| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.008466603951082, | |
| "eval_steps": 50, | |
| "global_step": 67, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015051740357478834, | |
| "grad_norm": 0.9344162940979004, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6705, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015051740357478834, | |
| "eval_loss": 0.6895620226860046, | |
| "eval_runtime": 10.3955, | |
| "eval_samples_per_second": 21.548, | |
| "eval_steps_per_second": 5.387, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.030103480714957668, | |
| "grad_norm": 0.9302381873130798, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6946, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.045155221072436504, | |
| "grad_norm": 0.9359163045883179, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7409, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.060206961429915336, | |
| "grad_norm": 0.9642816781997681, | |
| "learning_rate": 8e-05, | |
| "loss": 0.6928, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07525870178739416, | |
| "grad_norm": 0.8229894042015076, | |
| "learning_rate": 0.0001, | |
| "loss": 0.577, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09031044214487301, | |
| "grad_norm": 0.4650634527206421, | |
| "learning_rate": 0.00012, | |
| "loss": 0.5228, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10536218250235184, | |
| "grad_norm": 0.4150318205356598, | |
| "learning_rate": 0.00014, | |
| "loss": 0.4753, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.12041392285983067, | |
| "grad_norm": 0.5093539357185364, | |
| "learning_rate": 0.00016, | |
| "loss": 0.505, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1354656632173095, | |
| "grad_norm": 0.4901506006717682, | |
| "learning_rate": 0.00018, | |
| "loss": 0.4358, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.15051740357478832, | |
| "grad_norm": 0.3130745589733124, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4193, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16556914393226718, | |
| "grad_norm": 0.4450761675834656, | |
| "learning_rate": 0.00019984815164333163, | |
| "loss": 0.3821, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.18062088428974601, | |
| "grad_norm": 0.44579023122787476, | |
| "learning_rate": 0.00019939306773179497, | |
| "loss": 0.3957, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.19567262464722485, | |
| "grad_norm": 0.3342147469520569, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 0.3776, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.21072436500470368, | |
| "grad_norm": 0.3169708549976349, | |
| "learning_rate": 0.00019757963826274357, | |
| "loss": 0.4155, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2257761053621825, | |
| "grad_norm": 0.3119909167289734, | |
| "learning_rate": 0.00019622680003092503, | |
| "loss": 0.404, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.24082784571966134, | |
| "grad_norm": 0.2754630148410797, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 0.3648, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2558795860771402, | |
| "grad_norm": 0.3073170781135559, | |
| "learning_rate": 0.00019264940672148018, | |
| "loss": 0.3565, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.270931326434619, | |
| "grad_norm": 0.2857714295387268, | |
| "learning_rate": 0.00019043571606975777, | |
| "loss": 0.3717, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.28598306679209784, | |
| "grad_norm": 0.25880104303359985, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 0.3576, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.30103480714957664, | |
| "grad_norm": 0.2680279314517975, | |
| "learning_rate": 0.00018519194088383273, | |
| "loss": 0.3916, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3160865475070555, | |
| "grad_norm": 0.3286673426628113, | |
| "learning_rate": 0.0001821777815225245, | |
| "loss": 0.4095, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.33113828786453436, | |
| "grad_norm": 0.2846011817455292, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 0.3653, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.34619002822201317, | |
| "grad_norm": 0.2800520360469818, | |
| "learning_rate": 0.00017541066097768963, | |
| "loss": 0.3917, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.36124176857949203, | |
| "grad_norm": 0.26333191990852356, | |
| "learning_rate": 0.00017167825131684513, | |
| "loss": 0.3782, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.37629350893697083, | |
| "grad_norm": 0.2338825762271881, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 0.3709, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3913452492944497, | |
| "grad_norm": 0.23630400002002716, | |
| "learning_rate": 0.00016357237482099684, | |
| "loss": 0.3753, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4063969896519285, | |
| "grad_norm": 0.22607026994228363, | |
| "learning_rate": 0.00015922352526649803, | |
| "loss": 0.356, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.42144873000940736, | |
| "grad_norm": 0.23991024494171143, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 0.3531, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.43650047036688616, | |
| "grad_norm": 0.2309068888425827, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.377, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.451552210724365, | |
| "grad_norm": 0.27483415603637695, | |
| "learning_rate": 0.00014515333583108896, | |
| "loss": 0.3769, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4666039510818438, | |
| "grad_norm": 0.253368616104126, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 0.3579, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4816556914393227, | |
| "grad_norm": 0.2460198998451233, | |
| "learning_rate": 0.00013506375551927547, | |
| "loss": 0.3424, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4967074317968015, | |
| "grad_norm": 0.24006766080856323, | |
| "learning_rate": 0.00012985148110016947, | |
| "loss": 0.4105, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5117591721542804, | |
| "grad_norm": 0.242473304271698, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 0.3545, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5268109125117592, | |
| "grad_norm": 0.22222432494163513, | |
| "learning_rate": 0.00011917106319237386, | |
| "loss": 0.3626, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.541862652869238, | |
| "grad_norm": 0.2172698825597763, | |
| "learning_rate": 0.00011373535578184082, | |
| "loss": 0.3121, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5569143932267169, | |
| "grad_norm": 0.19818319380283356, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 0.345, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5719661335841957, | |
| "grad_norm": 0.23813501000404358, | |
| "learning_rate": 0.00010275543423681621, | |
| "loss": 0.3227, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5870178739416745, | |
| "grad_norm": 0.22211886942386627, | |
| "learning_rate": 9.724456576318381e-05, | |
| "loss": 0.3428, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6020696142991533, | |
| "grad_norm": 0.20863519608974457, | |
| "learning_rate": 9.174206545276677e-05, | |
| "loss": 0.3357, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6171213546566322, | |
| "grad_norm": 0.24819327890872955, | |
| "learning_rate": 8.626464421815919e-05, | |
| "loss": 0.3799, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.632173095014111, | |
| "grad_norm": 0.2553349435329437, | |
| "learning_rate": 8.082893680762619e-05, | |
| "loss": 0.3727, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6472248353715898, | |
| "grad_norm": 0.21132054924964905, | |
| "learning_rate": 7.54514512859201e-05, | |
| "loss": 0.3465, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6622765757290687, | |
| "grad_norm": 0.24369095265865326, | |
| "learning_rate": 7.014851889983057e-05, | |
| "loss": 0.3558, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6773283160865475, | |
| "grad_norm": 0.2254449874162674, | |
| "learning_rate": 6.493624448072457e-05, | |
| "loss": 0.3473, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6923800564440263, | |
| "grad_norm": 0.2430431842803955, | |
| "learning_rate": 5.983045753470308e-05, | |
| "loss": 0.3568, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7074317968015051, | |
| "grad_norm": 0.22099405527114868, | |
| "learning_rate": 5.484666416891109e-05, | |
| "loss": 0.3572, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7224835371589841, | |
| "grad_norm": 0.22853314876556396, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.3486, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7375352775164629, | |
| "grad_norm": 0.23912452161312103, | |
| "learning_rate": 4.530518418775733e-05, | |
| "loss": 0.3443, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7525870178739417, | |
| "grad_norm": 0.2265036553144455, | |
| "learning_rate": 4.077647473350201e-05, | |
| "loss": 0.3062, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7525870178739417, | |
| "eval_loss": 0.3498118817806244, | |
| "eval_runtime": 10.5271, | |
| "eval_samples_per_second": 21.278, | |
| "eval_steps_per_second": 5.32, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7676387582314205, | |
| "grad_norm": 0.23014026880264282, | |
| "learning_rate": 3.642762517900322e-05, | |
| "loss": 0.3562, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.7826904985888994, | |
| "grad_norm": 0.2177976369857788, | |
| "learning_rate": 3.227184283742591e-05, | |
| "loss": 0.3473, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.7977422389463782, | |
| "grad_norm": 0.22603270411491394, | |
| "learning_rate": 2.8321748683154893e-05, | |
| "loss": 0.3505, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.812793979303857, | |
| "grad_norm": 0.22148269414901733, | |
| "learning_rate": 2.4589339022310386e-05, | |
| "loss": 0.332, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.8278457196613358, | |
| "grad_norm": 0.2047235518693924, | |
| "learning_rate": 2.1085949060360654e-05, | |
| "loss": 0.3512, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.8428974600188147, | |
| "grad_norm": 0.21254387497901917, | |
| "learning_rate": 1.7822218477475494e-05, | |
| "loss": 0.3424, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.8579492003762935, | |
| "grad_norm": 0.21842923760414124, | |
| "learning_rate": 1.4808059116167305e-05, | |
| "loss": 0.3436, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.8730009407337723, | |
| "grad_norm": 0.22964705526828766, | |
| "learning_rate": 1.2052624879351104e-05, | |
| "loss": 0.3484, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.8880526810912511, | |
| "grad_norm": 0.2156173586845398, | |
| "learning_rate": 9.564283930242257e-06, | |
| "loss": 0.3396, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.90310442144873, | |
| "grad_norm": 0.21700626611709595, | |
| "learning_rate": 7.350593278519824e-06, | |
| "loss": 0.3249, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9181561618062088, | |
| "grad_norm": 0.2113395631313324, | |
| "learning_rate": 5.418275829936537e-06, | |
| "loss": 0.3659, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.9332079021636877, | |
| "grad_norm": 0.2139684408903122, | |
| "learning_rate": 3.7731999690749585e-06, | |
| "loss": 0.3683, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.9482596425211665, | |
| "grad_norm": 0.22140838205814362, | |
| "learning_rate": 2.420361737256438e-06, | |
| "loss": 0.3689, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.9633113828786454, | |
| "grad_norm": 0.21749098598957062, | |
| "learning_rate": 1.3638696597277679e-06, | |
| "loss": 0.3842, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.9783631232361242, | |
| "grad_norm": 0.2486245036125183, | |
| "learning_rate": 6.069322682050516e-07, | |
| "loss": 0.3889, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.993414863593603, | |
| "grad_norm": 0.22336921095848083, | |
| "learning_rate": 1.518483566683826e-07, | |
| "loss": 0.3572, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.008466603951082, | |
| "grad_norm": 0.3670308291912079, | |
| "learning_rate": 0.0, | |
| "loss": 0.4966, | |
| "step": 67 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 67, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 7.389133837801882e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |