{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.02024906348081401, "eval_steps": 13, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00040498126961628026, "grad_norm": 0.016281457617878914, "learning_rate": 1e-05, "loss": 11.929, "step": 1 }, { "epoch": 0.00040498126961628026, "eval_loss": 11.929625511169434, "eval_runtime": 20.8534, "eval_samples_per_second": 199.44, "eval_steps_per_second": 99.744, "step": 1 }, { "epoch": 0.0008099625392325605, "grad_norm": 0.016497384756803513, "learning_rate": 2e-05, "loss": 11.9295, "step": 2 }, { "epoch": 0.0012149438088488408, "grad_norm": 0.014399677515029907, "learning_rate": 3e-05, "loss": 11.9307, "step": 3 }, { "epoch": 0.001619925078465121, "grad_norm": 0.012118221260607243, "learning_rate": 4e-05, "loss": 11.93, "step": 4 }, { "epoch": 0.0020249063480814013, "grad_norm": 0.014372492209076881, "learning_rate": 5e-05, "loss": 11.9299, "step": 5 }, { "epoch": 0.0024298876176976816, "grad_norm": 0.014841921627521515, "learning_rate": 6e-05, "loss": 11.929, "step": 6 }, { "epoch": 0.002834868887313962, "grad_norm": 0.013597904704511166, "learning_rate": 7e-05, "loss": 11.9283, "step": 7 }, { "epoch": 0.003239850156930242, "grad_norm": 0.016889022663235664, "learning_rate": 8e-05, "loss": 11.9291, "step": 8 }, { "epoch": 0.0036448314265465223, "grad_norm": 0.012072063982486725, "learning_rate": 9e-05, "loss": 11.9299, "step": 9 }, { "epoch": 0.004049812696162803, "grad_norm": 0.014724480919539928, "learning_rate": 0.0001, "loss": 11.9314, "step": 10 }, { "epoch": 0.004454793965779083, "grad_norm": 0.014864698983728886, "learning_rate": 9.98458666866564e-05, "loss": 11.9283, "step": 11 }, { "epoch": 0.004859775235395363, "grad_norm": 0.012745369225740433, "learning_rate": 9.938441702975689e-05, "loss": 11.9302, "step": 12 }, { "epoch": 0.005264756505011643, "grad_norm": 0.01918998919427395, "learning_rate": 9.861849601988383e-05, "loss": 11.9299, "step": 13 }, { "epoch": 0.005264756505011643, "eval_loss": 11.929468154907227, "eval_runtime": 7.0015, "eval_samples_per_second": 594.019, "eval_steps_per_second": 297.081, "step": 13 }, { "epoch": 0.005669737774627924, "grad_norm": 0.013973494991660118, "learning_rate": 9.755282581475769e-05, "loss": 11.9297, "step": 14 }, { "epoch": 0.006074719044244204, "grad_norm": 0.014227038249373436, "learning_rate": 9.619397662556435e-05, "loss": 11.9289, "step": 15 }, { "epoch": 0.006479700313860484, "grad_norm": 0.014232249930500984, "learning_rate": 9.45503262094184e-05, "loss": 11.9294, "step": 16 }, { "epoch": 0.0068846815834767644, "grad_norm": 0.01532355509698391, "learning_rate": 9.263200821770461e-05, "loss": 11.9282, "step": 17 }, { "epoch": 0.007289662853093045, "grad_norm": 0.01495895441621542, "learning_rate": 9.045084971874738e-05, "loss": 11.9276, "step": 18 }, { "epoch": 0.007694644122709325, "grad_norm": 0.012949861586093903, "learning_rate": 8.802029828000156e-05, "loss": 11.9292, "step": 19 }, { "epoch": 0.008099625392325605, "grad_norm": 0.015499262139201164, "learning_rate": 8.535533905932738e-05, "loss": 11.9285, "step": 20 }, { "epoch": 0.008504606661941885, "grad_norm": 0.016316721215844154, "learning_rate": 8.247240241650918e-05, "loss": 11.9294, "step": 21 }, { "epoch": 0.008909587931558166, "grad_norm": 0.01622353307902813, "learning_rate": 7.938926261462366e-05, "loss": 11.929, "step": 22 }, { "epoch": 0.009314569201174445, "grad_norm": 0.0137627013027668, "learning_rate": 7.612492823579745e-05, "loss": 11.9301, "step": 23 }, { "epoch": 0.009719550470790726, "grad_norm": 0.015497871674597263, "learning_rate": 7.269952498697734e-05, "loss": 11.9295, "step": 24 }, { "epoch": 0.010124531740407006, "grad_norm": 0.01868840865790844, "learning_rate": 6.91341716182545e-05, "loss": 11.9277, "step": 25 }, { "epoch": 0.010529513010023287, "grad_norm": 0.012535473331809044, "learning_rate": 6.545084971874738e-05, "loss": 11.9298, "step": 26 }, { "epoch": 0.010529513010023287, "eval_loss": 11.92922306060791, "eval_runtime": 7.0474, "eval_samples_per_second": 590.143, "eval_steps_per_second": 295.142, "step": 26 }, { "epoch": 0.010934494279639566, "grad_norm": 0.01646103709936142, "learning_rate": 6.167226819279528e-05, "loss": 11.9288, "step": 27 }, { "epoch": 0.011339475549255847, "grad_norm": 0.01632491685450077, "learning_rate": 5.782172325201155e-05, "loss": 11.9289, "step": 28 }, { "epoch": 0.011744456818872127, "grad_norm": 0.015698088333010674, "learning_rate": 5.392295478639225e-05, "loss": 11.929, "step": 29 }, { "epoch": 0.012149438088488408, "grad_norm": 0.016495509073138237, "learning_rate": 5e-05, "loss": 11.9298, "step": 30 }, { "epoch": 0.012554419358104687, "grad_norm": 0.016273178160190582, "learning_rate": 4.607704521360776e-05, "loss": 11.9295, "step": 31 }, { "epoch": 0.012959400627720968, "grad_norm": 0.015034040436148643, "learning_rate": 4.2178276747988446e-05, "loss": 11.9304, "step": 32 }, { "epoch": 0.013364381897337248, "grad_norm": 0.014879411086440086, "learning_rate": 3.832773180720475e-05, "loss": 11.9288, "step": 33 }, { "epoch": 0.013769363166953529, "grad_norm": 0.014941861853003502, "learning_rate": 3.4549150281252636e-05, "loss": 11.9293, "step": 34 }, { "epoch": 0.014174344436569808, "grad_norm": 0.01598219946026802, "learning_rate": 3.086582838174551e-05, "loss": 11.9287, "step": 35 }, { "epoch": 0.01457932570618609, "grad_norm": 0.015294226817786694, "learning_rate": 2.7300475013022663e-05, "loss": 11.9286, "step": 36 }, { "epoch": 0.014984306975802369, "grad_norm": 0.015234192833304405, "learning_rate": 2.3875071764202563e-05, "loss": 11.9291, "step": 37 }, { "epoch": 0.01538928824541865, "grad_norm": 0.016300296410918236, "learning_rate": 2.061073738537635e-05, "loss": 11.9293, "step": 38 }, { "epoch": 0.01579426951503493, "grad_norm": 0.015601075254380703, "learning_rate": 1.7527597583490822e-05, "loss": 11.9291, "step": 39 }, { "epoch": 0.01579426951503493, "eval_loss": 11.929096221923828, "eval_runtime": 7.0495, "eval_samples_per_second": 589.971, "eval_steps_per_second": 295.056, "step": 39 }, { "epoch": 0.01619925078465121, "grad_norm": 0.013766695745289326, "learning_rate": 1.4644660940672627e-05, "loss": 11.9299, "step": 40 }, { "epoch": 0.01660423205426749, "grad_norm": 0.019628174602985382, "learning_rate": 1.1979701719998453e-05, "loss": 11.9294, "step": 41 }, { "epoch": 0.01700921332388377, "grad_norm": 0.016885703429579735, "learning_rate": 9.549150281252633e-06, "loss": 11.9285, "step": 42 }, { "epoch": 0.017414194593500052, "grad_norm": 0.01529628038406372, "learning_rate": 7.367991782295391e-06, "loss": 11.9281, "step": 43 }, { "epoch": 0.01781917586311633, "grad_norm": 0.01732531376183033, "learning_rate": 5.449673790581611e-06, "loss": 11.9294, "step": 44 }, { "epoch": 0.01822415713273261, "grad_norm": 0.014228262938559055, "learning_rate": 3.8060233744356633e-06, "loss": 11.9297, "step": 45 }, { "epoch": 0.01862913840234889, "grad_norm": 0.017510289326310158, "learning_rate": 2.4471741852423237e-06, "loss": 11.9293, "step": 46 }, { "epoch": 0.019034119671965173, "grad_norm": 0.015506377443671227, "learning_rate": 1.3815039801161721e-06, "loss": 11.9295, "step": 47 }, { "epoch": 0.019439100941581453, "grad_norm": 0.016405014321208, "learning_rate": 6.15582970243117e-07, "loss": 11.9275, "step": 48 }, { "epoch": 0.019844082211197732, "grad_norm": 0.014786036685109138, "learning_rate": 1.5413331334360182e-07, "loss": 11.9295, "step": 49 }, { "epoch": 0.02024906348081401, "grad_norm": 0.016270695254206657, "learning_rate": 0.0, "loss": 11.929, "step": 50 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 23632281600.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }