| { | |
| "best_metric": 0.37047404050827026, | |
| "best_model_checkpoint": "/home/ahf38/palmer_scratch/brainlm/training-runs/2023-07-19-17_00_00/checkpoint-3250", | |
| "epoch": 13.63040629095675, | |
| "global_step": 3250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0, | |
| "learning_rate": 0.0002100840336134454, | |
| "loss": 0.3863, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0, | |
| "eval_loss": 0.3854129910469055, | |
| "eval_mae": 0.4674049913883209, | |
| "eval_mse": 0.38541293144226074, | |
| "eval_r2": 0.4410198587613452, | |
| "eval_runtime": 273.6849, | |
| "eval_samples_per_second": 2.923, | |
| "eval_steps_per_second": 0.731, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0, | |
| "learning_rate": 0.0004201680672268908, | |
| "loss": 0.3852, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0, | |
| "eval_loss": 0.38619935512542725, | |
| "eval_mae": 0.46789708733558655, | |
| "eval_mse": 0.386198490858078, | |
| "eval_r2": 0.4393806237898299, | |
| "eval_runtime": 280.3385, | |
| "eval_samples_per_second": 2.854, | |
| "eval_steps_per_second": 0.713, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0, | |
| "learning_rate": 0.0006302521008403362, | |
| "loss": 0.3851, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0, | |
| "eval_loss": 0.38692620396614075, | |
| "eval_mae": 0.4686347544193268, | |
| "eval_mse": 0.3869261145591736, | |
| "eval_r2": 0.43769447169001496, | |
| "eval_runtime": 264.849, | |
| "eval_samples_per_second": 3.021, | |
| "eval_steps_per_second": 0.755, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0, | |
| "learning_rate": 0.0008403361344537816, | |
| "loss": 0.393, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0, | |
| "eval_loss": 0.409867525100708, | |
| "eval_mae": 0.4844866693019867, | |
| "eval_mse": 0.4098674952983856, | |
| "eval_r2": 0.4059509929564361, | |
| "eval_runtime": 264.8497, | |
| "eval_samples_per_second": 3.021, | |
| "eval_steps_per_second": 0.755, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1, | |
| "learning_rate": 0.0009999826244478293, | |
| "loss": 0.3975, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1, | |
| "eval_loss": 0.3888590931892395, | |
| "eval_mae": 0.46977394819259644, | |
| "eval_mse": 0.38885924220085144, | |
| "eval_r2": 0.43532054204855475, | |
| "eval_runtime": 263.3448, | |
| "eval_samples_per_second": 3.038, | |
| "eval_steps_per_second": 0.759, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1, | |
| "learning_rate": 0.0009995362383107963, | |
| "loss": 0.3883, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1, | |
| "eval_loss": 0.3876199424266815, | |
| "eval_mae": 0.46888846158981323, | |
| "eval_mse": 0.3876205086708069, | |
| "eval_r2": 0.4391745591771552, | |
| "eval_runtime": 264.9341, | |
| "eval_samples_per_second": 3.02, | |
| "eval_steps_per_second": 0.755, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1, | |
| "learning_rate": 0.000998487151097676, | |
| "loss": 0.3887, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1, | |
| "eval_loss": 0.3875642418861389, | |
| "eval_mae": 0.4687305688858032, | |
| "eval_mse": 0.38756391406059265, | |
| "eval_r2": 0.4382047783977898, | |
| "eval_runtime": 272.0994, | |
| "eval_samples_per_second": 2.94, | |
| "eval_steps_per_second": 0.735, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1, | |
| "learning_rate": 0.0009968366285544618, | |
| "loss": 0.386, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1, | |
| "eval_loss": 0.3863183557987213, | |
| "eval_mae": 0.4679754078388214, | |
| "eval_mse": 0.386318176984787, | |
| "eval_r2": 0.4391650800336171, | |
| "eval_runtime": 272.2539, | |
| "eval_samples_per_second": 2.938, | |
| "eval_steps_per_second": 0.735, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1, | |
| "learning_rate": 0.000994586662071641, | |
| "loss": 0.3861, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1, | |
| "eval_loss": 0.39024049043655396, | |
| "eval_mae": 0.47065961360931396, | |
| "eval_mse": 0.39024049043655396, | |
| "eval_r2": 0.4331343008067088, | |
| "eval_runtime": 266.2407, | |
| "eval_samples_per_second": 3.005, | |
| "eval_steps_per_second": 0.751, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2, | |
| "learning_rate": 0.000991739966281539, | |
| "loss": 0.3876, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2, | |
| "eval_loss": 0.3867352604866028, | |
| "eval_mae": 0.46853551268577576, | |
| "eval_mse": 0.3867342174053192, | |
| "eval_r2": 0.43885509094622643, | |
| "eval_runtime": 265.3966, | |
| "eval_samples_per_second": 3.014, | |
| "eval_steps_per_second": 0.754, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2, | |
| "learning_rate": 0.0009882999757830587, | |
| "loss": 0.386, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2, | |
| "eval_loss": 0.38316670060157776, | |
| "eval_mae": 0.46593964099884033, | |
| "eval_mse": 0.3831673562526703, | |
| "eval_r2": 0.44430950413045944, | |
| "eval_runtime": 262.4987, | |
| "eval_samples_per_second": 3.048, | |
| "eval_steps_per_second": 0.762, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2, | |
| "learning_rate": 0.0009842708409977634, | |
| "loss": 0.3851, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2, | |
| "eval_loss": 0.3835921585559845, | |
| "eval_mae": 0.4662681818008423, | |
| "eval_mse": 0.38359254598617554, | |
| "eval_r2": 0.4431584385649353, | |
| "eval_runtime": 262.0832, | |
| "eval_samples_per_second": 3.052, | |
| "eval_steps_per_second": 0.763, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2, | |
| "learning_rate": 0.0009796574231623054, | |
| "loss": 0.3828, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2, | |
| "eval_loss": 0.38348111510276794, | |
| "eval_mae": 0.46614208817481995, | |
| "eval_mse": 0.3834820091724396, | |
| "eval_r2": 0.44133966944739267, | |
| "eval_runtime": 267.1672, | |
| "eval_samples_per_second": 2.994, | |
| "eval_steps_per_second": 0.749, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2, | |
| "learning_rate": 0.0009744652884632406, | |
| "loss": 0.3839, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2, | |
| "eval_loss": 0.38388848304748535, | |
| "eval_mae": 0.46622949838638306, | |
| "eval_mse": 0.38388875126838684, | |
| "eval_r2": 0.44094833637705777, | |
| "eval_runtime": 264.3781, | |
| "eval_samples_per_second": 3.026, | |
| "eval_steps_per_second": 0.756, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3, | |
| "learning_rate": 0.0009687007013213062, | |
| "loss": 0.3848, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3, | |
| "eval_loss": 0.3808014392852783, | |
| "eval_mae": 0.46472200751304626, | |
| "eval_mse": 0.38080185651779175, | |
| "eval_r2": 0.44630267861478945, | |
| "eval_runtime": 265.0946, | |
| "eval_samples_per_second": 3.018, | |
| "eval_steps_per_second": 0.754, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3, | |
| "learning_rate": 0.0009623706168332644, | |
| "loss": 0.3821, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3, | |
| "eval_loss": 0.3820662200450897, | |
| "eval_mae": 0.4652169346809387, | |
| "eval_mse": 0.3820664882659912, | |
| "eval_r2": 0.4448990871151196, | |
| "eval_runtime": 267.613, | |
| "eval_samples_per_second": 2.989, | |
| "eval_steps_per_second": 0.747, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3, | |
| "learning_rate": 0.0009554826723804303, | |
| "loss": 0.3818, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3, | |
| "eval_loss": 0.3809438645839691, | |
| "eval_mae": 0.46468687057495117, | |
| "eval_mse": 0.3809432089328766, | |
| "eval_r2": 0.4446287307018585, | |
| "eval_runtime": 264.0042, | |
| "eval_samples_per_second": 3.03, | |
| "eval_steps_per_second": 0.758, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3, | |
| "learning_rate": 0.0009480451784140092, | |
| "loss": 0.3824, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3, | |
| "eval_loss": 0.38150742650032043, | |
| "eval_mae": 0.4647422134876251, | |
| "eval_mse": 0.3815067708492279, | |
| "eval_r2": 0.44662126614575437, | |
| "eval_runtime": 267.3864, | |
| "eval_samples_per_second": 2.992, | |
| "eval_steps_per_second": 0.748, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3, | |
| "learning_rate": 0.0009400671084283606, | |
| "loss": 0.3816, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3, | |
| "eval_loss": 0.3832119107246399, | |
| "eval_mae": 0.46604394912719727, | |
| "eval_mse": 0.3832109272480011, | |
| "eval_r2": 0.4432983612099932, | |
| "eval_runtime": 284.3156, | |
| "eval_samples_per_second": 2.814, | |
| "eval_steps_per_second": 0.703, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 4, | |
| "learning_rate": 0.0009315580881342876, | |
| "loss": 0.3794, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4, | |
| "eval_loss": 0.3803976774215698, | |
| "eval_mae": 0.4641774296760559, | |
| "eval_mse": 0.380397766828537, | |
| "eval_r2": 0.4470804443192825, | |
| "eval_runtime": 265.2618, | |
| "eval_samples_per_second": 3.016, | |
| "eval_steps_per_second": 0.754, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4, | |
| "learning_rate": 0.000922528383845411, | |
| "loss": 0.3819, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4, | |
| "eval_loss": 0.38107830286026, | |
| "eval_mae": 0.4645218849182129, | |
| "eval_mse": 0.38107892870903015, | |
| "eval_r2": 0.4483045268109964, | |
| "eval_runtime": 265.6012, | |
| "eval_samples_per_second": 3.012, | |
| "eval_steps_per_second": 0.753, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4, | |
| "learning_rate": 0.0009129888900916457, | |
| "loss": 0.3799, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4, | |
| "eval_loss": 0.38090744614601135, | |
| "eval_mae": 0.46439129114151, | |
| "eval_mse": 0.38090750575065613, | |
| "eval_r2": 0.4488611430910662, | |
| "eval_runtime": 271.1593, | |
| "eval_samples_per_second": 2.95, | |
| "eval_steps_per_second": 0.738, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4, | |
| "learning_rate": 0.0009029511164747175, | |
| "loss": 0.383, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 4, | |
| "eval_loss": 0.3813271224498749, | |
| "eval_mae": 0.4647519886493683, | |
| "eval_mse": 0.38132649660110474, | |
| "eval_r2": 0.44615534251165345, | |
| "eval_runtime": 272.9035, | |
| "eval_samples_per_second": 2.931, | |
| "eval_steps_per_second": 0.733, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 5, | |
| "learning_rate": 0.0008924271737815855, | |
| "loss": 0.3809, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5, | |
| "eval_loss": 0.37957870960235596, | |
| "eval_mae": 0.46358469128608704, | |
| "eval_mse": 0.3795786499977112, | |
| "eval_r2": 0.4479695425018687, | |
| "eval_runtime": 265.8282, | |
| "eval_samples_per_second": 3.009, | |
| "eval_steps_per_second": 0.752, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5, | |
| "learning_rate": 0.0008814297593725199, | |
| "loss": 0.3805, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 5, | |
| "eval_loss": 0.38085976243019104, | |
| "eval_mae": 0.46433085203170776, | |
| "eval_mse": 0.38085973262786865, | |
| "eval_r2": 0.44749606591539537, | |
| "eval_runtime": 270.336, | |
| "eval_samples_per_second": 2.959, | |
| "eval_steps_per_second": 0.74, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 5, | |
| "learning_rate": 0.0008699721418614672, | |
| "loss": 0.3805, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 5, | |
| "eval_loss": 0.3793216049671173, | |
| "eval_mae": 0.46346384286880493, | |
| "eval_mse": 0.3793216049671173, | |
| "eval_r2": 0.4494445278203605, | |
| "eval_runtime": 264.9048, | |
| "eval_samples_per_second": 3.02, | |
| "eval_steps_per_second": 0.755, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 5, | |
| "learning_rate": 0.0008580681451071866, | |
| "loss": 0.3794, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 5, | |
| "eval_loss": 0.37941062450408936, | |
| "eval_mae": 0.4636057913303375, | |
| "eval_mse": 0.37941014766693115, | |
| "eval_r2": 0.4489888493647255, | |
| "eval_runtime": 279.0513, | |
| "eval_samples_per_second": 2.867, | |
| "eval_steps_per_second": 0.717, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 5, | |
| "learning_rate": 0.0008457321315344694, | |
| "loss": 0.3806, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 5, | |
| "eval_loss": 0.37968844175338745, | |
| "eval_mae": 0.4636916518211365, | |
| "eval_mse": 0.3796885013580322, | |
| "eval_r2": 0.4474722627694526, | |
| "eval_runtime": 268.6996, | |
| "eval_samples_per_second": 2.977, | |
| "eval_steps_per_second": 0.744, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 6, | |
| "learning_rate": 0.0008329789848055705, | |
| "loss": 0.3764, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 6, | |
| "eval_loss": 0.3784217834472656, | |
| "eval_mae": 0.4628964364528656, | |
| "eval_mse": 0.37842199206352234, | |
| "eval_r2": 0.45179472514661223, | |
| "eval_runtime": 275.6704, | |
| "eval_samples_per_second": 2.902, | |
| "eval_steps_per_second": 0.726, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 6, | |
| "learning_rate": 0.0008198240918627525, | |
| "loss": 0.3802, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6, | |
| "eval_loss": 0.3779056966304779, | |
| "eval_mae": 0.4623972177505493, | |
| "eval_mse": 0.37790581583976746, | |
| "eval_r2": 0.45185399059020337, | |
| "eval_runtime": 269.5949, | |
| "eval_samples_per_second": 2.967, | |
| "eval_steps_per_second": 0.742, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6, | |
| "learning_rate": 0.0008062833243636134, | |
| "loss": 0.3787, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 6, | |
| "eval_loss": 0.3789410889148712, | |
| "eval_mae": 0.46288514137268066, | |
| "eval_mse": 0.37894150614738464, | |
| "eval_r2": 0.4510378453068221, | |
| "eval_runtime": 291.6469, | |
| "eval_samples_per_second": 2.743, | |
| "eval_steps_per_second": 0.686, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 6, | |
| "learning_rate": 0.0007923730195315961, | |
| "loss": 0.379, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6, | |
| "eval_loss": 0.3779994249343872, | |
| "eval_mae": 0.4624533951282501, | |
| "eval_mse": 0.377999484539032, | |
| "eval_r2": 0.4508841579385672, | |
| "eval_runtime": 278.879, | |
| "eval_samples_per_second": 2.869, | |
| "eval_steps_per_second": 0.717, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6, | |
| "learning_rate": 0.0007781099604447793, | |
| "loss": 0.3765, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 6, | |
| "eval_loss": 0.37762123346328735, | |
| "eval_mae": 0.4622168242931366, | |
| "eval_mse": 0.37762120366096497, | |
| "eval_r2": 0.452898354940625, | |
| "eval_runtime": 278.1979, | |
| "eval_samples_per_second": 2.876, | |
| "eval_steps_per_second": 0.719, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 7, | |
| "learning_rate": 0.0007635113557867395, | |
| "loss": 0.3797, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 7, | |
| "eval_loss": 0.37847700715065, | |
| "eval_mae": 0.4626946747303009, | |
| "eval_mse": 0.378477543592453, | |
| "eval_r2": 0.4524606040645045, | |
| "eval_runtime": 265.647, | |
| "eval_samples_per_second": 3.012, | |
| "eval_steps_per_second": 0.753, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 7, | |
| "learning_rate": 0.0007485948190839076, | |
| "loss": 0.3772, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 7, | |
| "eval_loss": 0.3774454891681671, | |
| "eval_mae": 0.46223533153533936, | |
| "eval_mse": 0.37744590640068054, | |
| "eval_r2": 0.45290920313283933, | |
| "eval_runtime": 268.9714, | |
| "eval_samples_per_second": 2.974, | |
| "eval_steps_per_second": 0.744, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 7, | |
| "learning_rate": 0.0007333783474544757, | |
| "loss": 0.3792, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 7, | |
| "eval_loss": 0.37726637721061707, | |
| "eval_mae": 0.46205469965934753, | |
| "eval_mse": 0.3772661089897156, | |
| "eval_r2": 0.45215750792291154, | |
| "eval_runtime": 270.804, | |
| "eval_samples_per_second": 2.954, | |
| "eval_steps_per_second": 0.739, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 7, | |
| "learning_rate": 0.0007178802998944933, | |
| "loss": 0.3753, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 7, | |
| "eval_loss": 0.3767879009246826, | |
| "eval_mae": 0.4616534411907196, | |
| "eval_mse": 0.3767889440059662, | |
| "eval_r2": 0.4520469227666626, | |
| "eval_runtime": 263.9276, | |
| "eval_samples_per_second": 3.031, | |
| "eval_steps_per_second": 0.758, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 7, | |
| "learning_rate": 0.0007021193751273463, | |
| "loss": 0.3758, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 7, | |
| "eval_loss": 0.37764108180999756, | |
| "eval_mae": 0.4621761739253998, | |
| "eval_mse": 0.37764135003089905, | |
| "eval_r2": 0.45377418641465317, | |
| "eval_runtime": 283.3511, | |
| "eval_samples_per_second": 2.823, | |
| "eval_steps_per_second": 0.706, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 8, | |
| "learning_rate": 0.0006861145890433519, | |
| "loss": 0.377, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 8, | |
| "eval_loss": 0.3769887685775757, | |
| "eval_mae": 0.46189454197883606, | |
| "eval_mse": 0.37698760628700256, | |
| "eval_r2": 0.45451653345429155, | |
| "eval_runtime": 269.8194, | |
| "eval_samples_per_second": 2.965, | |
| "eval_steps_per_second": 0.741, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 8, | |
| "learning_rate": 0.0006698852517566836, | |
| "loss": 0.3761, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8, | |
| "eval_loss": 0.3763187527656555, | |
| "eval_mae": 0.4613550901412964, | |
| "eval_mse": 0.3763185143470764, | |
| "eval_r2": 0.45283548813003005, | |
| "eval_runtime": 272.1057, | |
| "eval_samples_per_second": 2.94, | |
| "eval_steps_per_second": 0.735, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8, | |
| "learning_rate": 0.0006534509443073072, | |
| "loss": 0.3764, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 8, | |
| "eval_loss": 0.3749840557575226, | |
| "eval_mae": 0.46052685379981995, | |
| "eval_mse": 0.37498345971107483, | |
| "eval_r2": 0.45454628406748754, | |
| "eval_runtime": 277.2032, | |
| "eval_samples_per_second": 2.886, | |
| "eval_steps_per_second": 0.721, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 8, | |
| "learning_rate": 0.0006368314950360416, | |
| "loss": 0.3747, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 8, | |
| "eval_loss": 0.37445199489593506, | |
| "eval_mae": 0.46010997891426086, | |
| "eval_mse": 0.3744511008262634, | |
| "eval_r2": 0.4568363191792082, | |
| "eval_runtime": 276.9731, | |
| "eval_samples_per_second": 2.888, | |
| "eval_steps_per_second": 0.722, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 9, | |
| "learning_rate": 0.0006200469556612435, | |
| "loss": 0.3754, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 9, | |
| "eval_loss": 0.3743913769721985, | |
| "eval_mae": 0.4600675106048584, | |
| "eval_mse": 0.3743920922279358, | |
| "eval_r2": 0.45744293340515363, | |
| "eval_runtime": 281.3782, | |
| "eval_samples_per_second": 2.843, | |
| "eval_steps_per_second": 0.711, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 9, | |
| "learning_rate": 0.0006031175770859848, | |
| "loss": 0.3736, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 9, | |
| "eval_loss": 0.3738979399204254, | |
| "eval_mae": 0.45969095826148987, | |
| "eval_mse": 0.37389707565307617, | |
| "eval_r2": 0.4581812073615178, | |
| "eval_runtime": 270.2281, | |
| "eval_samples_per_second": 2.96, | |
| "eval_steps_per_second": 0.74, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 9, | |
| "learning_rate": 0.0005860637849649073, | |
| "loss": 0.3743, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 9, | |
| "eval_loss": 0.3741012513637543, | |
| "eval_mae": 0.4597731828689575, | |
| "eval_mse": 0.37410181760787964, | |
| "eval_r2": 0.4575432685303391, | |
| "eval_runtime": 278.4971, | |
| "eval_samples_per_second": 2.873, | |
| "eval_steps_per_second": 0.718, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 9, | |
| "learning_rate": 0.000568906155060237, | |
| "loss": 0.3734, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 9, | |
| "eval_loss": 0.37282341718673706, | |
| "eval_mae": 0.4590661823749542, | |
| "eval_mse": 0.3728235960006714, | |
| "eval_r2": 0.457423055516365, | |
| "eval_runtime": 279.5267, | |
| "eval_samples_per_second": 2.862, | |
| "eval_steps_per_second": 0.715, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 9, | |
| "learning_rate": 0.0005516653884166902, | |
| "loss": 0.371, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 9, | |
| "eval_loss": 0.3734956681728363, | |
| "eval_mae": 0.45936986804008484, | |
| "eval_mse": 0.3734953701496124, | |
| "eval_r2": 0.4600796269569801, | |
| "eval_runtime": 274.1528, | |
| "eval_samples_per_second": 2.918, | |
| "eval_steps_per_second": 0.73, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 10, | |
| "learning_rate": 0.0005343622863852232, | |
| "loss": 0.3754, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 10, | |
| "eval_loss": 0.3738192021846771, | |
| "eval_mae": 0.45952871441841125, | |
| "eval_mse": 0.37381842732429504, | |
| "eval_r2": 0.4592306947745455, | |
| "eval_runtime": 277.5843, | |
| "eval_samples_per_second": 2.882, | |
| "eval_steps_per_second": 0.721, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 10, | |
| "learning_rate": 0.0005170177255257618, | |
| "loss": 0.373, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 10, | |
| "eval_loss": 0.3726402521133423, | |
| "eval_mae": 0.4587893486022949, | |
| "eval_mse": 0.3726405203342438, | |
| "eval_r2": 0.45936278859727786, | |
| "eval_runtime": 281.2863, | |
| "eval_samples_per_second": 2.844, | |
| "eval_steps_per_second": 0.711, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 10, | |
| "learning_rate": 0.0004996526324191872, | |
| "loss": 0.3717, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 10, | |
| "eval_loss": 0.37096771597862244, | |
| "eval_mae": 0.45787444710731506, | |
| "eval_mse": 0.3709667921066284, | |
| "eval_r2": 0.4609350988985167, | |
| "eval_runtime": 270.5778, | |
| "eval_samples_per_second": 2.957, | |
| "eval_steps_per_second": 0.739, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 10, | |
| "learning_rate": 0.0004822879584189731, | |
| "loss": 0.3727, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 10, | |
| "eval_loss": 0.3726476728916168, | |
| "eval_mae": 0.4586939215660095, | |
| "eval_mse": 0.37264758348464966, | |
| "eval_r2": 0.4587349241462606, | |
| "eval_runtime": 273.9493, | |
| "eval_samples_per_second": 2.92, | |
| "eval_steps_per_second": 0.73, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 10, | |
| "learning_rate": 0.0004649446543729322, | |
| "loss": 0.372, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 10, | |
| "eval_loss": 0.37159234285354614, | |
| "eval_mae": 0.4583428204059601, | |
| "eval_mse": 0.3715912401676178, | |
| "eval_r2": 0.4603821208241091, | |
| "eval_runtime": 278.26, | |
| "eval_samples_per_second": 2.875, | |
| "eval_steps_per_second": 0.719, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 11, | |
| "learning_rate": 0.0004476436453455742, | |
| "loss": 0.3715, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 11, | |
| "eval_loss": 0.3717365562915802, | |
| "eval_mae": 0.4582462012767792, | |
| "eval_mse": 0.3717361092567444, | |
| "eval_r2": 0.45976387138394437, | |
| "eval_runtime": 292.146, | |
| "eval_samples_per_second": 2.738, | |
| "eval_steps_per_second": 0.685, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 11, | |
| "learning_rate": 0.0004304058053715702, | |
| "loss": 0.3717, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 11, | |
| "eval_loss": 0.3717900216579437, | |
| "eval_mae": 0.45822903513908386, | |
| "eval_mse": 0.37178927659988403, | |
| "eval_r2": 0.45998171303819835, | |
| "eval_runtime": 269.82, | |
| "eval_samples_per_second": 2.965, | |
| "eval_steps_per_second": 0.741, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 11, | |
| "learning_rate": 0.0004132519322707882, | |
| "loss": 0.3707, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 11, | |
| "eval_loss": 0.3708600699901581, | |
| "eval_mae": 0.45766767859458923, | |
| "eval_mse": 0.3708597719669342, | |
| "eval_r2": 0.4603013858171726, | |
| "eval_runtime": 269.9605, | |
| "eval_samples_per_second": 2.963, | |
| "eval_steps_per_second": 0.741, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 11, | |
| "learning_rate": 0.00039620272255528065, | |
| "loss": 0.3739, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 11, | |
| "eval_loss": 0.3721630573272705, | |
| "eval_mae": 0.4584360122680664, | |
| "eval_mse": 0.37216344475746155, | |
| "eval_r2": 0.459010225690355, | |
| "eval_runtime": 268.3335, | |
| "eval_samples_per_second": 2.981, | |
| "eval_steps_per_second": 0.745, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 11, | |
| "learning_rate": 0.000379278746458504, | |
| "loss": 0.3702, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 11, | |
| "eval_loss": 0.37071841955184937, | |
| "eval_mae": 0.4574899673461914, | |
| "eval_mse": 0.3707171678543091, | |
| "eval_r2": 0.4613746011063965, | |
| "eval_runtime": 279.1852, | |
| "eval_samples_per_second": 2.865, | |
| "eval_steps_per_second": 0.716, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 12, | |
| "learning_rate": 0.000362500423116895, | |
| "loss": 0.3712, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 12, | |
| "eval_loss": 0.37087440490722656, | |
| "eval_mae": 0.45766788721084595, | |
| "eval_mse": 0.37087327241897583, | |
| "eval_r2": 0.4618904862700307, | |
| "eval_runtime": 292.1987, | |
| "eval_samples_per_second": 2.738, | |
| "eval_steps_per_second": 0.684, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 12, | |
| "learning_rate": 0.0003458879959337494, | |
| "loss": 0.3693, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 12, | |
| "eval_loss": 0.3699745535850525, | |
| "eval_mae": 0.4571460485458374, | |
| "eval_mse": 0.36997491121292114, | |
| "eval_r2": 0.4619671878026411, | |
| "eval_runtime": 273.9573, | |
| "eval_samples_per_second": 2.92, | |
| "eval_steps_per_second": 0.73, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 12, | |
| "learning_rate": 0.00032946150815512586, | |
| "loss": 0.3719, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 12, | |
| "eval_loss": 0.3705122470855713, | |
| "eval_mae": 0.45748522877693176, | |
| "eval_mse": 0.37051278352737427, | |
| "eval_r2": 0.46142887892760176, | |
| "eval_runtime": 268.3928, | |
| "eval_samples_per_second": 2.981, | |
| "eval_steps_per_second": 0.745, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 12, | |
| "learning_rate": 0.0003132407786872442, | |
| "loss": 0.3716, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 12, | |
| "eval_loss": 0.3708195388317108, | |
| "eval_mae": 0.45740067958831787, | |
| "eval_mse": 0.3708195090293884, | |
| "eval_r2": 0.4616999176965736, | |
| "eval_runtime": 273.3209, | |
| "eval_samples_per_second": 2.927, | |
| "eval_steps_per_second": 0.732, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 13, | |
| "learning_rate": 0.00029724537818455465, | |
| "loss": 0.3693, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 13, | |
| "eval_loss": 0.3704887628555298, | |
| "eval_mae": 0.45740318298339844, | |
| "eval_mse": 0.37048864364624023, | |
| "eval_r2": 0.4616717003785853, | |
| "eval_runtime": 273.739, | |
| "eval_samples_per_second": 2.922, | |
| "eval_steps_per_second": 0.731, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 13, | |
| "learning_rate": 0.00028149460543732666, | |
| "loss": 0.3706, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 13, | |
| "eval_loss": 0.37004169821739197, | |
| "eval_mae": 0.45711666345596313, | |
| "eval_mse": 0.37004172801971436, | |
| "eval_r2": 0.46274949898335205, | |
| "eval_runtime": 265.1017, | |
| "eval_samples_per_second": 3.018, | |
| "eval_steps_per_second": 0.754, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 13, | |
| "learning_rate": 0.00026600746408725063, | |
| "loss": 0.3703, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 13, | |
| "eval_loss": 0.3703955113887787, | |
| "eval_mae": 0.45735496282577515, | |
| "eval_mse": 0.37039563059806824, | |
| "eval_r2": 0.4622188399376109, | |
| "eval_runtime": 287.415, | |
| "eval_samples_per_second": 2.783, | |
| "eval_steps_per_second": 0.696, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 13, | |
| "learning_rate": 0.000250802639699139, | |
| "loss": 0.3693, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 13, | |
| "eval_loss": 0.37047404050827026, | |
| "eval_mae": 0.45720237493515015, | |
| "eval_mse": 0.37047335505485535, | |
| "eval_r2": 0.46234450920301984, | |
| "eval_runtime": 265.936, | |
| "eval_samples_per_second": 3.008, | |
| "eval_steps_per_second": 0.752, | |
| "step": 3250 | |
| } | |
| ], | |
| "max_steps": 4760, | |
| "num_train_epochs": 20, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |