|
{ |
|
"best_metric": 6.696208477020264, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-50", |
|
"epoch": 0.0353198686697841, |
|
"eval_steps": 25, |
|
"global_step": 71, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0004974629390110437, |
|
"grad_norm": 2.1102797985076904, |
|
"learning_rate": 0.00015, |
|
"loss": 6.9589, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0004974629390110437, |
|
"eval_loss": 6.948693752288818, |
|
"eval_runtime": 0.0403, |
|
"eval_samples_per_second": 1242.035, |
|
"eval_steps_per_second": 74.522, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0009949258780220873, |
|
"grad_norm": 0.7844905853271484, |
|
"learning_rate": 0.0003, |
|
"loss": 6.9495, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0014923888170331311, |
|
"grad_norm": 1.2520802021026611, |
|
"learning_rate": 0.0002998600959423082, |
|
"loss": 6.9498, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0019898517560441747, |
|
"grad_norm": 1.3780094385147095, |
|
"learning_rate": 0.0002994406737417567, |
|
"loss": 6.9461, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0024873146950552183, |
|
"grad_norm": 1.5773358345031738, |
|
"learning_rate": 0.00029874260271490463, |
|
"loss": 6.9386, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0029847776340662623, |
|
"grad_norm": 1.953880786895752, |
|
"learning_rate": 0.00029776732972055516, |
|
"loss": 6.9294, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.003482240573077306, |
|
"grad_norm": 1.976645588874817, |
|
"learning_rate": 0.0002965168761609197, |
|
"loss": 6.9055, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.003979703512088349, |
|
"grad_norm": 0.8517647385597229, |
|
"learning_rate": 0.0002949938337919529, |
|
"loss": 6.9133, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.004477166451099393, |
|
"grad_norm": 1.1108756065368652, |
|
"learning_rate": 0.0002932013593515431, |
|
"loss": 6.9281, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.0049746293901104365, |
|
"grad_norm": 1.314795732498169, |
|
"learning_rate": 0.00029114316801669057, |
|
"loss": 6.8758, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.0054720923291214805, |
|
"grad_norm": 1.5624110698699951, |
|
"learning_rate": 0.00028882352570323616, |
|
"loss": 6.8467, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.0059695552681325245, |
|
"grad_norm": 1.8820241689682007, |
|
"learning_rate": 0.00028624724022409897, |
|
"loss": 6.8124, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.006467018207143568, |
|
"grad_norm": 1.1546019315719604, |
|
"learning_rate": 0.0002834196513243502, |
|
"loss": 6.8769, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.006964481146154612, |
|
"grad_norm": 1.020631194114685, |
|
"learning_rate": 0.0002803466196137759, |
|
"loss": 6.8753, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.007461944085165655, |
|
"grad_norm": 0.9455771446228027, |
|
"learning_rate": 0.00027703451441986836, |
|
"loss": 6.8669, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.007959407024176699, |
|
"grad_norm": 1.3777406215667725, |
|
"learning_rate": 0.000273490200586422, |
|
"loss": 6.8486, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.008456869963187742, |
|
"grad_norm": 0.7217961549758911, |
|
"learning_rate": 0.00026972102424509665, |
|
"loss": 6.8179, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.008954332902198787, |
|
"grad_norm": 1.2333062887191772, |
|
"learning_rate": 0.00026573479758943753, |
|
"loss": 6.7716, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.00945179584120983, |
|
"grad_norm": 1.557617425918579, |
|
"learning_rate": 0.0002615397826829114, |
|
"loss": 6.7166, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.009949258780220873, |
|
"grad_norm": 1.0129878520965576, |
|
"learning_rate": 0.0002571446743345183, |
|
"loss": 6.8344, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.010446721719231918, |
|
"grad_norm": 1.1682052612304688, |
|
"learning_rate": 0.00025255858207747205, |
|
"loss": 6.8857, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.010944184658242961, |
|
"grad_norm": 1.0228655338287354, |
|
"learning_rate": 0.0002477910112883017, |
|
"loss": 6.8231, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.011441647597254004, |
|
"grad_norm": 1.154994010925293, |
|
"learning_rate": 0.00024285184348550706, |
|
"loss": 6.7277, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.011939110536265049, |
|
"grad_norm": 1.3172268867492676, |
|
"learning_rate": 0.0002377513158486027, |
|
"loss": 6.6751, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.012436573475276092, |
|
"grad_norm": 1.1298874616622925, |
|
"learning_rate": 0.00023249999999999999, |
|
"loss": 6.7232, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.012436573475276092, |
|
"eval_loss": 6.769708633422852, |
|
"eval_runtime": 0.0413, |
|
"eval_samples_per_second": 1209.612, |
|
"eval_steps_per_second": 72.577, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.012934036414287135, |
|
"grad_norm": 1.482825756072998, |
|
"learning_rate": 0.00022710878009370554, |
|
"loss": 6.835, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.013431499353298178, |
|
"grad_norm": 0.6565159559249878, |
|
"learning_rate": 0.00022158883025624965, |
|
"loss": 6.8394, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.013928962292309223, |
|
"grad_norm": 1.1333484649658203, |
|
"learning_rate": 0.0002159515914266029, |
|
"loss": 6.8224, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.014426425231320266, |
|
"grad_norm": 0.9818063974380493, |
|
"learning_rate": 0.0002102087476430831, |
|
"loss": 6.8011, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.01492388817033131, |
|
"grad_norm": 1.1090376377105713, |
|
"learning_rate": 0.00020437220182640135, |
|
"loss": 6.6984, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.015421351109342354, |
|
"grad_norm": 1.2643979787826538, |
|
"learning_rate": 0.00019845405110904146, |
|
"loss": 6.6402, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.015918814048353398, |
|
"grad_norm": 0.8210477232933044, |
|
"learning_rate": 0.00019246656176210558, |
|
"loss": 6.7164, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.01641627698736444, |
|
"grad_norm": 0.8293486833572388, |
|
"learning_rate": 0.0001864221437715939, |
|
"loss": 6.8353, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.016913739926375484, |
|
"grad_norm": 0.9909377098083496, |
|
"learning_rate": 0.0001803333251168141, |
|
"loss": 6.8237, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.01741120286538653, |
|
"grad_norm": 0.7456725239753723, |
|
"learning_rate": 0.00017421272580423058, |
|
"loss": 6.7016, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.017908665804397574, |
|
"grad_norm": 0.9571717381477356, |
|
"learning_rate": 0.00016807303171057425, |
|
"loss": 6.6303, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.018406128743408617, |
|
"grad_norm": 1.1454938650131226, |
|
"learning_rate": 0.00016192696828942573, |
|
"loss": 6.5629, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.01890359168241966, |
|
"grad_norm": 1.051835298538208, |
|
"learning_rate": 0.00015578727419576942, |
|
"loss": 6.8194, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.019401054621430703, |
|
"grad_norm": 0.9183468818664551, |
|
"learning_rate": 0.00014966667488318586, |
|
"loss": 6.8263, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.019898517560441746, |
|
"grad_norm": 1.002596378326416, |
|
"learning_rate": 0.00014357785622840606, |
|
"loss": 6.8061, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.02039598049945279, |
|
"grad_norm": 1.323659896850586, |
|
"learning_rate": 0.00013753343823789445, |
|
"loss": 6.7613, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.020893443438463836, |
|
"grad_norm": 0.601455569267273, |
|
"learning_rate": 0.00013154594889095854, |
|
"loss": 6.721, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.02139090637747488, |
|
"grad_norm": 0.9729992747306824, |
|
"learning_rate": 0.00012562779817359865, |
|
"loss": 6.6221, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.021888369316485922, |
|
"grad_norm": 1.1012927293777466, |
|
"learning_rate": 0.00011979125235691685, |
|
"loss": 6.5465, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.022385832255496965, |
|
"grad_norm": 0.921903133392334, |
|
"learning_rate": 0.00011404840857339706, |
|
"loss": 6.7825, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.02288329519450801, |
|
"grad_norm": 1.041771650314331, |
|
"learning_rate": 0.0001084111697437504, |
|
"loss": 6.8214, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.02338075813351905, |
|
"grad_norm": 0.6873188018798828, |
|
"learning_rate": 0.00010289121990629447, |
|
"loss": 6.7128, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.023878221072530098, |
|
"grad_norm": 0.9764477014541626, |
|
"learning_rate": 9.750000000000003e-05, |
|
"loss": 6.6194, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.02437568401154114, |
|
"grad_norm": 0.851015031337738, |
|
"learning_rate": 9.22486841513973e-05, |
|
"loss": 6.55, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.024873146950552184, |
|
"grad_norm": 0.7856554388999939, |
|
"learning_rate": 8.714815651449293e-05, |
|
"loss": 6.628, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.024873146950552184, |
|
"eval_loss": 6.696208477020264, |
|
"eval_runtime": 0.0415, |
|
"eval_samples_per_second": 1204.166, |
|
"eval_steps_per_second": 72.25, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.025370609889563227, |
|
"grad_norm": 1.6974908113479614, |
|
"learning_rate": 8.220898871169827e-05, |
|
"loss": 6.8279, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 0.02586807282857427, |
|
"grad_norm": 0.6426116824150085, |
|
"learning_rate": 7.744141792252794e-05, |
|
"loss": 6.802, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 0.026365535767585314, |
|
"grad_norm": 1.004481315612793, |
|
"learning_rate": 7.285532566548172e-05, |
|
"loss": 6.767, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 0.026862998706596357, |
|
"grad_norm": 1.2093220949172974, |
|
"learning_rate": 6.846021731708856e-05, |
|
"loss": 6.7411, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 0.027360461645607403, |
|
"grad_norm": 0.7267762422561646, |
|
"learning_rate": 6.426520241056245e-05, |
|
"loss": 6.6548, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.027857924584618447, |
|
"grad_norm": 0.8319692611694336, |
|
"learning_rate": 6.0278975754903317e-05, |
|
"loss": 6.5916, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 0.02835538752362949, |
|
"grad_norm": 0.7229805588722229, |
|
"learning_rate": 5.6509799413577934e-05, |
|
"loss": 6.593, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 0.028852850462640533, |
|
"grad_norm": 0.8349987268447876, |
|
"learning_rate": 5.296548558013161e-05, |
|
"loss": 6.7984, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 0.029350313401651576, |
|
"grad_norm": 0.9424655437469482, |
|
"learning_rate": 4.9653380386224046e-05, |
|
"loss": 6.7904, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 0.02984777634066262, |
|
"grad_norm": 0.6447422504425049, |
|
"learning_rate": 4.658034867564977e-05, |
|
"loss": 6.66, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.030345239279673666, |
|
"grad_norm": 0.8311784267425537, |
|
"learning_rate": 4.375275977590104e-05, |
|
"loss": 6.5813, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 0.03084270221868471, |
|
"grad_norm": 0.9207125902175903, |
|
"learning_rate": 4.117647429676387e-05, |
|
"loss": 6.5121, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 0.03134016515769575, |
|
"grad_norm": 1.0499930381774902, |
|
"learning_rate": 3.885683198330941e-05, |
|
"loss": 6.7942, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 0.031837628096706795, |
|
"grad_norm": 0.9650680422782898, |
|
"learning_rate": 3.679864064845691e-05, |
|
"loss": 6.8169, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 0.03233509103571784, |
|
"grad_norm": 0.8432676792144775, |
|
"learning_rate": 3.500616620804712e-05, |
|
"loss": 6.7807, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.03283255397472888, |
|
"grad_norm": 1.2601343393325806, |
|
"learning_rate": 3.348312383908033e-05, |
|
"loss": 6.7331, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 0.03333001691373993, |
|
"grad_norm": 0.5202540755271912, |
|
"learning_rate": 3.223267027944483e-05, |
|
"loss": 6.7119, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 0.03382747985275097, |
|
"grad_norm": 0.8801518678665161, |
|
"learning_rate": 3.125739728509535e-05, |
|
"loss": 6.5942, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 0.034324942791762014, |
|
"grad_norm": 0.9333907961845398, |
|
"learning_rate": 3.055932625824328e-05, |
|
"loss": 6.5063, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 0.03482240573077306, |
|
"grad_norm": 0.7383935451507568, |
|
"learning_rate": 3.0139904057691777e-05, |
|
"loss": 6.6695, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.0353198686697841, |
|
"grad_norm": 0.9811359643936157, |
|
"learning_rate": 2.9999999999999997e-05, |
|
"loss": 6.8281, |
|
"step": 71 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 71, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 50, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 1, |
|
"early_stopping_threshold": 0.0 |
|
}, |
|
"attributes": { |
|
"early_stopping_patience_counter": 0 |
|
} |
|
}, |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 7767234478080.0, |
|
"train_batch_size": 6, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|