| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.12843565373747753, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.003210891343436938, |
| "grad_norm": 69.8836441040039, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 11.0959, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.006421782686873876, |
| "grad_norm": 5.493549346923828, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 5.2907, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.009632674030310814, |
| "grad_norm": 4.560669422149658, |
| "learning_rate": 1.2e-05, |
| "loss": 1.4063, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.012843565373747753, |
| "grad_norm": 1.4942766427993774, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.7632, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.016054456717184692, |
| "grad_norm": 0.9895948767662048, |
| "learning_rate": 2e-05, |
| "loss": 0.4862, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.019265348060621627, |
| "grad_norm": 0.45268505811691284, |
| "learning_rate": 1.9975640502598243e-05, |
| "loss": 0.3328, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.022476239404058566, |
| "grad_norm": 0.42247167229652405, |
| "learning_rate": 1.9902680687415704e-05, |
| "loss": 0.255, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.025687130747495505, |
| "grad_norm": 0.24037286639213562, |
| "learning_rate": 1.9781476007338058e-05, |
| "loss": 0.2204, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.028898022090932445, |
| "grad_norm": 0.25233975052833557, |
| "learning_rate": 1.961261695938319e-05, |
| "loss": 0.2068, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.032108913434369384, |
| "grad_norm": 0.21763837337493896, |
| "learning_rate": 1.9396926207859085e-05, |
| "loss": 0.1901, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.035319804777806316, |
| "grad_norm": 0.1445178985595703, |
| "learning_rate": 1.913545457642601e-05, |
| "loss": 0.1877, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.038530696121243255, |
| "grad_norm": 0.13639642298221588, |
| "learning_rate": 1.8829475928589272e-05, |
| "loss": 0.186, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.041741587464680194, |
| "grad_norm": 0.13293865323066711, |
| "learning_rate": 1.848048096156426e-05, |
| "loss": 0.1813, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.04495247880811713, |
| "grad_norm": 0.11292831599712372, |
| "learning_rate": 1.8090169943749477e-05, |
| "loss": 0.177, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.04816337015155407, |
| "grad_norm": 0.1082601547241211, |
| "learning_rate": 1.766044443118978e-05, |
| "loss": 0.1744, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.05137426149499101, |
| "grad_norm": 0.13378290832042694, |
| "learning_rate": 1.7193398003386514e-05, |
| "loss": 0.1743, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.05458515283842795, |
| "grad_norm": 0.12352604418992996, |
| "learning_rate": 1.6691306063588583e-05, |
| "loss": 0.176, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.05779604418186489, |
| "grad_norm": 0.10596515983343124, |
| "learning_rate": 1.6156614753256583e-05, |
| "loss": 0.1696, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.06100693552530182, |
| "grad_norm": 0.11924272775650024, |
| "learning_rate": 1.5591929034707468e-05, |
| "loss": 0.1746, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.06421782686873877, |
| "grad_norm": 0.1027117520570755, |
| "learning_rate": 1.5000000000000002e-05, |
| "loss": 0.1716, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.0674287182121757, |
| "grad_norm": 0.10724334418773651, |
| "learning_rate": 1.4383711467890776e-05, |
| "loss": 0.168, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.07063960955561263, |
| "grad_norm": 0.11224232614040375, |
| "learning_rate": 1.3746065934159123e-05, |
| "loss": 0.1675, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.07385050089904957, |
| "grad_norm": 0.12550988793373108, |
| "learning_rate": 1.3090169943749475e-05, |
| "loss": 0.1719, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.07706139224248651, |
| "grad_norm": 0.09472157061100006, |
| "learning_rate": 1.2419218955996677e-05, |
| "loss": 0.1683, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.08027228358592345, |
| "grad_norm": 0.1025599017739296, |
| "learning_rate": 1.1736481776669307e-05, |
| "loss": 0.1676, |
| "step": 1250 |
| }, |
| { |
| "epoch": 0.08348317492936039, |
| "grad_norm": 0.11636577546596527, |
| "learning_rate": 1.1045284632676535e-05, |
| "loss": 0.1649, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.08669406627279733, |
| "grad_norm": 0.09252961724996567, |
| "learning_rate": 1.0348994967025012e-05, |
| "loss": 0.1634, |
| "step": 1350 |
| }, |
| { |
| "epoch": 0.08990495761623427, |
| "grad_norm": 0.10500337928533554, |
| "learning_rate": 9.651005032974994e-06, |
| "loss": 0.1663, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.0931158489596712, |
| "grad_norm": 0.10679896920919418, |
| "learning_rate": 8.954715367323468e-06, |
| "loss": 0.1665, |
| "step": 1450 |
| }, |
| { |
| "epoch": 0.09632674030310814, |
| "grad_norm": 0.10078398883342743, |
| "learning_rate": 8.263518223330698e-06, |
| "loss": 0.1628, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.09953763164654508, |
| "grad_norm": 0.1051444560289383, |
| "learning_rate": 7.580781044003324e-06, |
| "loss": 0.167, |
| "step": 1550 |
| }, |
| { |
| "epoch": 0.10274852298998202, |
| "grad_norm": 0.10106322169303894, |
| "learning_rate": 6.909830056250527e-06, |
| "loss": 0.1659, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.10595941433341896, |
| "grad_norm": 0.11052313446998596, |
| "learning_rate": 6.25393406584088e-06, |
| "loss": 0.1641, |
| "step": 1650 |
| }, |
| { |
| "epoch": 0.1091703056768559, |
| "grad_norm": 0.10461756587028503, |
| "learning_rate": 5.616288532109225e-06, |
| "loss": 0.1634, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.11238119702029284, |
| "grad_norm": 0.09713000804185867, |
| "learning_rate": 5.000000000000003e-06, |
| "loss": 0.1637, |
| "step": 1750 |
| }, |
| { |
| "epoch": 0.11559208836372978, |
| "grad_norm": 0.10034234076738358, |
| "learning_rate": 4.408070965292534e-06, |
| "loss": 0.1629, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.1188029797071667, |
| "grad_norm": 0.1057053729891777, |
| "learning_rate": 3.8433852467434175e-06, |
| "loss": 0.1592, |
| "step": 1850 |
| }, |
| { |
| "epoch": 0.12201387105060364, |
| "grad_norm": 0.09985993802547455, |
| "learning_rate": 3.308693936411421e-06, |
| "loss": 0.1627, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.1252247623940406, |
| "grad_norm": 0.10140643268823624, |
| "learning_rate": 2.8066019966134907e-06, |
| "loss": 0.1617, |
| "step": 1950 |
| }, |
| { |
| "epoch": 0.12843565373747753, |
| "grad_norm": 0.10307465493679047, |
| "learning_rate": 2.339555568810221e-06, |
| "loss": 0.1664, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 2500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5.209439921504256e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
