| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.2125069175428886, | |
| "eval_steps": 500, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05534034311012728, | |
| "grad_norm": 0.7568074464797974, | |
| "learning_rate": 9.8e-05, | |
| "loss": 1.0759, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11068068622025456, | |
| "grad_norm": 0.14674387872219086, | |
| "learning_rate": 0.00019800000000000002, | |
| "loss": 0.1883, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16602102933038185, | |
| "grad_norm": 0.13491740822792053, | |
| "learning_rate": 0.0001998263839556516, | |
| "loss": 0.1823, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22136137244050913, | |
| "grad_norm": 0.11964733898639679, | |
| "learning_rate": 0.00019929192281085555, | |
| "loss": 0.1812, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27670171555063644, | |
| "grad_norm": 0.14810685813426971, | |
| "learning_rate": 0.0001983984765530473, | |
| "loss": 0.181, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.3320420586607637, | |
| "grad_norm": 0.11917376518249512, | |
| "learning_rate": 0.0001971492753936756, | |
| "loss": 0.1801, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.387382401770891, | |
| "grad_norm": 0.11992548406124115, | |
| "learning_rate": 0.0001955488357587162, | |
| "loss": 0.1777, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.44272274488101826, | |
| "grad_norm": 0.09655219316482544, | |
| "learning_rate": 0.00019360294395975392, | |
| "loss": 0.1778, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.49806308799114557, | |
| "grad_norm": 0.08890487998723984, | |
| "learning_rate": 0.00019131863527385433, | |
| "loss": 0.1776, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.5534034311012729, | |
| "grad_norm": 0.09338568150997162, | |
| "learning_rate": 0.0001887041685078625, | |
| "loss": 0.1756, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6087437742114001, | |
| "grad_norm": 0.10447146743535995, | |
| "learning_rate": 0.0001857689961390886, | |
| "loss": 0.1769, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.6640841173215274, | |
| "grad_norm": 0.08940507471561432, | |
| "learning_rate": 0.00018252373014033646, | |
| "loss": 0.1767, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7194244604316546, | |
| "grad_norm": 0.1015540286898613, | |
| "learning_rate": 0.0001789801036128327, | |
| "loss": 0.1749, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.774764803541782, | |
| "grad_norm": 0.0866508036851883, | |
| "learning_rate": 0.0001751509283657702, | |
| "loss": 0.1765, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.8301051466519093, | |
| "grad_norm": 0.08853679150342941, | |
| "learning_rate": 0.00017105004859583578, | |
| "loss": 0.1757, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.8854454897620365, | |
| "grad_norm": 0.09371698647737503, | |
| "learning_rate": 0.00016669229083419114, | |
| "loss": 0.1766, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.9407858328721638, | |
| "grad_norm": 0.8600781559944153, | |
| "learning_rate": 0.00016209341034187125, | |
| "loss": 0.342, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.9961261759822911, | |
| "grad_norm": 0.0968112051486969, | |
| "learning_rate": 0.00015727003414740492, | |
| "loss": 0.1816, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.0509131156613172, | |
| "grad_norm": 0.092947818338871, | |
| "learning_rate": 0.00015223960093260294, | |
| "loss": 0.1753, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.1062534587714443, | |
| "grad_norm": 0.07544200122356415, | |
| "learning_rate": 0.00014702029798385264, | |
| "loss": 0.1747, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.1615938018815717, | |
| "grad_norm": 0.06907663494348526, | |
| "learning_rate": 0.00014163099543686964, | |
| "loss": 0.1741, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.2169341449916988, | |
| "grad_norm": 0.07450341433286667, | |
| "learning_rate": 0.00013609117805264063, | |
| "loss": 0.1754, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.2722744881018262, | |
| "grad_norm": 0.09569600224494934, | |
| "learning_rate": 0.0001304208747712189, | |
| "loss": 0.1732, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.3276148312119536, | |
| "grad_norm": 0.08210264891386032, | |
| "learning_rate": 0.00012464058629806633, | |
| "loss": 0.1716, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.3829551743220807, | |
| "grad_norm": 0.06857864558696747, | |
| "learning_rate": 0.00011877121098475106, | |
| "loss": 0.1728, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.438295517432208, | |
| "grad_norm": 0.11595187336206436, | |
| "learning_rate": 0.00011283396927197472, | |
| "loss": 0.174, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.4936358605423354, | |
| "grad_norm": 0.07529956847429276, | |
| "learning_rate": 0.00010685032696810226, | |
| "loss": 0.1733, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.5489762036524626, | |
| "grad_norm": 0.0644264817237854, | |
| "learning_rate": 0.00010084191764057676, | |
| "loss": 0.1738, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.60431654676259, | |
| "grad_norm": 0.060298092663288116, | |
| "learning_rate": 9.483046440080949e-05, | |
| "loss": 0.1717, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.6596568898727173, | |
| "grad_norm": 0.059512991458177567, | |
| "learning_rate": 8.883770136532834e-05, | |
| "loss": 0.1735, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.7149972329828445, | |
| "grad_norm": 0.0744907408952713, | |
| "learning_rate": 8.288529507713752e-05, | |
| "loss": 0.1722, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.7703375760929718, | |
| "grad_norm": 0.05729057267308235, | |
| "learning_rate": 7.699476617138598e-05, | |
| "loss": 0.1728, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.8256779192030992, | |
| "grad_norm": 0.06146302446722984, | |
| "learning_rate": 7.118741156855904e-05, | |
| "loss": 0.1714, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.8810182623132263, | |
| "grad_norm": 0.08402097970247269, | |
| "learning_rate": 6.548422747649902e-05, | |
| "loss": 0.1711, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.9363586054233535, | |
| "grad_norm": 0.06482277065515518, | |
| "learning_rate": 5.990583347963793e-05, | |
| "loss": 0.1714, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.991698948533481, | |
| "grad_norm": 0.06089329719543457, | |
| "learning_rate": 5.44723979898939e-05, | |
| "loss": 0.1711, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.0464858882125068, | |
| "grad_norm": 0.053777534514665604, | |
| "learning_rate": 4.9203565328759604e-05, | |
| "loss": 0.1708, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.1018262313226344, | |
| "grad_norm": 0.052074234932661057, | |
| "learning_rate": 4.411838470421454e-05, | |
| "loss": 0.169, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.1571665744327615, | |
| "grad_norm": 0.04878537356853485, | |
| "learning_rate": 3.923524133924069e-05, | |
| "loss": 0.1705, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.2125069175428886, | |
| "grad_norm": 0.06310058385133743, | |
| "learning_rate": 3.4571790000943973e-05, | |
| "loss": 0.1706, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 2712, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 3.341042688193413e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |