| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.014275517487508922, | |
| "eval_steps": 9, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00028551034975017847, | |
| "grad_norm": 0.027432993054389954, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3805, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028551034975017847, | |
| "eval_loss": 10.382046699523926, | |
| "eval_runtime": 42.12, | |
| "eval_samples_per_second": 70.038, | |
| "eval_steps_per_second": 8.761, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005710206995003569, | |
| "grad_norm": 0.027489671483635902, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3802, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008565310492505353, | |
| "grad_norm": 0.02459365874528885, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3816, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011420413990007139, | |
| "grad_norm": 0.02365339733660221, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3818, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014275517487508922, | |
| "grad_norm": 0.02527313493192196, | |
| "learning_rate": 5e-05, | |
| "loss": 10.38, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0017130620985010706, | |
| "grad_norm": 0.03066786751151085, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3819, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001998572448251249, | |
| "grad_norm": 0.024464154615998268, | |
| "learning_rate": 7e-05, | |
| "loss": 10.3822, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022840827980014277, | |
| "grad_norm": 0.025396525859832764, | |
| "learning_rate": 8e-05, | |
| "loss": 10.382, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002569593147751606, | |
| "grad_norm": 0.02810545265674591, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3803, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002569593147751606, | |
| "eval_loss": 10.38175106048584, | |
| "eval_runtime": 42.136, | |
| "eval_samples_per_second": 70.011, | |
| "eval_steps_per_second": 8.757, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0028551034975017845, | |
| "grad_norm": 0.02721717581152916, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3812, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003140613847251963, | |
| "grad_norm": 0.022978119552135468, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 10.3798, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003426124197002141, | |
| "grad_norm": 0.026420678943395615, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 10.3813, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0037116345467523197, | |
| "grad_norm": 0.032193541526794434, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 10.38, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003997144896502498, | |
| "grad_norm": 0.036693818867206573, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 10.3818, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004282655246252677, | |
| "grad_norm": 0.025059012696146965, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.3803, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0045681655960028555, | |
| "grad_norm": 0.02436673268675804, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 10.3805, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004853675945753033, | |
| "grad_norm": 0.03707301244139671, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 10.3836, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005139186295503212, | |
| "grad_norm": 0.025976257398724556, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 10.3789, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005139186295503212, | |
| "eval_loss": 10.380975723266602, | |
| "eval_runtime": 42.4056, | |
| "eval_samples_per_second": 69.566, | |
| "eval_steps_per_second": 8.702, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00542469664525339, | |
| "grad_norm": 0.028088079765439034, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 10.3773, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005710206995003569, | |
| "grad_norm": 0.02719559706747532, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.3819, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0059957173447537475, | |
| "grad_norm": 0.024702034890651703, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 10.3805, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006281227694503926, | |
| "grad_norm": 0.02431425452232361, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 10.3804, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006566738044254105, | |
| "grad_norm": 0.03136470168828964, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 10.3779, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006852248394004282, | |
| "grad_norm": 0.02518298849463463, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 10.3798, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007137758743754461, | |
| "grad_norm": 0.029198575764894485, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3807, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0074232690935046395, | |
| "grad_norm": 0.026710139587521553, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 10.3785, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007708779443254818, | |
| "grad_norm": 0.033151932060718536, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 10.3804, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007708779443254818, | |
| "eval_loss": 10.380158424377441, | |
| "eval_runtime": 42.2392, | |
| "eval_samples_per_second": 69.84, | |
| "eval_steps_per_second": 8.736, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007994289793004997, | |
| "grad_norm": 0.03826072812080383, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.3811, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.008279800142755174, | |
| "grad_norm": 0.028944505378603935, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 10.3767, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008565310492505354, | |
| "grad_norm": 0.025594528764486313, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 10.3826, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008850820842255532, | |
| "grad_norm": 0.03534218296408653, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 10.3787, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.009136331192005711, | |
| "grad_norm": 0.03356329724192619, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 10.3809, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.009421841541755889, | |
| "grad_norm": 0.03521755710244179, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 10.3805, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009707351891506066, | |
| "grad_norm": 0.04086000844836235, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 10.3797, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009992862241256246, | |
| "grad_norm": 0.028289103880524635, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 10.3805, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010278372591006424, | |
| "grad_norm": 0.03809809312224388, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 10.377, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.010278372591006424, | |
| "eval_loss": 10.379316329956055, | |
| "eval_runtime": 42.2396, | |
| "eval_samples_per_second": 69.84, | |
| "eval_steps_per_second": 8.736, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.010563882940756603, | |
| "grad_norm": 0.03364298865199089, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 10.3792, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01084939329050678, | |
| "grad_norm": 0.03586876392364502, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 10.3766, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01113490364025696, | |
| "grad_norm": 0.030886787921190262, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 10.3789, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.011420413990007138, | |
| "grad_norm": 0.03570697829127312, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3804, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011705924339757316, | |
| "grad_norm": 0.03459020331501961, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 10.3777, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011991434689507495, | |
| "grad_norm": 0.03704289346933365, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 10.3769, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.012276945039257673, | |
| "grad_norm": 0.03582561016082764, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 10.378, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.012562455389007852, | |
| "grad_norm": 0.033004630357027054, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 10.38, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.01284796573875803, | |
| "grad_norm": 0.034119606018066406, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 10.3789, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01284796573875803, | |
| "eval_loss": 10.378472328186035, | |
| "eval_runtime": 42.1903, | |
| "eval_samples_per_second": 69.921, | |
| "eval_steps_per_second": 8.746, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01313347608850821, | |
| "grad_norm": 0.03747232258319855, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 10.3778, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.013418986438258387, | |
| "grad_norm": 0.04485693201422691, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 10.3784, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.013704496788008565, | |
| "grad_norm": 0.051734451204538345, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 10.3775, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013990007137758744, | |
| "grad_norm": 0.046976011246442795, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 10.3767, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.014275517487508922, | |
| "grad_norm": 0.04274662956595421, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 10.3785, | |
| "step": 50 | |
| } | |
| ], | |
| "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": 5230244659200.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |