| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004256949470009791, | |
| "eval_steps": 9, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.513898940019582e-05, | |
| "grad_norm": 0.06632853299379349, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3844, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.513898940019582e-05, | |
| "eval_loss": 10.380781173706055, | |
| "eval_runtime": 37.6703, | |
| "eval_samples_per_second": 262.567, | |
| "eval_steps_per_second": 32.838, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017027797880039163, | |
| "grad_norm": 0.06305789947509766, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3866, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002554169682005875, | |
| "grad_norm": 0.09040896594524384, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3699, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00034055595760078326, | |
| "grad_norm": 0.08260149508714676, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3876, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0004256949470009791, | |
| "grad_norm": 0.09195930510759354, | |
| "learning_rate": 5e-05, | |
| "loss": 10.39, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000510833936401175, | |
| "grad_norm": 0.08319511264562607, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3756, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005959729258013707, | |
| "grad_norm": 0.07701607048511505, | |
| "learning_rate": 7e-05, | |
| "loss": 10.3714, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006811119152015665, | |
| "grad_norm": 0.08848275989294052, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3649, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007662509046017624, | |
| "grad_norm": 0.07215868681669235, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3825, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007662509046017624, | |
| "eval_loss": 10.380110740661621, | |
| "eval_runtime": 37.0373, | |
| "eval_samples_per_second": 267.055, | |
| "eval_steps_per_second": 33.399, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008513898940019582, | |
| "grad_norm": 0.0638326108455658, | |
| "learning_rate": 0.0001, | |
| "loss": 10.376, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000936528883402154, | |
| "grad_norm": 0.0767514705657959, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 10.3839, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00102166787280235, | |
| "grad_norm": 0.06683874130249023, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 10.3901, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0011068068622025456, | |
| "grad_norm": 0.06641669571399689, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 10.3774, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0011919458516027415, | |
| "grad_norm": 0.05661563575267792, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 10.3847, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0012770848410029374, | |
| "grad_norm": 0.08233150839805603, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.3761, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001362223830403133, | |
| "grad_norm": 0.06432665884494781, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 10.3694, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.001447362819803329, | |
| "grad_norm": 0.08495861291885376, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 10.3777, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0015325018092035248, | |
| "grad_norm": 0.06713090091943741, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 10.3927, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0015325018092035248, | |
| "eval_loss": 10.378459930419922, | |
| "eval_runtime": 36.9921, | |
| "eval_samples_per_second": 267.381, | |
| "eval_steps_per_second": 33.44, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0016176407986037205, | |
| "grad_norm": 0.07406238466501236, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 10.3736, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0017027797880039164, | |
| "grad_norm": 0.06992701441049576, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.3714, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001787918777404112, | |
| "grad_norm": 0.0749615877866745, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 10.372, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.001873057766804308, | |
| "grad_norm": 0.06695009022951126, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 10.3943, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0019581967562045037, | |
| "grad_norm": 0.058970991522073746, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 10.3757, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0020433357456047, | |
| "grad_norm": 0.060394152998924255, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 10.3769, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0021284747350048955, | |
| "grad_norm": 0.07403624802827835, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3898, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002213613724405091, | |
| "grad_norm": 0.06255259364843369, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 10.3848, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0022987527138052873, | |
| "grad_norm": 0.07093428820371628, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 10.3834, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0022987527138052873, | |
| "eval_loss": 10.376791000366211, | |
| "eval_runtime": 37.1822, | |
| "eval_samples_per_second": 266.014, | |
| "eval_steps_per_second": 33.269, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002383891703205483, | |
| "grad_norm": 0.06431137025356293, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.3878, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0024690306926056786, | |
| "grad_norm": 0.06749837845563889, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 10.3917, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0025541696820058747, | |
| "grad_norm": 0.06856685876846313, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 10.3812, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0026393086714060704, | |
| "grad_norm": 0.07790417969226837, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 10.3734, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.002724447660806266, | |
| "grad_norm": 0.06906121224164963, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 10.3667, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0028095866502064622, | |
| "grad_norm": 0.07379811257123947, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 10.3681, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.002894725639606658, | |
| "grad_norm": 0.0777546837925911, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 10.3742, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0029798646290068536, | |
| "grad_norm": 0.09084642678499222, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 10.3725, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0030650036184070497, | |
| "grad_norm": 0.07533272355794907, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 10.3616, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0030650036184070497, | |
| "eval_loss": 10.3751859664917, | |
| "eval_runtime": 37.0132, | |
| "eval_samples_per_second": 267.229, | |
| "eval_steps_per_second": 33.42, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0031501426078072454, | |
| "grad_norm": 0.09557131677865982, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 10.3627, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.003235281597207441, | |
| "grad_norm": 0.086721271276474, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 10.3797, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.003320420586607637, | |
| "grad_norm": 0.0951017513871193, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 10.3642, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.003405559576007833, | |
| "grad_norm": 0.08322468400001526, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3718, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0034906985654080285, | |
| "grad_norm": 0.08715411275625229, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 10.3912, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.003575837554808224, | |
| "grad_norm": 0.07306662946939468, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 10.3831, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0036609765442084203, | |
| "grad_norm": 0.07265879958868027, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 10.3775, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.003746115533608616, | |
| "grad_norm": 0.07239469140768051, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 10.3708, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0038312545230088117, | |
| "grad_norm": 0.06718676537275314, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 10.3772, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0038312545230088117, | |
| "eval_loss": 10.373581886291504, | |
| "eval_runtime": 36.9465, | |
| "eval_samples_per_second": 267.712, | |
| "eval_steps_per_second": 33.481, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003916393512409007, | |
| "grad_norm": 0.1044333428144455, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 10.3736, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.004001532501809204, | |
| "grad_norm": 0.09110475331544876, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 10.3743, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0040866714912094, | |
| "grad_norm": 0.08908325433731079, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 10.3715, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.004171810480609595, | |
| "grad_norm": 0.09201818704605103, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 10.3745, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.004256949470009791, | |
| "grad_norm": 0.08138486742973328, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 10.3831, | |
| "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": 4864127533056.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |