| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001053230257198829, | |
| "eval_steps": 9, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.1064605143976575e-05, | |
| "grad_norm": 0.0323529914021492, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3808, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.1064605143976575e-05, | |
| "eval_loss": 10.377638816833496, | |
| "eval_runtime": 325.5686, | |
| "eval_samples_per_second": 122.794, | |
| "eval_steps_per_second": 15.352, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.212921028795315e-05, | |
| "grad_norm": 0.033095818012952805, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3753, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 6.319381543192973e-05, | |
| "grad_norm": 0.03802718222141266, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3781, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 8.42584205759063e-05, | |
| "grad_norm": 0.03922766447067261, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3802, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00010532302571988288, | |
| "grad_norm": 0.029788147658109665, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3783, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00012638763086385946, | |
| "grad_norm": 0.03316537290811539, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3773, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00014745223600783603, | |
| "grad_norm": 0.04057418555021286, | |
| "learning_rate": 7e-05, | |
| "loss": 10.3763, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0001685168411518126, | |
| "grad_norm": 0.03403380885720253, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3768, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0001895814462957892, | |
| "grad_norm": 0.0315258726477623, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3756, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001895814462957892, | |
| "eval_loss": 10.37730598449707, | |
| "eval_runtime": 326.3329, | |
| "eval_samples_per_second": 122.507, | |
| "eval_steps_per_second": 15.316, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00021064605143976577, | |
| "grad_norm": 0.04213544726371765, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3773, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00023171065658374233, | |
| "grad_norm": 0.03319665044546127, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 10.377, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00025277526172771893, | |
| "grad_norm": 0.03507379814982414, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 10.3762, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00027383986687169547, | |
| "grad_norm": 0.038384709507226944, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 10.379, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00029490447201567207, | |
| "grad_norm": 0.03694895654916763, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 10.3775, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00031596907715964866, | |
| "grad_norm": 0.03095310926437378, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.3755, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0003370336823036252, | |
| "grad_norm": 0.039225611835718155, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 10.3762, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0003580982874476018, | |
| "grad_norm": 0.036280952394008636, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 10.3766, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0003791628925915784, | |
| "grad_norm": 0.03579021990299225, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 10.3789, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0003791628925915784, | |
| "eval_loss": 10.376466751098633, | |
| "eval_runtime": 326.5405, | |
| "eval_samples_per_second": 122.429, | |
| "eval_steps_per_second": 15.306, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00040022749773555494, | |
| "grad_norm": 0.0345304012298584, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 10.3765, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00042129210287953153, | |
| "grad_norm": 0.04037633165717125, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.3748, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00044235670802350807, | |
| "grad_norm": 0.03361587971448898, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 10.376, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00046342131316748467, | |
| "grad_norm": 0.03614883869886398, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 10.3734, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.00048448591831146126, | |
| "grad_norm": 0.04295242205262184, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 10.3764, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0005055505234554379, | |
| "grad_norm": 0.04079096391797066, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 10.3732, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0005266151285994145, | |
| "grad_norm": 0.03456183150410652, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3755, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0005476797337433909, | |
| "grad_norm": 0.05067078769207001, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 10.3736, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0005687443388873675, | |
| "grad_norm": 0.03656363859772682, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 10.375, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0005687443388873675, | |
| "eval_loss": 10.375572204589844, | |
| "eval_runtime": 325.6996, | |
| "eval_samples_per_second": 122.745, | |
| "eval_steps_per_second": 15.345, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0005898089440313441, | |
| "grad_norm": 0.03712327778339386, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.3759, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0006108735491753207, | |
| "grad_norm": 0.04191397503018379, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 10.3776, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0006319381543192973, | |
| "grad_norm": 0.040405046194791794, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 10.3771, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0006530027594632738, | |
| "grad_norm": 0.04103453829884529, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 10.3751, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0006740673646072504, | |
| "grad_norm": 0.043744977563619614, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 10.3738, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.000695131969751227, | |
| "grad_norm": 0.041353847831487656, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 10.3742, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0007161965748952036, | |
| "grad_norm": 0.041590310633182526, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 10.3747, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0007372611800391802, | |
| "grad_norm": 0.042141202837228775, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 10.3763, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0007583257851831568, | |
| "grad_norm": 0.051582399755716324, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 10.3748, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0007583257851831568, | |
| "eval_loss": 10.374592781066895, | |
| "eval_runtime": 326.5386, | |
| "eval_samples_per_second": 122.43, | |
| "eval_steps_per_second": 15.306, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0007793903903271333, | |
| "grad_norm": 0.03906949236989021, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 10.3753, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0008004549954711099, | |
| "grad_norm": 0.04390184208750725, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 10.373, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0008215196006150865, | |
| "grad_norm": 0.04439748823642731, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 10.3749, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0008425842057590631, | |
| "grad_norm": 0.05099000036716461, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.375, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0008636488109030397, | |
| "grad_norm": 0.04918903857469559, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 10.3728, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0008847134160470161, | |
| "grad_norm": 0.05172858387231827, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 10.374, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0009057780211909927, | |
| "grad_norm": 0.05202887952327728, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 10.3728, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0009268426263349693, | |
| "grad_norm": 0.06054721027612686, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 10.3731, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0009479072314789459, | |
| "grad_norm": 0.05004347860813141, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 10.3759, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0009479072314789459, | |
| "eval_loss": 10.37352180480957, | |
| "eval_runtime": 326.6722, | |
| "eval_samples_per_second": 122.38, | |
| "eval_steps_per_second": 15.3, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0009689718366229225, | |
| "grad_norm": 0.04989779740571976, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 10.3752, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.000990036441766899, | |
| "grad_norm": 0.05517362803220749, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 10.3756, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0010111010469108757, | |
| "grad_norm": 0.05383509770035744, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 10.3726, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0010321656520548522, | |
| "grad_norm": 0.06373439729213715, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 10.3715, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.001053230257198829, | |
| "grad_norm": 0.055983684957027435, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 10.3733, | |
| "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": 2824332115968.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |