mse": 0.017521008849143982, | |
| "eval_r2": 0.2173146917939317, | |
| "eval_runtime": 63.7702, | |
| "eval_samples_per_second": 6.273, | |
| "eval_steps_per_second": 3.136, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4, | |
| "learning_rate": 9.225283838454111e-05, | |
| "loss": 0.0169, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4, | |
| "eval_loss": 0.017473317682743073, | |
| "eval_mae": 0.1008896455168724, | |
| "eval_mse": 0.0174697358161211, | |
| "eval_r2": 0.21592913051237428, | |
| "eval_runtime": 63.0763, | |
| "eval_samples_per_second": 6.342, | |
| "eval_steps_per_second": 3.171, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4, | |
| "learning_rate": 9.129888900916456e-05, | |
| "loss": 0.0168, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4, | |
| "eval_loss": 0.01740197278559208, | |
| "eval_mae": 0.10066132992506027, | |
| "eval_mse": 0.017395442351698875, | |
| "eval_r2": 0.21965390849250066, | |
| "eval_runtime": 62.679, | |
| "eval_samples_per_second": 6.382, | |
| "eval_steps_per_second": 3.191, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4, | |
| "learning_rate": 9.029511164747175e-05, | |
| "loss": 0.0168, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 4, | |
| "eval_loss": 0.01737840846180916, | |
| "eval_mae": 0.100642628967762, | |
| "eval_mse": 0.01738792657852173, | |
| "eval_r2": 0.2177673870807011, | |
| "eval_runtime": 63.0635, | |
| "eval_samples_per_second": 6.343, | |
| "eval_steps_per_second": 3.171, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 5, | |
| "learning_rate": 8.924271737815854e-05, | |
| "loss": 0.0167, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5, | |
| "eval_loss": 0.017356639727950096, | |
| "eval_mae": 0.10054408758878708, | |
| "eval_mse": 0.01736092008650303, | |
| "eval_r2": 0.22268234003478382, | |
| "eval_runtime": 62.6903, | |
| "eval_samples_per_second": 6.381, | |
| "eval_steps_per_second": 3.19, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5, | |
| "learning_rate": 8.814297593725199e-05, | |
| "loss": 0.0167, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 5, | |
| "eval_loss": 0.017370322719216347, | |
| "eval_mae": 0.10060014575719833, | |
| "eval_mse": 0.017372848466038704, | |
| "eval_r2": 0.22218442610232647, | |
| "eval_runtime": 62.9578, | |
| "eval_samples_per_second": 6.353, | |
| "eval_steps_per_second": 3.177, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 5, | |
| "learning_rate": 8.699721418614673e-05, | |
| "loss": 0.0167, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 5, | |
| "eval_loss": 0.017255190759897232, | |
| "eval_mae": 0.10025202482938766, | |
| "eval_mse": 0.0172572061419487, | |
| "eval_r2": 0.2245981157395297, | |
| "eval_runtime": 62.725, | |
| "eval_samples_per_second": 6.377, | |
| "eval_steps_per_second": 3.189, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 5, | |
| "learning_rate": 8.580681451071866e-05, | |
| "loss": 0.0166, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 5, | |
| "eval_loss": 0.017206793650984764, | |
| "eval_mae": 0.10011155903339386, | |
| "eval_mse": 0.017209110781550407, | |
| "eval_r2": 0.22857719354252215, | |
| "eval_runtime": 63.8964, | |
| "eval_samples_per_second": 6.26, | |
| "eval_steps_per_second": 3.13, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 5, | |
| "learning_rate": 8.457321315344694e-05, | |
| "loss": 0.0167, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 5, | |
| "eval_loss": 0.017166156321763992, | |
| "eval_mae": 0.10000505298376083, | |
| "eval_mse": 0.017173225060105324, | |
| "eval_r2": 0.22773855218146166, | |
| "eval_runtime": 63.4268, | |
| "eval_samples_per_second": 6.306, | |
| "eval_steps_per_second": 3.153, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 6, | |
| "learning_rate": 8.329789848055704e-05, | |
| "loss": 0.0164, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 6, | |
| "eval_loss": 0.01718437485396862, | |
| "eval_mae": 0.10002291202545166, | |
| "eval_mse": 0.01718369498848915, | |
| "eval_r2": 0.2300388059901679, | |
| "eval_runtime": 63.8338, | |
| "eval_samples_per_second": 6.266, | |
| "eval_steps_per_second": 3.133, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 6, | |
| "learning_rate": 8.198240918627524e-05, | |
| "loss": 0.0166, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6, | |
| "eval_loss": 0.017157739028334618, | |
| "eval_mae": 0.09996546804904938, | |
| "eval_mse": 0.017160937190055847, | |
| "eval_r2": 0.23035895673172035, | |
| "eval_runtime": 62.0856, | |
| "eval_samples_per_second": 6.443, | |
| "eval_steps_per_second": 3.221, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6, | |
| "learning_rate": 8.062833243636134e-05, | |
| "loss": 0.0165, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 6, | |
| "eval_loss": 0.01712297834455967, | |
| "eval_mae": 0.09981416165828705, | |
| "eval_mse": 0.017125777900218964, | |
| "eval_r2": 0.23338275672251196, | |
| "eval_runtime": 62.5642, | |
| "eval_samples_per_second": 6.393, | |
| "eval_steps_per_second": 3.197, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 6, | |
| "learning_rate": 7.923730195315962e-05, | |
| "loss": 0.0165, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6, | |
| "eval_loss": 0.01711028628051281, | |
| "eval_mae": 0.09980826824903488, | |
| "eval_mse": 0.01711735874414444, | |
| "eval_r2": 0.23415986485617102, | |
| "eval_runtime": 63.2895, | |
| "eval_samples_per_second": 6.32, | |
| "eval_steps_per_second": 3.16, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6, | |
| "learning_rate": 7.781099604447794e-05, | |
| "loss": 0.0164, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 6, | |
| "eval_loss": 0.017070267349481583, | |
| "eval_mae": 0.09970243275165558, | |
| "eval_mse": 0.01707725040614605, | |
| "eval_r2": 0.23408428218933097, | |
| "eval_runtime": 62.7311, | |
| "eval_samples_per_second": 6.376, | |
| "eval_steps_per_second": 3.188, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 7, | |
| "learning_rate": 7.635113557867395e-05, | |
| "loss": 0.0165, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 7, | |
| "eval_loss": 0.017109189182519913, | |
| "eval_mae": 0.09978970885276794, | |
| "eval_mse": 0.017108654603362083, | |
| "eval_r2": 0.23454243286934806, | |
| "eval_runtime": 63.1248, | |
| "eval_samples_per_second": 6.337, | |
| "eval_steps_per_second": 3.168, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 7, | |
| "learning_rate": 7.485948190839077e-05, | |
| "loss": 0.0164, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 7, | |
| "eval_loss": 0.01705513708293438, | |
| "eval_mae": 0.09960421919822693, | |
| "eval_mse": 0.017058243975043297, | |
| "eval_r2": 0.2349071550024685, | |
| "eval_runtime": 62.8704, | |
| "eval_samples_per_second": 6.362, | |
| "eval_steps_per_second": 3.181, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 7, | |
| "learning_rate": 7.333783474544758e-05, | |
| "loss": 0.0165, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 7, | |
| "eval_loss": 0.01703445240855217, | |
| "eval_mae": 0.09956526756286621, | |
| "eval_mse": 0.017035936936736107, | |
| "eval_r2": 0.23700014890629983, | |
| "eval_runtime": 62.8756, | |
| "eval_samples_per_second": 6.362, | |
| "eval_steps_per_second": 3.181, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 7, | |
| "learning_rate": 7.178802998944933e-05, | |
| "loss": 0.0163, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 7, | |
| "eval_loss": 0.017014818266034126, | |
| "eval_mae": 0.09949322044849396, | |
| "eval_mse": 0.01701194979250431, | |
| "eval_r2": 0.23927528453479352, | |
| "eval_runtime": 62.7426, | |
| "eval_samples_per_second": 6.375, | |
| "eval_steps_per_second": 3.188, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 7, | |
| "learning_rate": 7.021193751273462e-05, | |
| "loss": 0.0163, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 7, | |
| "eval_loss": 0.016955234110355377, | |
| "eval_mae": 0.09930498152971268, | |
| "eval_mse": 0.01695319451391697, | |
| "eval_r2": 0.2370158653005695, | |
| "eval_runtime": 63.4621, | |
| "eval_samples_per_second": 6.303, | |
| "eval_steps_per_second": 3.151, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 8, | |
| "learning_rate": 6.86114589043352e-05, | |
| "loss": 0.0163, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 8, | |
| "eval_loss": 0.016957027837634087, | |
| "eval_mae": 0.09929080307483673, | |
| "eval_mse": 0.016954666003584862, | |
| "eval_r2": 0.23837789423341782, | |
| "eval_runtime": 63.6096, | |
| "eval_samples_per_second": 6.288, | |
| "eval_steps_per_second": 3.144, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 8, | |
| "learning_rate": 6.698852517566836e-05, | |
| "loss": 0.0163, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8, | |
| "eval_loss": 0.016924967989325523, | |
| "eval_mae": 0.09920791536569595, | |
| "eval_mse": 0.016921618953347206, | |
| "eval_r2": 0.23921405049323863, | |
| "eval_runtime": 62.3232, | |
| "eval_samples_per_second": 6.418, | |
| "eval_steps_per_second": 3.209, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8, | |
| "learning_rate": 6.534509443073072e-05, | |
| "loss": 0.0163, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 8, | |
| "eval_loss": 0.016955628991127014, | |
| "eval_mae": 0.09933258593082428, | |
| "eval_mse": 0.01695682480931282, | |
| "eval_r2": 0.24050878076217264, | |
| "eval_runtime": 62.7525, | |
| "eval_samples_per_second": 6.374, | |
| "eval_steps_per_second": 3.187, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 8, | |
| "learning_rate": 6.368314950360415e-05, | |
| "loss": 0.0163, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 8, | |
| "eval_loss": 0.016915885731577873, | |
| "eval_mae": 0.09923145920038223, | |
| "eval_mse": 0.01692046783864498, | |
| "eval_r2": 0.24116580712888347, | |
| "eval_runtime": 62.4103, | |
| "eval_samples_per_second": 6.409, | |
| "eval_steps_per_second": 3.205, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 9, | |
| "learning_rate": 6.200469556612435e-05, | |
| "loss": 0.0163, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 9, | |
| "eval_loss": 0.016883673146367073, | |
| "eval_mae": 0.09907432645559311, | |
| "eval_mse": 0.016882291063666344, | |
| "eval_r2": 0.23994247077801656, | |
| "eval_runtime": 63.1914, | |
| "eval_samples_per_second": 6.33, | |
| "eval_steps_per_second": 3.165, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 9, | |
| "learning_rate": 6.031175770859848e-05, | |
| "loss": 0.0163, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 9, | |
| "eval_loss": 0.01691693253815174, | |
| "eval_mae": 0.09921909868717194, | |
| "eval_mse": 0.01691514253616333, | |
| "eval_r2": 0.24448073571582285, | |
| "eval_runtime": 63.0869, | |
| "eval_samples_per_second": 6.34, | |
| "eval_steps_per_second": 3.17, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 9, | |
| "learning_rate": 5.8606378496490735e-05, | |
| "loss": 0.0163, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 9, | |
| "eval_loss": 0.01691095158457756, | |
| "eval_mae": 0.09917566925287247, | |
| "eval_mse": 0.016911856830120087, | |
| "eval_r2": 0.24367263560029062, | |
| "eval_runtime": 62.6214, | |
| "eval_samples_per_second": 6.388, | |
| "eval_steps_per_second": 3.194, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 9, | |
| "learning_rate": 5.6890615506023705e-05, | |
| "loss": 0.0162, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 9, | |
| "eval_loss": 0.016852255910634995, | |
| "eval_mae": 0.09895263612270355, | |
| "eval_mse": 0.016846586018800735, | |
| "eval_r2": 0.24440525606317043, | |
| "eval_runtime": 63.9638, | |
| "eval_samples_per_second": 6.254, | |
| "eval_steps_per_second": 3.127, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 9, | |
| "learning_rate": 5.5166538841669025e-05, | |
| "loss": 0.0161, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 9, | |
| "eval_loss": 0.016831671819090843, | |
| "eval_mae": 0.09894772619009018, | |
| "eval_mse": 0.01683351770043373, | |
| "eval_r2": 0.24440384235611556, | |
| "eval_runtime": 63.0545, | |
| "eval_samples_per_second": 6.344, | |
| "eval_steps_per_second": 3.172, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 10, | |
| "learning_rate": 5.343622863852232e-05, | |
| "loss": 0.0163, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 10, | |
| "eval_loss": 0.016827262938022614, | |
| "eval_mae": 0.09892594069242477, | |
| "eval_mse": 0.01683083176612854, | |
| "eval_r2": 0.24909316086739675, | |
| "eval_runtime": 62.71, | |
| "eval_samples_per_second": 6.379, | |
| "eval_steps_per_second": 3.189, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 10, | |
| "learning_rate": 5.170177255257618e-05, | |
| "loss": 0.0162, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 10, | |
| "eval_loss": 0.016822684556245804, | |
| "eval_mae": 0.09890511631965637, | |
| "eval_mse": 0.016828058287501335, | |
| "eval_r2": 0.24537013068417224, | |
| "eval_runtime": 62.313, | |
| "eval_samples_per_second": 6.419, | |
| "eval_steps_per_second": 3.21, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 10, | |
| "learning_rate": 4.996526324191872e-05, | |
| "loss": 0.0161, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 10, | |
| "eval_loss": 0.016806134954094887, | |
| "eval_mae": 0.09885768592357635, | |
| "eval_mse": 0.01680225133895874, | |
| "eval_r2": 0.24621643781805225, | |
| "eval_runtime": 62.9889, | |
| "eval_samples_per_second": 6.35, | |
| "eval_steps_per_second": 3.175, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 10, | |
| "learning_rate": 4.822879584189731e-05, | |
| "loss": 0.0162, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 10, | |
| "eval_loss": 0.01680067367851734, | |
| "eval_mae": 0.09885375201702118, | |
| "eval_mse": 0.01680714637041092, | |
| "eval_r2": 0.2480926793721172, | |
| "eval_runtime": 62.8794, | |
| "eval_samples_per_second": 6.361, | |
| "eval_steps_per_second": 3.181, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 10, | |
| "learning_rate": 4.6494465437293225e-05, | |
| "loss": 0.0162, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 10, | |
| "eval_loss": 0.01678573526442051, | |
| "eval_mae": 0.09876307845115662, | |
| "eval_mse": 0.01678406447172165, | |
| "eval_r2": 0.24622674800267175, | |
| "eval_runtime": 63.1145, | |
| "eval_samples_per_second": 6.338, | |
| "eval_steps_per_second": 3.169, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 11, | |
| "learning_rate": 4.476436453455742e-05, | |
| "loss": 0.0161, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 11, | |
| "eval_loss": 0.016767781227827072, | |
| "eval_mae": 0.09874103963375092, | |
| "eval_mse": 0.01676834560930729, | |
| "eval_r2": 0.24893675048568276, | |
| "eval_runtime": 63.6881, | |
| "eval_samples_per_second": 6.281, | |
| "eval_steps_per_second": 3.14, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 11, | |
| "learning_rate": 4.3040580537157024e-05, | |
| "loss": 0.0161, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 11, | |
| "eval_loss": 0.016766654327511787, | |
| "eval_mae": 0.0987214520573616, | |
| "eval_mse": 0.016764981672167778, | |
| "eval_r2": 0.24921689372938038, | |
| "eval_runtime": 62.2087, | |
| "eval_samples_per_second": 6.43, | |
| "eval_steps_per_second": 3.215, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 11, | |
| "learning_rate": 4.1325193227078816e-05, | |
| "loss": 0.0161, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 11, | |
| "eval_loss": 0.01673816703259945, | |
| "eval_mae": 0.09863594174385071, | |
| "eval_mse": 0.01673576422035694, | |
| "eval_r2": 0.24761288350255228, | |
| "eval_runtime": 62.9694, | |
| "eval_samples_per_second": 6.352, | |
| "eval_steps_per_second": 3.176, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 11, | |
| "learning_rate": 3.962027225552807e-05, | |
| "loss": 0.0162, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 11, | |
| "eval_loss": 0.016739826649427414, | |
| "eval_mae": 0.09863518178462982, | |
| "eval_mse": 0.016731785610318184, | |
| "eval_r2": 0.24922910335616988, | |
| "eval_runtime": 62.5788, | |
| "eval_samples_per_second": 6.392, | |
| "eval_steps_per_second": 3.196, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 11, | |
| "learning_rate": 3.79278746458504e-05, | |
| "loss": 0.0161, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 11, | |
| "eval_loss": 0.016736237332224846, | |
| "eval_mae": 0.09862860292196274, | |
| "eval_mse": 0.016738129779696465, | |
| "eval_r2": 0.24936630700011952, | |
| "eval_runtime": 63.2169, | |
| "eval_samples_per_second": 6.327, | |
| "eval_steps_per_second": 3.164, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 12, | |
| "learning_rate": 3.6250042311689505e-05, | |
| "loss": 0.0161, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 12, | |
| "eval_loss": 0.016720617190003395, | |
| "eval_mae": 0.09856829792261124, | |
| "eval_mse": 0.016721663996577263, | |
| "eval_r2": 0.24943757367634767, | |
| "eval_runtime": 62.9559, | |
| "eval_samples_per_second": 6.354, | |
| "eval_steps_per_second": 3.177, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 12, | |
| "learning_rate": 3.458879959337494e-05, | |
| "loss": 0.016, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 12, | |
| "eval_loss": 0.01672213524580002, | |
| "eval_mae": 0.0985676720738411, | |
| "eval_mse": 0.016720319166779518, | |
| "eval_r2": 0.24865355220765406, | |
| "eval_runtime": 63.4117, | |
| "eval_samples_per_second": 6.308, | |
| "eval_steps_per_second": 3.154, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 12, | |
| "learning_rate": 3.294615081551259e-05, | |
| "loss": 0.0161, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 12, | |
| "eval_loss": 0.016707362607121468, | |
| "eval_mae": 0.09850940108299255, | |
| "eval_mse": 0.016702940687537193, | |
| "eval_r2": 0.24840998553438287, | |
| "eval_runtime": 62.8197, | |
| "eval_samples_per_second": 6.367, | |
| "eval_steps_per_second": 3.184, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 12, | |
| "learning_rate": 3.132407786872442e-05, | |
| "loss": 0.0161, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 12, | |
| "eval_loss": 0.01671912521123886, | |
| "eval_mae": 0.09860337525606155, | |
| "eval_mse": 0.016718650236725807, | |
| "eval_r2": 0.2525614324396165, | |
| "eval_runtime": 62.3061, | |
| "eval_samples_per_second": 6.42, | |
| "eval_steps_per_second": 3.21, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 13, | |
| "learning_rate": 2.9724537818455466e-05, | |
| "loss": 0.016, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 13, | |
| "eval_loss": 0.016661079600453377, | |
| "eval_mae": 0.09843301773071289, | |
| "eval_mse": 0.016662681475281715, | |
| "eval_r2": 0.25208811381954643, | |
| "eval_runtime": 62.656, | |
| "eval_samples_per_second": 6.384, | |
| "eval_steps_per_second": 3.192, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 13, | |
| "learning_rate": 2.8149460543732664e-05, | |
| "loss": 0.0161, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 13, | |
| "eval_loss": 0.016676336526870728, | |
| "eval_mae": 0.09842842072248459, | |
| "eval_mse": 0.01667998544871807, | |
| "eval_r2": 0.25096189530992574, | |
| "eval_runtime": 61.8687, | |
| "eval_samples_per_second": 6.465, | |
| "eval_steps_per_second": 3.233, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 13, | |
| "learning_rate": 2.6600746408725063e-05, | |
| "loss": 0.0161, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 13, | |
| "eval_loss": 0.016732489690184593, | |
| "eval_mae": 0.09858258813619614, | |
| "eval_mse": 0.016734851524233818, | |
| "eval_r2": 0.25186837331344525, | |
| "eval_runtime": 62.9675, | |
| "eval_samples_per_second": 6.352, | |
| "eval_steps_per_second": 3.176, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 13, | |
| "learning_rate": 2.5080263969913897e-05, | |
| "loss": 0.016, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 13, | |
| "eval_loss": 0.016638994216918945, | |
| "eval_mae": 0.09835705161094666, | |
| "eval_mse": 0.016642747446894646, | |
| "eval_r2": 0.25120772331092656, | |
| "eval_runtime": 62.2252, | |
| "eval_samples_per_second": 6.428, | |
| "eval_steps_per_second": 3.214, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 13, | |
| "learning_rate": 2.3589847721639617e-05, | |
| "loss": 0.0161, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 13, | |
| "eval_loss": 0.01668979413807392, | |
| "eval_mae": 0.09847620874643326, | |
| "eval_mse": 0.016691412776708603, | |
| "eval_r2": 0.2516642585572433, | |
| "eval_runtime": 63.1219, | |
| "eval_samples_per_second": 6.337, | |
| "eval_steps_per_second": 3.168, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 14, | |
| "learning_rate": 2.2131295882745597e-05, | |
| "loss": 0.016, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 14, | |
| "eval_loss": 0.016662921756505966, | |
| "eval_mae": 0.09842050820589066, | |
| "eval_mse": 0.016670849174261093, | |
| "eval_r2": 0.2505160489332994, | |
| "eval_runtime": 62.776, | |
| "eval_samples_per_second": 6.372, | |
| "eval_steps_per_second": 3.186, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 14, | |
| "learning_rate": 2.070636822698877e-05, | |
| "loss": 0.0159, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 14, | |
| "eval_loss": 0.01665448024868965, | |
| "eval_mae": 0.09836740046739578, | |
| "eval_mse": 0.016657505184412003, | |
| "eval_r2": 0.25081546773511, | |
| "eval_runtime": 62.5067, | |
| "eval_samples_per_second": 6.399, | |
| "eval_steps_per_second": 3.2, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 14, | |
| "learning_rate": 1.9316783959835345e-05, | |
| "loss": 0.016, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 14, | |
| "eval_loss": 0.01669839210808277, | |
| "eval_mae": 0.09849409759044647, | |
| "eval_mse": 0.01669597439467907, | |
| "eval_r2": 0.25497888003639246, | |
| "eval_runtime": 63.4933, | |
| "eval_samples_per_second": 6.3, | |
| "eval_steps_per_second": 3.15, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 14, | |
| "learning_rate": 1.796421964420285e-05, | |
| "loss": 0.0161, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 14, | |
| "eval_loss": 0.01662326790392399, | |
| "eval_mae": 0.0982794538140297, | |
| "eval_mse": 0.016625171527266502, | |
| "eval_r2": 0.2520529598686879, | |
| "eval_runtime": 62.7103, | |
| "eval_samples_per_second": 6.379, | |
| "eval_steps_per_second": 3.189, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 14, | |
| "learning_rate": 1.665030717765149e-05, | |
| "loss": 0.016, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 14, | |
| "eval_loss": 0.016656357795000076, | |
| "eval_mae": 0.09835183620452881, | |
| "eval_mse": 0.016651729121804237, | |
| "eval_r2": 0.2521458867843698, | |
| "eval_runtime": 64.4578, | |
| "eval_samples_per_second": 6.206, | |
| "eval_steps_per_second": 3.103, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 15, | |
| "learning_rate": 1.5376631823464953e-05, | |
| "loss": 0.0161, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 15, | |
| "eval_loss": 0.01665300317108631, | |
| "eval_mae": 0.09836214780807495, | |
| "eval_mse": 0.01665370911359787, | |
| "eval_r2": 0.25267425736469795, | |
| "eval_runtime": 63.0441, | |
| "eval_samples_per_second": 6.345, | |
| "eval_steps_per_second": 3.172, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 15, | |
| "learning_rate": 1.4144730297996666e-05, | |
| "loss": 0.016, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 15, | |
| "eval_loss": 0.01662749983370304, | |
| "eval_mae": 0.09827445447444916, | |
| "eval_mse": 0.016627401113510132, | |
| "eval_r2": 0.2526889218862315, | |
| "eval_runtime": 62.6614, | |
| "eval_samples_per_second": 6.384, | |
| "eval_steps_per_second": 3.192, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 15, | |
| "learning_rate": 1.295608891658896e-05, | |
| "loss": 0.016, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 15, | |
| "eval_loss": 0.016592269763350487, | |
| "eval_mae": 0.09820396453142166, | |
| "eval_mse": 0.0165996253490448, | |
| "eval_r2": 0.25472996642841683, | |
| "eval_runtime": 63.4328, | |
| "eval_samples_per_second": 6.306, | |
| "eval_steps_per_second": 3.153, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 15, | |
| "learning_rate": 1.1812141800301945e-05, | |
| "loss": 0.016, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 15, | |
| "eval_loss": 0.016636423766613007, | |
| "eval_mae": 0.0983065739274025, | |
| "eval_mse": 0.016633499413728714, | |
| "eval_r2": 0.25374046203309764, | |
| "eval_runtime": 62.8839, | |
| "eval_samples_per_second": 6.361, | |
| "eval_steps_per_second": 3.18, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 15, | |
| "learning_rate": 1.0714269145616063e-05, | |
| "loss": 0.0159, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 15, | |
| "eval_loss": 0.016631022095680237, | |
| "eval_mae": 0.09828473627567291, | |
| "eval_mse": 0.01662875898182392, | |
| "eval_r2": 0.25143078561422905, | |
| "eval_runtime": 62.4886, | |
| "eval_samples_per_second": 6.401, | |
| "eval_steps_per_second": 3.201, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 16, | |
| "learning_rate": 9.663795559195733e-06, | |
| "loss": 0.0159, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 16, | |
| "eval_loss": 0.016640575602650642, | |
| "eval_mae": 0.09832051396369934, | |
| "eval_mse": 0.016639817506074905, | |
| "eval_r2": 0.25420519067693936, | |
| "eval_runtime": 63.7918, | |
| "eval_samples_per_second": 6.27, | |
| "eval_steps_per_second": 3.135, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 16, | |
| "learning_rate": 8.661988459723309e-06, | |
| "loss": 0.016, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 16, | |
| "eval_loss": 0.016633687540888786, | |
| "eval_mae": 0.09830807894468307, | |
| "eval_mse": 0.0166340135037899, | |
| "eval_r2": 0.2559419583101087, | |
| "eval_runtime": 64.9995, | |
| "eval_samples_per_second": 6.154, | |
| "eval_steps_per_second": 3.077, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 16, | |
| "learning_rate": 7.710056548731447e-06, | |
| "loss": 0.016, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 16, | |
| "eval_loss": 0.01665404625236988, | |
| "eval_mae": 0.09835316985845566, | |
| "eval_mse": 0.01665414310991764, | |
| "eval_r2": 0.25389154611800946, | |
| "eval_runtime": 63.3284, | |
| "eval_samples_per_second": 6.316, | |
| "eval_steps_per_second": 3.158, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 16, | |
| "learning_rate": 6.809148352279182e-06, | |
| "loss": 0.016, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 16, | |
| "eval_loss": 0.016643621027469635, | |
| "eval_mae": 0.09831266850233078, | |
| "eval_mse": 0.0166462492197752, | |
| "eval_r2": 0.253610910132235, | |
| "eval_runtime": 62.8474, | |
| "eval_samples_per_second": 6.365, | |
| "eval_steps_per_second": 3.182, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 16, | |
| "learning_rate": 5.960350835230766e-06, | |
| "loss": 0.0159, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 16, | |
| "eval_loss": 0.016641885042190552, | |
| "eval_mae": 0.09831728786230087, | |
| "eval_mse": 0.01664014533162117, | |
| "eval_r2": 0.2530172455633002, | |
| "eval_runtime": 62.9766, | |
| "eval_samples_per_second": 6.352, | |
| "eval_steps_per_second": 3.176, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 17, | |
| "learning_rate": 5.164688089809444e-06, | |
| "loss": 0.0159, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 17, | |
| "eval_loss": 0.016620321199297905, | |
| "eval_mae": 0.09825479984283447, | |
| "eval_mse": 0.016620123758912086, | |
| "eval_r2": 0.2543216647578763, | |
| "eval_runtime": 63.7821, | |
| "eval_samples_per_second": 6.271, | |
| "eval_steps_per_second": 3.136, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 17, | |
| "learning_rate": 4.423120100008582e-06, | |
| "loss": 0.016, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 17, | |
| "eval_loss": 0.016626114025712013, | |
| "eval_mae": 0.0982520654797554, | |
| "eval_mse": 0.01661662384867668, | |
| "eval_r2": 0.25688829356860643, | |
| "eval_runtime": 63.3768, | |
| "eval_samples_per_second": 6.311, | |
| "eval_steps_per_second": 3.156, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 17, | |
| "learning_rate": 3.7365415833504725e-06, | |
| "loss": 0.0159, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 17, | |
| "eval_loss": 0.016621023416519165, | |
| "eval_mae": 0.0982469841837883, | |
| "eval_mse": 0.01662403903901577, | |
| "eval_r2": 0.2562592876194061, | |
| "eval_runtime": 63.3616, | |
| "eval_samples_per_second": 6.313, | |
| "eval_steps_per_second": 3.156, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 17, | |
| "learning_rate": 3.105780911390738e-06, | |
| "loss": 0.016, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 17, | |
| "eval_loss": 0.01661110669374466, | |
| "eval_mae": 0.09821216762065887, | |
| "eval_mse": 0.016603710129857063, | |
| "eval_r2": 0.2534045631002596, | |
| "eval_runtime": 63.6674, | |
| "eval_samples_per_second": 6.283, | |
| "eval_steps_per_second": 3.141, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 18, | |
| "learning_rate": 2.5315991102703716e-06, | |
| "loss": 0.016, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 18, | |
| "eval_loss": 0.016594773158431053, | |
| "eval_mae": 0.09816820174455643, | |
| "eval_mse": 0.016600053757429123, | |
| "eval_r2": 0.25425809369382535, | |
| "eval_runtime": 63.3127, | |
| "eval_samples_per_second": 6.318, | |
| "eval_steps_per_second": 3.159, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 18, | |
| "learning_rate": 2.0146889425216476e-06, | |
| "loss": 0.016, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 18, | |
| "eval_loss": 0.016598813235759735, | |
| "eval_mae": 0.09816797077655792, | |
| "eval_mse": 0.016591567546129227, | |
| "eval_r2": 0.2551125072294508, | |
| "eval_runtime": 61.9837, | |
| "eval_samples_per_second": 6.453, | |
| "eval_steps_per_second": 3.227, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 18, | |
| "learning_rate": 1.555674071235358e-06, | |
| "loss": 0.0159, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 18, | |
| "eval_loss": 0.016573524102568626, | |
| "eval_mae": 0.09814300388097763, | |
| "eval_mse": 0.016571756452322006, | |
| "eval_r2": 0.25463921169715287, | |
| "eval_runtime": 63.1303, | |
| "eval_samples_per_second": 6.336, | |
| "eval_steps_per_second": 3.168, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 18, | |
| "learning_rate": 1.155108307598024e-06, | |
| "loss": 0.016, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 18, | |
| "eval_loss": 0.016580162569880486, | |
| "eval_mae": 0.09815159440040588, | |
| "eval_mse": 0.01658167876303196, | |
| "eval_r2": 0.25566179703610914, | |
| "eval_runtime": 63.3862, | |
| "eval_samples_per_second": 6.311, | |
| "eval_steps_per_second": 3.155, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 18, | |
| "learning_rate": 8.134749427070376e-07, | |
| "loss": 0.016, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 18, | |
| "eval_loss": 0.016592783853411674, | |
| "eval_mae": 0.0981706902384758, | |
| "eval_mse": 0.016597216948866844, | |
| "eval_r2": 0.25482598937850753, | |
| "eval_runtime": 63.3827, | |
| "eval_samples_per_second": 6.311, | |
| "eval_steps_per_second": 3.155, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 19, | |
| "learning_rate": 5.311861644696048e-07, | |
| "loss": 0.0159, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 19, | |
| "eval_loss": 0.01663564145565033, | |
| "eval_mae": 0.09826894104480743, | |
| "eval_mse": 0.0166276004165411, | |
| "eval_r2": 0.2547617221900892, | |
| "eval_runtime": 62.9726, | |
| "eval_samples_per_second": 6.352, | |
| "eval_steps_per_second": 3.176, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 19, | |
| "learning_rate": 3.0858256028932776e-07, | |
| "loss": 0.016, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 19, | |
| "eval_loss": 0.016616160050034523, | |
| "eval_mae": 0.09824874997138977, | |
| "eval_mse": 0.016616739332675934, | |
| "eval_r2": 0.2550670819722727, | |
| "eval_runtime": 62.541, | |
| "eval_samples_per_second": 6.396, | |
| "eval_steps_per_second": 3.198, | |
| "step": 4600 | |
| } | |
| ], | |
| "max_steps": 4760, | |
| "num_train_epochs": 20, | |
| "total_flos": 1.1833548390119886e+21, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |