Batch upload: checkpoint-1000 checkpoint-10000 checkpoint-100000 checkpoint-101000 checkpoint-102000 checkpoint-103000 checkpoint-104000 checkpoint-105000 checkpoint-106000 checkpoint-107000 checkpoint-108000 checkpoint-108168 checkpoint-11000 checkpoint-12000 checkpoint-13000 checkpoint-14000 checkpoint-15000 checkpoint-16000 checkpoint-17000 checkpoint-18000 checkpoint-19000 checkpoint-2000 checkpoint-20000 checkpoint-21000 checkpoint-22000 checkpoint-23000 checkpoint-24000 checkpoint-25000 checkpoint-26000 checkpoint-27000 checkpoint-28000 checkpoint-29000 checkpoint-3000 checkpoint-30000 checkpoint-31000 checkpoint-32000 checkpoint-33000 checkpoint-34000 checkpoint-35000 checkpoint-36000 checkpoint-37000 checkpoint-38000 checkpoint-39000 checkpoint-4000 checkpoint-40000 checkpoint-41000 checkpoint-42000 checkpoint-43000 checkpoint-44000 checkpoint-45000
e1ac6ff
verified
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11093815544515669, | |
| "eval_steps": 1000, | |
| "global_step": 4000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013867269430644586, | |
| "grad_norm": 1.8933687210083008, | |
| "learning_rate": 2.957486136783734e-06, | |
| "loss": 1.2241, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.002773453886128917, | |
| "grad_norm": 0.7502820491790771, | |
| "learning_rate": 6.038200862600124e-06, | |
| "loss": 1.0267, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.004160180829193376, | |
| "grad_norm": 0.5821689963340759, | |
| "learning_rate": 9.118915588416513e-06, | |
| "loss": 0.8167, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.005546907772257834, | |
| "grad_norm": 0.5138927698135376, | |
| "learning_rate": 1.2199630314232902e-05, | |
| "loss": 0.6408, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.006933634715322293, | |
| "grad_norm": 0.619263768196106, | |
| "learning_rate": 1.5280345040049293e-05, | |
| "loss": 0.5468, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.008320361658386751, | |
| "grad_norm": 0.5078439712524414, | |
| "learning_rate": 1.836105976586568e-05, | |
| "loss": 0.4952, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.00970708860145121, | |
| "grad_norm": 0.5653749108314514, | |
| "learning_rate": 2.144177449168207e-05, | |
| "loss": 0.4388, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.011093815544515669, | |
| "grad_norm": 0.6189213991165161, | |
| "learning_rate": 2.452248921749846e-05, | |
| "loss": 0.4232, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.012480542487580126, | |
| "grad_norm": 0.6082913875579834, | |
| "learning_rate": 2.760320394331485e-05, | |
| "loss": 0.401, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.013867269430644586, | |
| "grad_norm": 0.6956301331520081, | |
| "learning_rate": 3.068391866913124e-05, | |
| "loss": 0.3895, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.015253996373709043, | |
| "grad_norm": 0.7030412554740906, | |
| "learning_rate": 3.3764633394947633e-05, | |
| "loss": 0.3676, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.016640723316773503, | |
| "grad_norm": 0.6779190897941589, | |
| "learning_rate": 3.684534812076402e-05, | |
| "loss": 0.3653, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.01802745025983796, | |
| "grad_norm": 0.8930213451385498, | |
| "learning_rate": 3.992606284658041e-05, | |
| "loss": 0.3645, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.01941417720290242, | |
| "grad_norm": 0.6423994302749634, | |
| "learning_rate": 4.30067775723968e-05, | |
| "loss": 0.3514, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.02080090414596688, | |
| "grad_norm": 0.7728660106658936, | |
| "learning_rate": 4.608749229821319e-05, | |
| "loss": 0.3468, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.022187631089031337, | |
| "grad_norm": 0.7561061978340149, | |
| "learning_rate": 4.916820702402958e-05, | |
| "loss": 0.3499, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.023574358032095795, | |
| "grad_norm": 0.6163890957832336, | |
| "learning_rate": 5.224892174984597e-05, | |
| "loss": 0.3417, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.024961084975160253, | |
| "grad_norm": 0.7334563732147217, | |
| "learning_rate": 5.532963647566236e-05, | |
| "loss": 0.3299, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.026347811918224714, | |
| "grad_norm": 0.655237078666687, | |
| "learning_rate": 5.841035120147874e-05, | |
| "loss": 0.3306, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.02773453886128917, | |
| "grad_norm": 0.8147113919258118, | |
| "learning_rate": 6.149106592729513e-05, | |
| "loss": 0.3281, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.02773453886128917, | |
| "eval_loss": 0.32194069027900696, | |
| "eval_runtime": 501.2457, | |
| "eval_samples_per_second": 5.7, | |
| "eval_steps_per_second": 5.7, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.02912126580435363, | |
| "grad_norm": 0.6397083401679993, | |
| "learning_rate": 6.457178065311152e-05, | |
| "loss": 0.3204, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.030507992747418087, | |
| "grad_norm": 0.5808627009391785, | |
| "learning_rate": 6.765249537892791e-05, | |
| "loss": 0.3229, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.03189471969048255, | |
| "grad_norm": 0.6929567456245422, | |
| "learning_rate": 7.073321010474431e-05, | |
| "loss": 0.3148, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.033281446633547006, | |
| "grad_norm": 0.620298445224762, | |
| "learning_rate": 7.38139248305607e-05, | |
| "loss": 0.32, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.034668173576611463, | |
| "grad_norm": 0.5947968363761902, | |
| "learning_rate": 7.689463955637708e-05, | |
| "loss": 0.306, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.03605490051967592, | |
| "grad_norm": 0.6097683906555176, | |
| "learning_rate": 7.997535428219347e-05, | |
| "loss": 0.3179, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.03744162746274038, | |
| "grad_norm": 0.6339348554611206, | |
| "learning_rate": 8.305606900800986e-05, | |
| "loss": 0.3161, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.03882835440580484, | |
| "grad_norm": 0.5278933644294739, | |
| "learning_rate": 8.613678373382625e-05, | |
| "loss": 0.3153, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.040215081348869294, | |
| "grad_norm": 0.4927423894405365, | |
| "learning_rate": 8.921749845964264e-05, | |
| "loss": 0.3111, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.04160180829193376, | |
| "grad_norm": 0.4745596945285797, | |
| "learning_rate": 9.229821318545902e-05, | |
| "loss": 0.304, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04298853523499822, | |
| "grad_norm": 0.6532231569290161, | |
| "learning_rate": 9.537892791127541e-05, | |
| "loss": 0.3084, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.044375262178062674, | |
| "grad_norm": 0.5528659820556641, | |
| "learning_rate": 9.84596426370918e-05, | |
| "loss": 0.3084, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.04576198912112713, | |
| "grad_norm": 0.45793089270591736, | |
| "learning_rate": 0.0001015403573629082, | |
| "loss": 0.2964, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.04714871606419159, | |
| "grad_norm": 0.5063529014587402, | |
| "learning_rate": 0.00010462107208872458, | |
| "loss": 0.2924, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.04853544300725605, | |
| "grad_norm": 0.48600247502326965, | |
| "learning_rate": 0.00010770178681454097, | |
| "loss": 0.2947, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.049922169950320505, | |
| "grad_norm": 0.4872143268585205, | |
| "learning_rate": 0.00011078250154035737, | |
| "loss": 0.297, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.05130889689338496, | |
| "grad_norm": 0.5091805458068848, | |
| "learning_rate": 0.00011386321626617376, | |
| "loss": 0.2888, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.05269562383644943, | |
| "grad_norm": 0.41649994254112244, | |
| "learning_rate": 0.00011694393099199015, | |
| "loss": 0.2871, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.054082350779513885, | |
| "grad_norm": 0.5174862146377563, | |
| "learning_rate": 0.00012002464571780654, | |
| "loss": 0.2922, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.05546907772257834, | |
| "grad_norm": 0.45786553621292114, | |
| "learning_rate": 0.00012310536044362293, | |
| "loss": 0.2883, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.05546907772257834, | |
| "eval_loss": 0.28488224744796753, | |
| "eval_runtime": 500.9558, | |
| "eval_samples_per_second": 5.703, | |
| "eval_steps_per_second": 5.703, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.0568558046656428, | |
| "grad_norm": 0.4992533326148987, | |
| "learning_rate": 0.00012606284658040666, | |
| "loss": 0.3033, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.05824253160870726, | |
| "grad_norm": 0.4205988049507141, | |
| "learning_rate": 0.00012914356130622304, | |
| "loss": 0.2867, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.059629258551771716, | |
| "grad_norm": 0.4288152754306793, | |
| "learning_rate": 0.00013222427603203944, | |
| "loss": 0.2795, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.061015985494836174, | |
| "grad_norm": 0.4856145977973938, | |
| "learning_rate": 0.00013530499075785582, | |
| "loss": 0.2833, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.06240271243790063, | |
| "grad_norm": 0.4891654849052429, | |
| "learning_rate": 0.00013838570548367222, | |
| "loss": 0.2797, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.0637894393809651, | |
| "grad_norm": 0.39899352192878723, | |
| "learning_rate": 0.00014146642020948863, | |
| "loss": 0.2785, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.06517616632402955, | |
| "grad_norm": 0.3616255819797516, | |
| "learning_rate": 0.000144547134935305, | |
| "loss": 0.2798, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.06656289326709401, | |
| "grad_norm": 0.3556617498397827, | |
| "learning_rate": 0.0001476278496611214, | |
| "loss": 0.2811, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.06794962021015846, | |
| "grad_norm": 0.39639297127723694, | |
| "learning_rate": 0.00015070856438693776, | |
| "loss": 0.2813, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.06933634715322293, | |
| "grad_norm": 0.35177573561668396, | |
| "learning_rate": 0.00015378927911275416, | |
| "loss": 0.2797, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.07072307409628739, | |
| "grad_norm": 0.38610222935676575, | |
| "learning_rate": 0.00015686999383857054, | |
| "loss": 0.2747, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.07210980103935184, | |
| "grad_norm": 0.36727309226989746, | |
| "learning_rate": 0.00015995070856438694, | |
| "loss": 0.2776, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.07349652798241631, | |
| "grad_norm": 0.3905107378959656, | |
| "learning_rate": 0.00016303142329020332, | |
| "loss": 0.2772, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.07488325492548076, | |
| "grad_norm": 0.3958912193775177, | |
| "learning_rate": 0.00016611213801601973, | |
| "loss": 0.2707, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.07626998186854522, | |
| "grad_norm": 0.4029497504234314, | |
| "learning_rate": 0.0001691928527418361, | |
| "loss": 0.2692, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.07765670881160967, | |
| "grad_norm": 0.3514055907726288, | |
| "learning_rate": 0.0001722735674676525, | |
| "loss": 0.2759, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.07904343575467414, | |
| "grad_norm": 0.34912553429603577, | |
| "learning_rate": 0.00017529266789895255, | |
| "loss": 0.2793, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.08043016269773859, | |
| "grad_norm": 0.3493233621120453, | |
| "learning_rate": 0.00017831176833025262, | |
| "loss": 0.2845, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.08181688964080305, | |
| "grad_norm": 0.30080145597457886, | |
| "learning_rate": 0.00018139248305606902, | |
| "loss": 0.2686, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.08320361658386752, | |
| "grad_norm": 0.3265998959541321, | |
| "learning_rate": 0.0001844731977818854, | |
| "loss": 0.2695, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.08320361658386752, | |
| "eval_loss": 0.26523345708847046, | |
| "eval_runtime": 500.4565, | |
| "eval_samples_per_second": 5.709, | |
| "eval_steps_per_second": 5.709, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.08459034352693197, | |
| "grad_norm": 0.29866209626197815, | |
| "learning_rate": 0.0001875539125077018, | |
| "loss": 0.2679, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.08597707046999643, | |
| "grad_norm": 0.3191625475883484, | |
| "learning_rate": 0.00019063462723351818, | |
| "loss": 0.267, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.08736379741306088, | |
| "grad_norm": 0.3110339939594269, | |
| "learning_rate": 0.00019371534195933459, | |
| "loss": 0.2658, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.08875052435612535, | |
| "grad_norm": 0.32120850682258606, | |
| "learning_rate": 0.00019679605668515096, | |
| "loss": 0.2724, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.0901372512991898, | |
| "grad_norm": 0.28446418046951294, | |
| "learning_rate": 0.00019987677141096734, | |
| "loss": 0.268, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.09152397824225426, | |
| "grad_norm": 0.2722443640232086, | |
| "learning_rate": 0.00019999989671933422, | |
| "loss": 0.2716, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.09291070518531871, | |
| "grad_norm": 0.31304416060447693, | |
| "learning_rate": 0.00019999956948482068, | |
| "loss": 0.2631, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.09429743212838318, | |
| "grad_norm": 0.2516928017139435, | |
| "learning_rate": 0.00019999901811788604, | |
| "loss": 0.2647, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.09568415907144764, | |
| "grad_norm": 0.288006067276001, | |
| "learning_rate": 0.00019999824261976613, | |
| "loss": 0.263, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.0970708860145121, | |
| "grad_norm": 0.2745107114315033, | |
| "learning_rate": 0.00019999724299219913, | |
| "loss": 0.2642, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.09845761295757656, | |
| "grad_norm": 2.800987720489502, | |
| "learning_rate": 0.00019999601923742548, | |
| "loss": 0.7176, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.09984433990064101, | |
| "grad_norm": 0.3590925931930542, | |
| "learning_rate": 0.00019999457135818805, | |
| "loss": 0.3146, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.10123106684370548, | |
| "grad_norm": 0.32617494463920593, | |
| "learning_rate": 0.00019999289935773202, | |
| "loss": 0.2786, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.10261779378676993, | |
| "grad_norm": 0.3239264488220215, | |
| "learning_rate": 0.0001999910032398049, | |
| "loss": 0.2807, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.10400452072983439, | |
| "grad_norm": 0.3022274076938629, | |
| "learning_rate": 0.00019998888300865652, | |
| "loss": 0.2758, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.10539124767289886, | |
| "grad_norm": 0.33024862408638, | |
| "learning_rate": 0.000199986538669039, | |
| "loss": 0.2687, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.1067779746159633, | |
| "grad_norm": 0.6899451017379761, | |
| "learning_rate": 0.00019998397022620687, | |
| "loss": 0.2699, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.10816470155902777, | |
| "grad_norm": 0.2794604003429413, | |
| "learning_rate": 0.0001999811776859168, | |
| "loss": 0.2667, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.10955142850209222, | |
| "grad_norm": 0.2764255106449127, | |
| "learning_rate": 0.00019997816105442778, | |
| "loss": 0.2658, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.11093815544515669, | |
| "grad_norm": 0.43574222922325134, | |
| "learning_rate": 0.0001999749203385012, | |
| "loss": 0.2664, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.11093815544515669, | |
| "eval_loss": 0.26065966486930847, | |
| "eval_runtime": 500.842, | |
| "eval_samples_per_second": 5.704, | |
| "eval_steps_per_second": 5.704, | |
| "step": 4000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 108168, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.209543008256e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |