| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6097560975609756, | |
| "eval_steps": 9, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008130081300813009, | |
| "grad_norm": 0.09686904400587082, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3889, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008130081300813009, | |
| "eval_loss": 10.389720916748047, | |
| "eval_runtime": 0.4759, | |
| "eval_samples_per_second": 872.114, | |
| "eval_steps_per_second": 27.319, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016260162601626018, | |
| "grad_norm": 0.1037309393286705, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3887, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.024390243902439025, | |
| "grad_norm": 0.09263376146554947, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3883, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.032520325203252036, | |
| "grad_norm": 0.09694579988718033, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3863, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04065040650406504, | |
| "grad_norm": 0.09658527374267578, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3861, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04878048780487805, | |
| "grad_norm": 0.10102847963571548, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3887, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.056910569105691054, | |
| "grad_norm": 0.09624768793582916, | |
| "learning_rate": 7e-05, | |
| "loss": 10.3884, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06504065040650407, | |
| "grad_norm": 0.09665016084909439, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3859, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07317073170731707, | |
| "grad_norm": 0.10208810120820999, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3866, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07317073170731707, | |
| "eval_loss": 10.388519287109375, | |
| "eval_runtime": 0.4716, | |
| "eval_samples_per_second": 879.969, | |
| "eval_steps_per_second": 27.565, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08130081300813008, | |
| "grad_norm": 0.10273765027523041, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3862, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08943089430894309, | |
| "grad_norm": 0.09759555011987686, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 10.3891, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 0.09805580228567123, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 10.384, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10569105691056911, | |
| "grad_norm": 0.10764916986227036, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 10.3893, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11382113821138211, | |
| "grad_norm": 0.09357812255620956, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 10.3871, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12195121951219512, | |
| "grad_norm": 0.11232280731201172, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.3861, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13008130081300814, | |
| "grad_norm": 0.10334710031747818, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 10.3854, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.13821138211382114, | |
| "grad_norm": 0.11682895570993423, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 10.3865, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14634146341463414, | |
| "grad_norm": 0.110913947224617, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 10.3843, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.14634146341463414, | |
| "eval_loss": 10.385440826416016, | |
| "eval_runtime": 0.4656, | |
| "eval_samples_per_second": 891.303, | |
| "eval_steps_per_second": 27.92, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15447154471544716, | |
| "grad_norm": 0.10033988207578659, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 10.3855, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.16260162601626016, | |
| "grad_norm": 0.09705800563097, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.3848, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17073170731707318, | |
| "grad_norm": 0.09242648631334305, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 10.3834, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.17886178861788618, | |
| "grad_norm": 0.1144818589091301, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 10.3833, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.18699186991869918, | |
| "grad_norm": 0.10459397733211517, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 10.3835, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 0.10212729871273041, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 10.3813, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2032520325203252, | |
| "grad_norm": 0.10831058770418167, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3812, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21138211382113822, | |
| "grad_norm": 0.11849161982536316, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 10.3872, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.21951219512195122, | |
| "grad_norm": 0.10534635931253433, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 10.3801, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.21951219512195122, | |
| "eval_loss": 10.382162094116211, | |
| "eval_runtime": 0.4726, | |
| "eval_samples_per_second": 878.139, | |
| "eval_steps_per_second": 27.508, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.22764227642276422, | |
| "grad_norm": 0.11179977655410767, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.3798, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.23577235772357724, | |
| "grad_norm": 0.12225475907325745, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 10.3798, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.24390243902439024, | |
| "grad_norm": 0.10354068130254745, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 10.3823, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.25203252032520324, | |
| "grad_norm": 0.12544958293437958, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 10.3814, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2601626016260163, | |
| "grad_norm": 0.09698833525180817, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 10.3784, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2682926829268293, | |
| "grad_norm": 0.12711447477340698, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 10.3771, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2764227642276423, | |
| "grad_norm": 0.14151258766651154, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 10.3822, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2845528455284553, | |
| "grad_norm": 0.10767289996147156, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 10.3796, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "grad_norm": 0.11947591602802277, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 10.3768, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "eval_loss": 10.37866497039795, | |
| "eval_runtime": 0.4767, | |
| "eval_samples_per_second": 870.534, | |
| "eval_steps_per_second": 27.27, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3008130081300813, | |
| "grad_norm": 0.1273428201675415, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 10.3778, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3089430894308943, | |
| "grad_norm": 0.12440553307533264, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 10.3797, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3170731707317073, | |
| "grad_norm": 0.12360162287950516, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 10.3798, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3252032520325203, | |
| "grad_norm": 0.13339215517044067, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3789, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.13511091470718384, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 10.3775, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.34146341463414637, | |
| "grad_norm": 0.12715180218219757, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 10.3757, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.34959349593495936, | |
| "grad_norm": 0.138566792011261, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 10.3778, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.35772357723577236, | |
| "grad_norm": 0.13547790050506592, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 10.3783, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.36585365853658536, | |
| "grad_norm": 0.1451762467622757, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 10.3737, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.36585365853658536, | |
| "eval_loss": 10.375040054321289, | |
| "eval_runtime": 0.4647, | |
| "eval_samples_per_second": 893.093, | |
| "eval_steps_per_second": 27.976, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.37398373983739835, | |
| "grad_norm": 0.14544105529785156, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 10.3762, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3821138211382114, | |
| "grad_norm": 0.15613853931427002, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 10.3718, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 0.15438242256641388, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 10.375, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3983739837398374, | |
| "grad_norm": 0.14396223425865173, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 10.3695, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4065040650406504, | |
| "grad_norm": 0.15646320581436157, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 10.3728, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4146341463414634, | |
| "grad_norm": 0.1587628722190857, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 10.3699, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.42276422764227645, | |
| "grad_norm": 0.14911603927612305, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 10.3695, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.43089430894308944, | |
| "grad_norm": 0.1736917495727539, | |
| "learning_rate": 5.348782368720626e-05, | |
| "loss": 10.3702, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.43902439024390244, | |
| "grad_norm": 0.1670113503932953, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 10.3715, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.43902439024390244, | |
| "eval_loss": 10.371479988098145, | |
| "eval_runtime": 0.4801, | |
| "eval_samples_per_second": 864.389, | |
| "eval_steps_per_second": 27.077, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.44715447154471544, | |
| "grad_norm": 0.14659471809864044, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3694, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.45528455284552843, | |
| "grad_norm": 0.1813124120235443, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 10.3698, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.4634146341463415, | |
| "grad_norm": 0.15320055186748505, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 10.371, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.4715447154471545, | |
| "grad_norm": 0.16380159556865692, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 10.3684, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.4796747967479675, | |
| "grad_norm": 0.14014634490013123, | |
| "learning_rate": 4.3041344951996746e-05, | |
| "loss": 10.3664, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 0.16128551959991455, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 10.3691, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4959349593495935, | |
| "grad_norm": 0.179128959774971, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 10.3663, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5040650406504065, | |
| "grad_norm": 0.1816730499267578, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 10.3667, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.5121951219512195, | |
| "grad_norm": 0.183024063706398, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 10.3674, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.5121951219512195, | |
| "eval_loss": 10.36843204498291, | |
| "eval_runtime": 0.4818, | |
| "eval_samples_per_second": 861.292, | |
| "eval_steps_per_second": 26.98, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.5203252032520326, | |
| "grad_norm": 0.16616392135620117, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 10.3696, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.5284552845528455, | |
| "grad_norm": 0.18292267620563507, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 10.3652, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5365853658536586, | |
| "grad_norm": 0.1613316386938095, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 10.3676, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.5447154471544715, | |
| "grad_norm": 0.17998585104942322, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 10.3678, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.5528455284552846, | |
| "grad_norm": 0.1902780830860138, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 10.365, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.5609756097560976, | |
| "grad_norm": 0.1761104017496109, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 10.368, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.5691056910569106, | |
| "grad_norm": 0.17624002695083618, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3665, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5772357723577236, | |
| "grad_norm": 0.18516290187835693, | |
| "learning_rate": 2.350403678833976e-05, | |
| "loss": 10.3661, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": 0.18870964646339417, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 10.3665, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "eval_loss": 10.366302490234375, | |
| "eval_runtime": 0.4628, | |
| "eval_samples_per_second": 896.775, | |
| "eval_steps_per_second": 28.092, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.5934959349593496, | |
| "grad_norm": 0.2053869515657425, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 10.3662, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.6016260162601627, | |
| "grad_norm": 0.18971996009349823, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 10.3648, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.6097560975609756, | |
| "grad_norm": 0.17851522564888, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 10.3638, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 31119955722240.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |