| { | |
| "best_metric": 0.01686818338930607, | |
| "best_model_checkpoint": "/gpfs/gibbs/pi/dijk/BrainLM_runs/2023-11-17-17_20_00/checkpoint-3900", | |
| "epoch": 19.711664482306684, | |
| "global_step": 4700, | |
| "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": 0.0209, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0, | |
| "eval_loss": 0.020767875015735626, | |
| "eval_mae": 0.11019120365381241, | |
| "eval_mse": 0.020768500864505768, | |
| "eval_r2": 0.06256083852108052, | |
| "eval_runtime": 126.6828, | |
| "eval_samples_per_second": 3.157, | |
| "eval_steps_per_second": 0.197, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0, | |
| "learning_rate": 4.201680672268908e-05, | |
| "loss": 0.02, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0, | |
| "eval_loss": 0.020464899018406868, | |
| "eval_mae": 0.10934258252382278, | |
| "eval_mse": 0.02046414092183113, | |
| "eval_r2": 0.0822418520285656, | |
| "eval_runtime": 190.4097, | |
| "eval_samples_per_second": 2.101, | |
| "eval_steps_per_second": 0.131, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0, | |
| "learning_rate": 6.302521008403361e-05, | |
| "loss": 0.0196, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0, | |
| "eval_loss": 0.02013571746647358, | |
| "eval_mae": 0.10845349729061127, | |
| "eval_mse": 0.020132917910814285, | |
| "eval_r2": 0.09748306648229965, | |
| "eval_runtime": 60.1594, | |
| "eval_samples_per_second": 6.649, | |
| "eval_steps_per_second": 0.416, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0, | |
| "learning_rate": 8.403361344537815e-05, | |
| "loss": 0.0193, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0, | |
| "eval_loss": 0.019823560491204262, | |
| "eval_mae": 0.10756562650203705, | |
| "eval_mse": 0.019823383539915085, | |
| "eval_r2": 0.11099549304277823, | |
| "eval_runtime": 162.8488, | |
| "eval_samples_per_second": 2.456, | |
| "eval_steps_per_second": 0.154, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1, | |
| "learning_rate": 9.999826244478293e-05, | |
| "loss": 0.0191, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1, | |
| "eval_loss": 0.019535023719072342, | |
| "eval_mae": 0.10683062672615051, | |
| "eval_mse": 0.01953577809035778, | |
| "eval_r2": 0.12390402334988537, | |
| "eval_runtime": 61.7292, | |
| "eval_samples_per_second": 6.48, | |
| "eval_steps_per_second": 0.405, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1, | |
| "learning_rate": 9.995362383107962e-05, | |
| "loss": 0.0188, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1, | |
| "eval_loss": 0.019223904237151146, | |
| "eval_mae": 0.10594414174556732, | |
| "eval_mse": 0.019219543784856796, | |
| "eval_r2": 0.1355137630125941, | |
| "eval_runtime": 62.8456, | |
| "eval_samples_per_second": 6.365, | |
| "eval_steps_per_second": 0.398, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1, | |
| "learning_rate": 9.98487151097676e-05, | |
| "loss": 0.0185, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1, | |
| "eval_loss": 0.018948782235383987, | |
| "eval_mae": 0.10521063953638077, | |
| "eval_mse": 0.018949836492538452, | |
| "eval_r2": 0.1472992781550666, | |
| "eval_runtime": 62.8686, | |
| "eval_samples_per_second": 6.362, | |
| "eval_steps_per_second": 0.398, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1, | |
| "learning_rate": 9.968366285544619e-05, | |
| "loss": 0.0182, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1, | |
| "eval_loss": 0.01880819909274578, | |
| "eval_mae": 0.10481799393892288, | |
| "eval_mse": 0.01880812644958496, | |
| "eval_r2": 0.15779620957023455, | |
| "eval_runtime": 57.2628, | |
| "eval_samples_per_second": 6.985, | |
| "eval_steps_per_second": 0.437, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1, | |
| "learning_rate": 9.945866620716411e-05, | |
| "loss": 0.0181, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1, | |
| "eval_loss": 0.018690017983317375, | |
| "eval_mae": 0.10444584488868713, | |
| "eval_mse": 0.01869109459221363, | |
| "eval_r2": 0.16425393659247034, | |
| "eval_runtime": 58.6008, | |
| "eval_samples_per_second": 6.826, | |
| "eval_steps_per_second": 0.427, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2, | |
| "learning_rate": 9.917399662815391e-05, | |
| "loss": 0.0179, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2, | |
| "eval_loss": 0.018527410924434662, | |
| "eval_mae": 0.10401275008916855, | |
| "eval_mse": 0.018530065193772316, | |
| "eval_r2": 0.16775397819003413, | |
| "eval_runtime": 56.6595, | |
| "eval_samples_per_second": 7.06, | |
| "eval_steps_per_second": 0.441, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2, | |
| "learning_rate": 9.882999757830588e-05, | |
| "loss": 0.0179, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2, | |
| "eval_loss": 0.018433190882205963, | |
| "eval_mae": 0.10371904820203781, | |
| "eval_mse": 0.018430989235639572, | |
| "eval_r2": 0.17258796261060627, | |
| "eval_runtime": 61.318, | |
| "eval_samples_per_second": 6.523, | |
| "eval_steps_per_second": 0.408, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2, | |
| "learning_rate": 9.842708409977635e-05, | |
| "loss": 0.0178, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2, | |
| "eval_loss": 0.018353702500462532, | |
| "eval_mae": 0.1034744456410408, | |
| "eval_mse": 0.018353240564465523, | |
| "eval_r2": 0.17714196201923582, | |
| "eval_runtime": 64.7666, | |
| "eval_samples_per_second": 6.176, | |
| "eval_steps_per_second": 0.386, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2, | |
| "learning_rate": 9.796574231623055e-05, | |
| "loss": 0.0177, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2, | |
| "eval_loss": 0.018298938870429993, | |
| "eval_mae": 0.10329218953847885, | |
| "eval_mse": 0.01829737052321434, | |
| "eval_r2": 0.18098740062966168, | |
| "eval_runtime": 58.7251, | |
| "eval_samples_per_second": 6.811, | |
| "eval_steps_per_second": 0.426, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2, | |
| "learning_rate": 9.744652884632406e-05, | |
| "loss": 0.0176, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2, | |
| "eval_loss": 0.01817883551120758, | |
| "eval_mae": 0.10299910604953766, | |
| "eval_mse": 0.018180398270487785, | |
| "eval_r2": 0.1854382026037652, | |
| "eval_runtime": 64.0748, | |
| "eval_samples_per_second": 6.243, | |
| "eval_steps_per_second": 0.39, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3, | |
| "learning_rate": 9.687007013213063e-05, | |
| "loss": 0.0175, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3, | |
| "eval_loss": 0.018099399283528328, | |
| "eval_mae": 0.10274745523929596, | |
| "eval_mse": 0.018099674955010414, | |
| "eval_r2": 0.18714389318808033, | |
| "eval_runtime": 57.0327, | |
| "eval_samples_per_second": 7.014, | |
| "eval_steps_per_second": 0.438, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3, | |
| "learning_rate": 9.623706168332645e-05, | |
| "loss": 0.0174, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3, | |
| "eval_loss": 0.01805899292230606, | |
| "eval_mae": 0.1026226207613945, | |
| "eval_mse": 0.018060266971588135, | |
| "eval_r2": 0.19156849973920198, | |
| "eval_runtime": 58.7166, | |
| "eval_samples_per_second": 6.812, | |
| "eval_steps_per_second": 0.426, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3, | |
| "learning_rate": 9.554826723804303e-05, | |
| "loss": 0.0174, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3, | |
| "eval_loss": 0.01803247630596161, | |
| "eval_mae": 0.10254286229610443, | |
| "eval_mse": 0.018035681918263435, | |
| "eval_r2": 0.18969497919656642, | |
| "eval_runtime": 60.3899, | |
| "eval_samples_per_second": 6.624, | |
| "eval_steps_per_second": 0.414, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3, | |
| "learning_rate": 9.480451784140091e-05, | |
| "loss": 0.0173, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3, | |
| "eval_loss": 0.017897402867674828, | |
| "eval_mae": 0.1021430492401123, | |
| "eval_mse": 0.017896411940455437, | |
| "eval_r2": 0.1964586734458611, | |
| "eval_runtime": 62.8605, | |
| "eval_samples_per_second": 6.363, | |
| "eval_steps_per_second": 0.398, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3, | |
| "learning_rate": 9.400671084283607e-05, | |
| "loss": 0.0173, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3, | |
| "eval_loss": 0.017886007204651833, | |
| "eval_mae": 0.10208527743816376, | |
| "eval_mse": 0.01788811758160591, | |
| "eval_r2": 0.19957007249531145, | |
| "eval_runtime": 60.1438, | |
| "eval_samples_per_second": 6.651, | |
| "eval_steps_per_second": 0.416, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 4, | |
| "learning_rate": 9.315580881342876e-05, | |
| "loss": 0.0172, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4, | |
| "eval_loss": 0.017858153209090233, | |
| "eval_mae": 0.10202876478433609, | |
| "eval_mse": 0.017859304323792458, | |
| "eval_r2": 0.19855005202715592, | |
| "eval_runtime": 58.8873, | |
| "eval_samples_per_second": 6.793, | |
| "eval_steps_per_second": 0.425, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4, | |
| "learning_rate": 9.225283838454111e-05, | |
| "loss": 0.0172, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4, | |
| "eval_loss": 0.017775438725948334, | |
| "eval_mae": 0.10180441290140152, | |
| "eval_mse": 0.017775651067495346, | |
| "eval_r2": 0.20128072921203966, | |
| "eval_runtime": 65.7432, | |
| "eval_samples_per_second": 6.084, | |
| "eval_steps_per_second": 0.38, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4, | |
| "learning_rate": 9.129888900916456e-05, | |
| "loss": 0.0171, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4, | |
| "eval_loss": 0.01773221045732498, | |
| "eval_mae": 0.10164433717727661, | |
| "eval_mse": 0.017730284482240677, | |
| "eval_r2": 0.20249305414753993, | |
| "eval_runtime": 56.7262, | |
| "eval_samples_per_second": 7.051, | |
| "eval_steps_per_second": 0.441, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4, | |
| "learning_rate": 9.029511164747175e-05, | |
| "loss": 0.0172, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 4, | |
| "eval_loss": 0.017706887796521187, | |
| "eval_mae": 0.10156488418579102, | |
| "eval_mse": 0.017707258462905884, | |
| "eval_r2": 0.2078045399984002, | |
| "eval_runtime": 58.2849, | |
| "eval_samples_per_second": 6.863, | |
| "eval_steps_per_second": 0.429, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 5, | |
| "learning_rate": 8.924271737815854e-05, | |
| "loss": 0.0171, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5, | |
| "eval_loss": 0.017714276909828186, | |
| "eval_mae": 0.10158883035182953, | |
| "eval_mse": 0.017715107649564743, | |
| "eval_r2": 0.2074889762440164, | |
| "eval_runtime": 57.6803, | |
| "eval_samples_per_second": 6.935, | |
| "eval_steps_per_second": 0.433, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5, | |
| "learning_rate": 8.814297593725199e-05, | |
| "loss": 0.0171, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 5, | |
| "eval_loss": 0.017648547887802124, | |
| "eval_mae": 0.10141555964946747, | |
| "eval_mse": 0.017654363065958023, | |
| "eval_r2": 0.20722885865364904, | |
| "eval_runtime": 64.9526, | |
| "eval_samples_per_second": 6.158, | |
| "eval_steps_per_second": 0.385, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 5, | |
| "learning_rate": 8.699721418614673e-05, | |
| "loss": 0.017, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 5, | |
| "eval_loss": 0.017601532861590385, | |
| "eval_mae": 0.10125792026519775, | |
| "eval_mse": 0.017598113045096397, | |
| "eval_r2": 0.20836808697871778, | |
| "eval_runtime": 57.4819, | |
| "eval_samples_per_second": 6.959, | |
| "eval_steps_per_second": 0.435, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 5, | |
| "learning_rate": 8.580681451071866e-05, | |
| "loss": 0.017, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 5, | |
| "eval_loss": 0.017580362036824226, | |
| "eval_mae": 0.10121016204357147, | |
| "eval_mse": 0.017584411427378654, | |
| "eval_r2": 0.21084466622121223, | |
| "eval_runtime": 60.2943, | |
| "eval_samples_per_second": 6.634, | |
| "eval_steps_per_second": 0.415, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 5, | |
| "learning_rate": 8.457321315344694e-05, | |
| "loss": 0.017, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 5, | |
| "eval_loss": 0.017519284039735794, | |
| "eval_mae": 0.10104001313447952, | |
| "eval_mse": 0.01752064935863018, | |
| "eval_r2": 0.2120289842294325, | |
| "eval_runtime": 60.1697, | |
| "eval_samples_per_second": 6.648, | |
| "eval_steps_per_second": 0.415, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 6, | |
| "learning_rate": 8.329789848055704e-05, | |
| "loss": 0.0168, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 6, | |
| "eval_loss": 0.017550144344568253, | |
| "eval_mae": 0.10109207779169083, | |
| "eval_mse": 0.017550604417920113, | |
| "eval_r2": 0.2133444473175402, | |
| "eval_runtime": 61.3969, | |
| "eval_samples_per_second": 6.515, | |
| "eval_steps_per_second": 0.407, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 6, | |
| "learning_rate": 8.198240918627524e-05, | |
| "loss": 0.0169, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6, | |
| "eval_loss": 0.01755845546722412, | |
| "eval_mae": 0.10110194236040115, | |
| "eval_mse": 0.017556479200720787, | |
| "eval_r2": 0.21656763083400632, | |
| "eval_runtime": 59.5515, | |
| "eval_samples_per_second": 6.717, | |
| "eval_steps_per_second": 0.42, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6, | |
| "learning_rate": 8.062833243636134e-05, | |
| "loss": 0.0169, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 6, | |
| "eval_loss": 0.017458565533161163, | |
| "eval_mae": 0.10081926733255386, | |
| "eval_mse": 0.017458630725741386, | |
| "eval_r2": 0.21455437331377625, | |
| "eval_runtime": 60.6637, | |
| "eval_samples_per_second": 6.594, | |
| "eval_steps_per_second": 0.412, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 6, | |
| "learning_rate": 7.923730195315962e-05, | |
| "loss": 0.0169, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6, | |
| "eval_loss": 0.017479494214057922, | |
| "eval_mae": 0.10087893158197403, | |
| "eval_mse": 0.017478736117482185, | |
| "eval_r2": 0.2180120287564331, | |
| "eval_runtime": 60.772, | |
| "eval_samples_per_second": 6.582, | |
| "eval_steps_per_second": 0.411, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6, | |
| "learning_rate": 7.781099604447794e-05, | |
| "loss": 0.0168, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 6, | |
| "eval_loss": 0.01743287593126297, | |
| "eval_mae": 0.10074793547391891, | |
| "eval_mse": 0.017432522028684616, | |
| "eval_r2": 0.2161429733042286, | |
| "eval_runtime": 64.79, | |
| "eval_samples_per_second": 6.174, | |
| "eval_steps_per_second": 0.386, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 7, | |
| "learning_rate": 7.635113557867395e-05, | |
| "loss": 0.0169, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 7, | |
| "eval_loss": 0.017418913543224335, | |
| "eval_mae": 0.10069431364536285, | |
| "eval_mse": 0.01741931587457657, | |
| "eval_r2": 0.2169098601070394, | |
| "eval_runtime": 60.5486, | |
| "eval_samples_per_second": 6.606, | |
| "eval_steps_per_second": 0.413, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 7, | |
| "learning_rate": 7.485948190839077e-05, | |
| "loss": 0.0168, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 7, | |
| "eval_loss": 0.01736665517091751, | |
| "eval_mae": 0.1005297377705574, | |
| "eval_mse": 0.01736704632639885, | |
| "eval_r2": 0.21929555782464094, | |
| "eval_runtime": 58.4317, | |
| "eval_samples_per_second": 6.846, | |
| "eval_steps_per_second": 0.428, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 7, | |
| "learning_rate": 7.333783474544758e-05, | |
| "loss": 0.0168, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 7, | |
| "eval_loss": 0.017343418672680855, | |
| "eval_mae": 0.10048038512468338, | |
| "eval_mse": 0.017341628670692444, | |
| "eval_r2": 0.21864552418706762, | |
| "eval_runtime": 60.3965, | |
| "eval_samples_per_second": 6.623, | |
| "eval_steps_per_second": 0.414, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 7, | |
| "learning_rate": 7.178802998944933e-05, | |
| "loss": 0.0166, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 7, | |
| "eval_loss": 0.017404844984412193, | |
| "eval_mae": 0.10062351077795029, | |
| "eval_mse": 0.017404979094862938, | |
| "eval_r2": 0.22093177958560895, | |
| "eval_runtime": 56.7185, | |
| "eval_samples_per_second": 7.052, | |
| "eval_steps_per_second": 0.441, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 7, | |
| "learning_rate": 7.021193751273462e-05, | |
| "loss": 0.0167, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 7, | |
| "eval_loss": 0.017301246523857117, | |
| "eval_mae": 0.10035215318202972, | |
| "eval_mse": 0.017301900312304497, | |
| "eval_r2": 0.22134026003758744, | |
| "eval_runtime": 57.7642, | |
| "eval_samples_per_second": 6.925, | |
| "eval_steps_per_second": 0.433, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 8, | |
| "learning_rate": 6.86114589043352e-05, | |
| "loss": 0.0167, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 8, | |
| "eval_loss": 0.01728537492454052, | |
| "eval_mae": 0.10028935223817825, | |
| "eval_mse": 0.017283864319324493, | |
| "eval_r2": 0.2218958493073836, | |
| "eval_runtime": 61.7673, | |
| "eval_samples_per_second": 6.476, | |
| "eval_steps_per_second": 0.405, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 8, | |
| "learning_rate": 6.698852517566836e-05, | |
| "loss": 0.0167, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8, | |
| "eval_loss": 0.0173500906676054, | |
| "eval_mae": 0.10045037418603897, | |
| "eval_mse": 0.017350492998957634, | |
| "eval_r2": 0.222062406323153, | |
| "eval_runtime": 63.3674, | |
| "eval_samples_per_second": 6.312, | |
| "eval_steps_per_second": 0.395, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8, | |
| "learning_rate": 6.534509443073072e-05, | |
| "loss": 0.0166, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 8, | |
| "eval_loss": 0.017278773710131645, | |
| "eval_mae": 0.10025625675916672, | |
| "eval_mse": 0.017278244718909264, | |
| "eval_r2": 0.22539687501717476, | |
| "eval_runtime": 57.2192, | |
| "eval_samples_per_second": 6.991, | |
| "eval_steps_per_second": 0.437, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 8, | |
| "learning_rate": 6.368314950360415e-05, | |
| "loss": 0.0166, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 8, | |
| "eval_loss": 0.017245473340153694, | |
| "eval_mae": 0.10017417371273041, | |
| "eval_mse": 0.017246615141630173, | |
| "eval_r2": 0.22572849115543347, | |
| "eval_runtime": 59.9387, | |
| "eval_samples_per_second": 6.673, | |
| "eval_steps_per_second": 0.417, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 9, | |
| "learning_rate": 6.200469556612435e-05, | |
| "loss": 0.0166, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 9, | |
| "eval_loss": 0.017270274460315704, | |
| "eval_mae": 0.10024827718734741, | |
| "eval_mse": 0.017270220443606377, | |
| "eval_r2": 0.22628471179764975, | |
| "eval_runtime": 63.0094, | |
| "eval_samples_per_second": 6.348, | |
| "eval_steps_per_second": 0.397, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 9, | |
| "learning_rate": 6.031175770859848e-05, | |
| "loss": 0.0166, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 9, | |
| "eval_loss": 0.017215639352798462, | |
| "eval_mae": 0.10008691996335983, | |
| "eval_mse": 0.017215678468346596, | |
| "eval_r2": 0.22768342129753605, | |
| "eval_runtime": 65.042, | |
| "eval_samples_per_second": 6.15, | |
| "eval_steps_per_second": 0.384, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 9, | |
| "learning_rate": 5.8606378496490735e-05, | |
| "loss": 0.0166, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 9, | |
| "eval_loss": 0.01721777580678463, | |
| "eval_mae": 0.10010144114494324, | |
| "eval_mse": 0.017218952998518944, | |
| "eval_r2": 0.22907452898565506, | |
| "eval_runtime": 65.4931, | |
| "eval_samples_per_second": 6.108, | |
| "eval_steps_per_second": 0.382, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 9, | |
| "learning_rate": 5.6890615506023705e-05, | |
| "loss": 0.0166, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 9, | |
| "eval_loss": 0.017191417515277863, | |
| "eval_mae": 0.10001853853464127, | |
| "eval_mse": 0.01718985289335251, | |
| "eval_r2": 0.2292284056000078, | |
| "eval_runtime": 64.9938, | |
| "eval_samples_per_second": 6.154, | |
| "eval_steps_per_second": 0.385, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 9, | |
| "learning_rate": 5.5166538841669025e-05, | |
| "loss": 0.0165, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 9, | |
| "eval_loss": 0.017166707664728165, | |
| "eval_mae": 0.09992814064025879, | |
| "eval_mse": 0.017164934426546097, | |
| "eval_r2": 0.23049413465235846, | |
| "eval_runtime": 63.4634, | |
| "eval_samples_per_second": 6.303, | |
| "eval_steps_per_second": 0.394, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 10, | |
| "learning_rate": 5.343622863852232e-05, | |
| "loss": 0.0166, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 10, | |
| "eval_loss": 0.017118161544203758, | |
| "eval_mae": 0.0998067557811737, | |
| "eval_mse": 0.017116105183959007, | |
| "eval_r2": 0.23199928273221992, | |
| "eval_runtime": 58.0985, | |
| "eval_samples_per_second": 6.885, | |
| "eval_steps_per_second": 0.43, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 10, | |
| "learning_rate": 5.170177255257618e-05, | |
| "loss": 0.0165, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 10, | |
| "eval_loss": 0.017119385302066803, | |
| "eval_mae": 0.09977566450834274, | |
| "eval_mse": 0.017119543626904488, | |
| "eval_r2": 0.22948023375281368, | |
| "eval_runtime": 58.2148, | |
| "eval_samples_per_second": 6.871, | |
| "eval_steps_per_second": 0.429, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 10, | |
| "learning_rate": 4.996526324191872e-05, | |
| "loss": 0.0164, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 10, | |
| "eval_loss": 0.017105862498283386, | |
| "eval_mae": 0.09975843131542206, | |
| "eval_mse": 0.017107795923948288, | |
| "eval_r2": 0.23160311839973746, | |
| "eval_runtime": 58.2306, | |
| "eval_samples_per_second": 6.869, | |
| "eval_steps_per_second": 0.429, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 10, | |
| "learning_rate": 4.822879584189731e-05, | |
| "loss": 0.0165, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 10, | |
| "eval_loss": 0.017133817076683044, | |
| "eval_mae": 0.09982656687498093, | |
| "eval_mse": 0.01713182032108307, | |
| "eval_r2": 0.23212640913876725, | |
| "eval_runtime": 60.6469, | |
| "eval_samples_per_second": 6.596, | |
| "eval_steps_per_second": 0.412, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 10, | |
| "learning_rate": 4.6494465437293225e-05, | |
| "loss": 0.0165, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 10, | |
| "eval_loss": 0.01714298315346241, | |
| "eval_mae": 0.0998401865363121, | |
| "eval_mse": 0.017137613147497177, | |
| "eval_r2": 0.2327516850849627, | |
| "eval_runtime": 58.7954, | |
| "eval_samples_per_second": 6.803, | |
| "eval_steps_per_second": 0.425, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 11, | |
| "learning_rate": 4.476436453455742e-05, | |
| "loss": 0.0164, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 11, | |
| "eval_loss": 0.017095215618610382, | |
| "eval_mae": 0.09970412403345108, | |
| "eval_mse": 0.01709286868572235, | |
| "eval_r2": 0.23346266146762296, | |
| "eval_runtime": 57.7966, | |
| "eval_samples_per_second": 6.921, | |
| "eval_steps_per_second": 0.433, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 11, | |
| "learning_rate": 4.3040580537157024e-05, | |
| "loss": 0.0165, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 11, | |
| "eval_loss": 0.017114490270614624, | |
| "eval_mae": 0.09975600242614746, | |
| "eval_mse": 0.01711602509021759, | |
| "eval_r2": 0.23458319148513607, | |
| "eval_runtime": 60.7105, | |
| "eval_samples_per_second": 6.589, | |
| "eval_steps_per_second": 0.412, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 11, | |
| "learning_rate": 4.1325193227078816e-05, | |
| "loss": 0.0164, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 11, | |
| "eval_loss": 0.01703326217830181, | |
| "eval_mae": 0.0995149165391922, | |
| "eval_mse": 0.01703346148133278, | |
| "eval_r2": 0.23379130521799119, | |
| "eval_runtime": 56.541, | |
| "eval_samples_per_second": 7.075, | |
| "eval_steps_per_second": 0.442, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 11, | |
| "learning_rate": 3.962027225552807e-05, | |
| "loss": 0.0165, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 11, | |
| "eval_loss": 0.017094749957323074, | |
| "eval_mae": 0.09970033168792725, | |
| "eval_mse": 0.017094548791646957, | |
| "eval_r2": 0.2349240350955354, | |
| "eval_runtime": 65.2081, | |
| "eval_samples_per_second": 6.134, | |
| "eval_steps_per_second": 0.383, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 11, | |
| "learning_rate": 3.79278746458504e-05, | |
| "loss": 0.0164, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 11, | |
| "eval_loss": 0.017008375376462936, | |
| "eval_mae": 0.09947662055492401, | |
| "eval_mse": 0.01700720377266407, | |
| "eval_r2": 0.23690627111999107, | |
| "eval_runtime": 57.0201, | |
| "eval_samples_per_second": 7.015, | |
| "eval_steps_per_second": 0.438, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 12, | |
| "learning_rate": 3.6250042311689505e-05, | |
| "loss": 0.0164, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 12, | |
| "eval_loss": 0.01702900230884552, | |
| "eval_mae": 0.09952793270349503, | |
| "eval_mse": 0.01703030802309513, | |
| "eval_r2": 0.23451840328295703, | |
| "eval_runtime": 59.8559, | |
| "eval_samples_per_second": 6.683, | |
| "eval_steps_per_second": 0.418, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 12, | |
| "learning_rate": 3.458879959337494e-05, | |
| "loss": 0.0163, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 12, | |
| "eval_loss": 0.017079642042517662, | |
| "eval_mae": 0.09966063499450684, | |
| "eval_mse": 0.017079809680581093, | |
| "eval_r2": 0.23587889518099114, | |
| "eval_runtime": 63.9836, | |
| "eval_samples_per_second": 6.252, | |
| "eval_steps_per_second": 0.391, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 12, | |
| "learning_rate": 3.294615081551259e-05, | |
| "loss": 0.0164, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 12, | |
| "eval_loss": 0.017014725133776665, | |
| "eval_mae": 0.09949040412902832, | |
| "eval_mse": 0.01701604574918747, | |
| "eval_r2": 0.2344194498588299, | |
| "eval_runtime": 64.9206, | |
| "eval_samples_per_second": 6.161, | |
| "eval_steps_per_second": 0.385, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 12, | |
| "learning_rate": 3.132407786872442e-05, | |
| "loss": 0.0164, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 12, | |
| "eval_loss": 0.017031442373991013, | |
| "eval_mae": 0.09950780868530273, | |
| "eval_mse": 0.01702970452606678, | |
| "eval_r2": 0.23397646038139297, | |
| "eval_runtime": 63.2282, | |
| "eval_samples_per_second": 6.326, | |
| "eval_steps_per_second": 0.395, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 13, | |
| "learning_rate": 2.9724537818455466e-05, | |
| "loss": 0.0163, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 13, | |
| "eval_loss": 0.017020680010318756, | |
| "eval_mae": 0.099485382437706, | |
| "eval_mse": 0.0170209389179945, | |
| "eval_r2": 0.23745581810255922, | |
| "eval_runtime": 57.2248, | |
| "eval_samples_per_second": 6.99, | |
| "eval_steps_per_second": 0.437, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 13, | |
| "learning_rate": 2.8149460543732664e-05, | |
| "loss": 0.0164, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 13, | |
| "eval_loss": 0.016971083357930183, | |
| "eval_mae": 0.09935550391674042, | |
| "eval_mse": 0.016970161348581314, | |
| "eval_r2": 0.23819887983596166, | |
| "eval_runtime": 58.3514, | |
| "eval_samples_per_second": 6.855, | |
| "eval_steps_per_second": 0.428, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 13, | |
| "learning_rate": 2.6600746408725063e-05, | |
| "loss": 0.0163, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 13, | |
| "eval_loss": 0.01702103763818741, | |
| "eval_mae": 0.09947419166564941, | |
| "eval_mse": 0.017017606645822525, | |
| "eval_r2": 0.23663776763542477, | |
| "eval_runtime": 65.0546, | |
| "eval_samples_per_second": 6.149, | |
| "eval_steps_per_second": 0.384, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 13, | |
| "learning_rate": 2.5080263969913897e-05, | |
| "loss": 0.0163, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 13, | |
| "eval_loss": 0.01702267862856388, | |
| "eval_mae": 0.09951028972864151, | |
| "eval_mse": 0.017020724713802338, | |
| "eval_r2": 0.23804915917081026, | |
| "eval_runtime": 63.3322, | |
| "eval_samples_per_second": 6.316, | |
| "eval_steps_per_second": 0.395, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 13, | |
| "learning_rate": 2.3589847721639617e-05, | |
| "loss": 0.0164, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 13, | |
| "eval_loss": 0.01695895753800869, | |
| "eval_mae": 0.09931185096502304, | |
| "eval_mse": 0.016959920525550842, | |
| "eval_r2": 0.23948235402533236, | |
| "eval_runtime": 62.2021, | |
| "eval_samples_per_second": 6.431, | |
| "eval_steps_per_second": 0.402, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 14, | |
| "learning_rate": 2.2131295882745597e-05, | |
| "loss": 0.0163, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 14, | |
| "eval_loss": 0.016953853890299797, | |
| "eval_mae": 0.09930908679962158, | |
| "eval_mse": 0.016957899555563927, | |
| "eval_r2": 0.2384040127996312, | |
| "eval_runtime": 59.6825, | |
| "eval_samples_per_second": 6.702, | |
| "eval_steps_per_second": 0.419, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 14, | |
| "learning_rate": 2.070636822698877e-05, | |
| "loss": 0.0162, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 14, | |
| "eval_loss": 0.016969269141554832, | |
| "eval_mae": 0.09930410981178284, | |
| "eval_mse": 0.016971617937088013, | |
| "eval_r2": 0.23911331324321627, | |
| "eval_runtime": 61.4012, | |
| "eval_samples_per_second": 6.515, | |
| "eval_steps_per_second": 0.407, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 14, | |
| "learning_rate": 1.9316783959835345e-05, | |
| "loss": 0.0164, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 14, | |
| "eval_loss": 0.01695878989994526, | |
| "eval_mae": 0.09929464012384415, | |
| "eval_mse": 0.016956914216279984, | |
| "eval_r2": 0.23904322049736015, | |
| "eval_runtime": 61.0952, | |
| "eval_samples_per_second": 6.547, | |
| "eval_steps_per_second": 0.409, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 14, | |
| "learning_rate": 1.796421964420285e-05, | |
| "loss": 0.0164, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 14, | |
| "eval_loss": 0.016925431787967682, | |
| "eval_mae": 0.09921905398368835, | |
| "eval_mse": 0.016928432509303093, | |
| "eval_r2": 0.23861995325924557, | |
| "eval_runtime": 58.2956, | |
| "eval_samples_per_second": 6.862, | |
| "eval_steps_per_second": 0.429, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 14, | |
| "learning_rate": 1.665030717765149e-05, | |
| "loss": 0.0163, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 14, | |
| "eval_loss": 0.016955168917775154, | |
| "eval_mae": 0.09928599745035172, | |
| "eval_mse": 0.016958734020590782, | |
| "eval_r2": 0.24003949016117532, | |
| "eval_runtime": 60.224, | |
| "eval_samples_per_second": 6.642, | |
| "eval_steps_per_second": 0.415, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 15, | |
| "learning_rate": 1.5376631823464953e-05, | |
| "loss": 0.0163, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 15, | |
| "eval_loss": 0.017045069485902786, | |
| "eval_mae": 0.09952731430530548, | |
| "eval_mse": 0.017046233639121056, | |
| "eval_r2": 0.2409846653602259, | |
| "eval_runtime": 56.9312, | |
| "eval_samples_per_second": 7.026, | |
| "eval_steps_per_second": 0.439, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 15, | |
| "learning_rate": 1.4144730297996666e-05, | |
| "loss": 0.0163, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 15, | |
| "eval_loss": 0.01690911501646042, | |
| "eval_mae": 0.09913720935583115, | |
| "eval_mse": 0.01690947264432907, | |
| "eval_r2": 0.24005320295619414, | |
| "eval_runtime": 63.4396, | |
| "eval_samples_per_second": 6.305, | |
| "eval_steps_per_second": 0.394, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 15, | |
| "learning_rate": 1.295608891658896e-05, | |
| "loss": 0.0163, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 15, | |
| "eval_loss": 0.016995713114738464, | |
| "eval_mae": 0.09939228743314743, | |
| "eval_mse": 0.016998106613755226, | |
| "eval_r2": 0.24257331961419693, | |
| "eval_runtime": 58.9315, | |
| "eval_samples_per_second": 6.788, | |
| "eval_steps_per_second": 0.424, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 15, | |
| "learning_rate": 1.1812141800301945e-05, | |
| "loss": 0.0163, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 15, | |
| "eval_loss": 0.01695888675749302, | |
| "eval_mae": 0.09927807003259659, | |
| "eval_mse": 0.016960280016064644, | |
| "eval_r2": 0.24255255772513262, | |
| "eval_runtime": 58.2565, | |
| "eval_samples_per_second": 6.866, | |
| "eval_steps_per_second": 0.429, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 15, | |
| "learning_rate": 1.0714269145616063e-05, | |
| "loss": 0.0163, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 15, | |
| "eval_loss": 0.016934260725975037, | |
| "eval_mae": 0.09918724000453949, | |
| "eval_mse": 0.016934024170041084, | |
| "eval_r2": 0.23905501031932674, | |
| "eval_runtime": 59.5916, | |
| "eval_samples_per_second": 6.712, | |
| "eval_steps_per_second": 0.42, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 16, | |
| "learning_rate": 9.663795559195733e-06, | |
| "loss": 0.0162, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 16, | |
| "eval_loss": 0.016940169036388397, | |
| "eval_mae": 0.09923317283391953, | |
| "eval_mse": 0.016941731795668602, | |
| "eval_r2": 0.2415171870593763, | |
| "eval_runtime": 59.9307, | |
| "eval_samples_per_second": 6.674, | |
| "eval_steps_per_second": 0.417, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 16, | |
| "learning_rate": 8.661988459723309e-06, | |
| "loss": 0.0163, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 16, | |
| "eval_loss": 0.01686818338930607, | |
| "eval_mae": 0.09902676939964294, | |
| "eval_mse": 0.01686619035899639, | |
| "eval_r2": 0.23881856654464984, | |
| "eval_runtime": 59.939, | |
| "eval_samples_per_second": 6.673, | |
| "eval_steps_per_second": 0.417, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 16, | |
| "learning_rate": 7.710056548731447e-06, | |
| "loss": 0.0164, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 16, | |
| "eval_loss": 0.01692971959710121, | |
| "eval_mae": 0.09918209910392761, | |
| "eval_mse": 0.01693139225244522, | |
| "eval_r2": 0.24229291180997825, | |
| "eval_runtime": 58.0894, | |
| "eval_samples_per_second": 6.886, | |
| "eval_steps_per_second": 0.43, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 16, | |
| "learning_rate": 6.809148352279182e-06, | |
| "loss": 0.0163, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 16, | |
| "eval_loss": 0.016949491575360298, | |
| "eval_mae": 0.09925098717212677, | |
| "eval_mse": 0.01695188321173191, | |
| "eval_r2": 0.23993232169758605, | |
| "eval_runtime": 61.4621, | |
| "eval_samples_per_second": 6.508, | |
| "eval_steps_per_second": 0.407, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 16, | |
| "learning_rate": 5.960350835230766e-06, | |
| "loss": 0.0163, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 16, | |
| "eval_loss": 0.016934702172875404, | |
| "eval_mae": 0.09920256584882736, | |
| "eval_mse": 0.016937121748924255, | |
| "eval_r2": 0.2416569624089897, | |
| "eval_runtime": 58.2108, | |
| "eval_samples_per_second": 6.872, | |
| "eval_steps_per_second": 0.429, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 17, | |
| "learning_rate": 5.164688089809444e-06, | |
| "loss": 0.0162, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 17, | |
| "eval_loss": 0.016918588429689407, | |
| "eval_mae": 0.09915737062692642, | |
| "eval_mse": 0.016918879002332687, | |
| "eval_r2": 0.24260718873499565, | |
| "eval_runtime": 56.8092, | |
| "eval_samples_per_second": 7.041, | |
| "eval_steps_per_second": 0.44, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 17, | |
| "learning_rate": 4.423120100008582e-06, | |
| "loss": 0.0163, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 17, | |
| "eval_loss": 0.016940301284193993, | |
| "eval_mae": 0.09919126331806183, | |
| "eval_mse": 0.016939815133810043, | |
| "eval_r2": 0.23998661125272824, | |
| "eval_runtime": 59.9186, | |
| "eval_samples_per_second": 6.676, | |
| "eval_steps_per_second": 0.417, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 17, | |
| "learning_rate": 3.7365415833504725e-06, | |
| "loss": 0.0162, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 17, | |
| "eval_loss": 0.016918940469622612, | |
| "eval_mae": 0.09915791451931, | |
| "eval_mse": 0.016918599605560303, | |
| "eval_r2": 0.23974174795237568, | |
| "eval_runtime": 63.0008, | |
| "eval_samples_per_second": 6.349, | |
| "eval_steps_per_second": 0.397, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 17, | |
| "learning_rate": 3.105780911390738e-06, | |
| "loss": 0.0163, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 17, | |
| "eval_loss": 0.016923611983656883, | |
| "eval_mae": 0.09916673600673676, | |
| "eval_mse": 0.016924140974879265, | |
| "eval_r2": 0.23963991013957076, | |
| "eval_runtime": 56.3879, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 0.443, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 18, | |
| "learning_rate": 2.5315991102703716e-06, | |
| "loss": 0.0163, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 18, | |
| "eval_loss": 0.01691032014787197, | |
| "eval_mae": 0.09915610402822495, | |
| "eval_mse": 0.01691248081624508, | |
| "eval_r2": 0.24413583693173724, | |
| "eval_runtime": 61.6302, | |
| "eval_samples_per_second": 6.49, | |
| "eval_steps_per_second": 0.406, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 18, | |
| "learning_rate": 2.0146889425216476e-06, | |
| "loss": 0.0163, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 18, | |
| "eval_loss": 0.016894323751330376, | |
| "eval_mae": 0.09909255057573318, | |
| "eval_mse": 0.016893018037080765, | |
| "eval_r2": 0.24154658591740408, | |
| "eval_runtime": 61.7977, | |
| "eval_samples_per_second": 6.473, | |
| "eval_steps_per_second": 0.405, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 18, | |
| "learning_rate": 1.555674071235358e-06, | |
| "loss": 0.0163, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 18, | |
| "eval_loss": 0.016896896064281464, | |
| "eval_mae": 0.09909563511610031, | |
| "eval_mse": 0.016896726563572884, | |
| "eval_r2": 0.2395997969159448, | |
| "eval_runtime": 63.3638, | |
| "eval_samples_per_second": 6.313, | |
| "eval_steps_per_second": 0.395, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 18, | |
| "learning_rate": 1.155108307598024e-06, | |
| "loss": 0.0163, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 18, | |
| "eval_loss": 0.016881046816706657, | |
| "eval_mae": 0.09909423440694809, | |
| "eval_mse": 0.016880322247743607, | |
| "eval_r2": 0.2425676493378176, | |
| "eval_runtime": 60.1702, | |
| "eval_samples_per_second": 6.648, | |
| "eval_steps_per_second": 0.415, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 18, | |
| "learning_rate": 8.134749427070376e-07, | |
| "loss": 0.0163, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 18, | |
| "eval_loss": 0.016920508816838264, | |
| "eval_mae": 0.09913913160562515, | |
| "eval_mse": 0.016919521614909172, | |
| "eval_r2": 0.240687826762218, | |
| "eval_runtime": 56.9763, | |
| "eval_samples_per_second": 7.02, | |
| "eval_steps_per_second": 0.439, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 19, | |
| "learning_rate": 5.311861644696048e-07, | |
| "loss": 0.0163, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 19, | |
| "eval_loss": 0.016956361010670662, | |
| "eval_mae": 0.09927552938461304, | |
| "eval_mse": 0.016957107931375504, | |
| "eval_r2": 0.23962235723125958, | |
| "eval_runtime": 57.5809, | |
| "eval_samples_per_second": 6.947, | |
| "eval_steps_per_second": 0.434, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 19, | |
| "learning_rate": 3.0858256028932776e-07, | |
| "loss": 0.0163, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 19, | |
| "eval_loss": 0.016894662752747536, | |
| "eval_mae": 0.09909520298242569, | |
| "eval_mse": 0.016894804313778877, | |
| "eval_r2": 0.24004589904875062, | |
| "eval_runtime": 58.5108, | |
| "eval_samples_per_second": 6.836, | |
| "eval_steps_per_second": 0.427, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 19, | |
| "learning_rate": 1.4593270614026154e-07, | |
| "loss": 0.0162, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 19, | |
| "eval_loss": 0.016891133040189743, | |
| "eval_mae": 0.09907051920890808, | |
| "eval_mse": 0.016890019178390503, | |
| "eval_r2": 0.24048031726771313, | |
| "eval_runtime": 62.2953, | |
| "eval_samples_per_second": 6.421, | |
| "eval_steps_per_second": 0.401, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 19, | |
| "learning_rate": 4.343284252429913e-08, | |
| "loss": 0.0162, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 19, | |
| "eval_loss": 0.016868911683559418, | |
| "eval_mae": 0.0990411788225174, | |
| "eval_mse": 0.016869619488716125, | |
| "eval_r2": 0.24109475503821198, | |
| "eval_runtime": 58.3864, | |
| "eval_samples_per_second": 6.851, | |
| "eval_steps_per_second": 0.428, | |
| "step": 4700 | |
| } | |
| ], | |
| "max_steps": 4760, | |
| "num_train_epochs": 20, | |
| "total_flos": 2.0677241114343014e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |