{ "best_metric": 0.2419588714838028, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.2588159171789065, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00517631834357813, "grad_norm": 0.10441477596759796, "learning_rate": 5e-05, "loss": 0.3731, "step": 1 }, { "epoch": 0.00517631834357813, "eval_loss": 0.6422037482261658, "eval_runtime": 1.4353, "eval_samples_per_second": 34.835, "eval_steps_per_second": 9.057, "step": 1 }, { "epoch": 0.01035263668715626, "grad_norm": 0.15498633682727814, "learning_rate": 0.0001, "loss": 0.4683, "step": 2 }, { "epoch": 0.01552895503073439, "grad_norm": 0.1770079880952835, "learning_rate": 9.990365154573717e-05, "loss": 0.4781, "step": 3 }, { "epoch": 0.02070527337431252, "grad_norm": 0.19880133867263794, "learning_rate": 9.961501876182148e-05, "loss": 0.4833, "step": 4 }, { "epoch": 0.02588159171789065, "grad_norm": 0.18236511945724487, "learning_rate": 9.913533761814537e-05, "loss": 0.4709, "step": 5 }, { "epoch": 0.03105791006146878, "grad_norm": 0.20692075788974762, "learning_rate": 9.846666218300807e-05, "loss": 0.4191, "step": 6 }, { "epoch": 0.03623422840504691, "grad_norm": 0.20755748450756073, "learning_rate": 9.761185582727977e-05, "loss": 0.4195, "step": 7 }, { "epoch": 0.04141054674862504, "grad_norm": 0.2131480723619461, "learning_rate": 9.657457896300791e-05, "loss": 0.4003, "step": 8 }, { "epoch": 0.046586865092203174, "grad_norm": 0.24724173545837402, "learning_rate": 9.535927336897098e-05, "loss": 0.3517, "step": 9 }, { "epoch": 0.0517631834357813, "grad_norm": 0.23559781908988953, "learning_rate": 9.397114317029975e-05, "loss": 0.3655, "step": 10 }, { "epoch": 0.05693950177935943, "grad_norm": 0.20029279589653015, "learning_rate": 9.241613255361455e-05, "loss": 0.3184, "step": 11 }, { "epoch": 0.06211582012293756, "grad_norm": 0.19484396278858185, "learning_rate": 9.070090031310558e-05, "loss": 0.3077, "step": 12 }, { "epoch": 0.06729213846651569, "grad_norm": 0.16507861018180847, "learning_rate": 8.883279133655399e-05, "loss": 0.2704, "step": 13 }, { "epoch": 0.07246845681009383, "grad_norm": 0.2216939777135849, "learning_rate": 8.681980515339464e-05, "loss": 0.2921, "step": 14 }, { "epoch": 0.07764477515367195, "grad_norm": 0.1648370772600174, "learning_rate": 8.467056167950311e-05, "loss": 0.2548, "step": 15 }, { "epoch": 0.08282109349725009, "grad_norm": 0.11311717331409454, "learning_rate": 8.239426430539243e-05, "loss": 0.2373, "step": 16 }, { "epoch": 0.08799741184082821, "grad_norm": 0.12028825283050537, "learning_rate": 8.000066048588211e-05, "loss": 0.2689, "step": 17 }, { "epoch": 0.09317373018440635, "grad_norm": 0.13627468049526215, "learning_rate": 7.75e-05, "loss": 0.2788, "step": 18 }, { "epoch": 0.09835004852798447, "grad_norm": 0.13786321878433228, "learning_rate": 7.490299105985507e-05, "loss": 0.2533, "step": 19 }, { "epoch": 0.1035263668715626, "grad_norm": 0.12153755873441696, "learning_rate": 7.222075445642904e-05, "loss": 0.2666, "step": 20 }, { "epoch": 0.10870268521514073, "grad_norm": 0.12565958499908447, "learning_rate": 6.946477593864228e-05, "loss": 0.2487, "step": 21 }, { "epoch": 0.11387900355871886, "grad_norm": 0.11313856393098831, "learning_rate": 6.664685702961344e-05, "loss": 0.2506, "step": 22 }, { "epoch": 0.11905532190229699, "grad_norm": 0.1219792291522026, "learning_rate": 6.377906449072578e-05, "loss": 0.2349, "step": 23 }, { "epoch": 0.12423164024587512, "grad_norm": 0.1459670513868332, "learning_rate": 6.087367864990233e-05, "loss": 0.2708, "step": 24 }, { "epoch": 0.12940795858945325, "grad_norm": 0.17884299159049988, "learning_rate": 5.794314081535644e-05, "loss": 0.2713, "step": 25 }, { "epoch": 0.12940795858945325, "eval_loss": 0.252530038356781, "eval_runtime": 1.4384, "eval_samples_per_second": 34.761, "eval_steps_per_second": 9.038, "step": 25 }, { "epoch": 0.13458427693303138, "grad_norm": 0.06610764563083649, "learning_rate": 5.500000000000001e-05, "loss": 0.2569, "step": 26 }, { "epoch": 0.1397605952766095, "grad_norm": 0.0721898227930069, "learning_rate": 5.205685918464356e-05, "loss": 0.2493, "step": 27 }, { "epoch": 0.14493691362018765, "grad_norm": 0.07561353594064713, "learning_rate": 4.912632135009769e-05, "loss": 0.2764, "step": 28 }, { "epoch": 0.15011323196376578, "grad_norm": 0.06619886308908463, "learning_rate": 4.6220935509274235e-05, "loss": 0.2175, "step": 29 }, { "epoch": 0.1552895503073439, "grad_norm": 0.07458724081516266, "learning_rate": 4.3353142970386564e-05, "loss": 0.2708, "step": 30 }, { "epoch": 0.16046586865092202, "grad_norm": 0.0770750567317009, "learning_rate": 4.053522406135775e-05, "loss": 0.2586, "step": 31 }, { "epoch": 0.16564218699450017, "grad_norm": 0.07303706556558609, "learning_rate": 3.777924554357096e-05, "loss": 0.2312, "step": 32 }, { "epoch": 0.1708185053380783, "grad_norm": 0.07124622166156769, "learning_rate": 3.509700894014496e-05, "loss": 0.2386, "step": 33 }, { "epoch": 0.17599482368165642, "grad_norm": 0.07879437506198883, "learning_rate": 3.250000000000001e-05, "loss": 0.2524, "step": 34 }, { "epoch": 0.18117114202523454, "grad_norm": 0.08590403199195862, "learning_rate": 2.9999339514117912e-05, "loss": 0.2526, "step": 35 }, { "epoch": 0.1863474603688127, "grad_norm": 0.08869822323322296, "learning_rate": 2.760573569460757e-05, "loss": 0.2401, "step": 36 }, { "epoch": 0.19152377871239082, "grad_norm": 0.09655508399009705, "learning_rate": 2.53294383204969e-05, "loss": 0.2486, "step": 37 }, { "epoch": 0.19670009705596894, "grad_norm": 0.042593903839588165, "learning_rate": 2.3180194846605367e-05, "loss": 0.2101, "step": 38 }, { "epoch": 0.20187641539954707, "grad_norm": 0.05090802162885666, "learning_rate": 2.1167208663446025e-05, "loss": 0.262, "step": 39 }, { "epoch": 0.2070527337431252, "grad_norm": 0.05375056713819504, "learning_rate": 1.9299099686894423e-05, "loss": 0.2499, "step": 40 }, { "epoch": 0.21222905208670334, "grad_norm": 0.05331680178642273, "learning_rate": 1.758386744638546e-05, "loss": 0.223, "step": 41 }, { "epoch": 0.21740537043028146, "grad_norm": 0.061501894146203995, "learning_rate": 1.602885682970026e-05, "loss": 0.2438, "step": 42 }, { "epoch": 0.2225816887738596, "grad_norm": 0.0702476054430008, "learning_rate": 1.464072663102903e-05, "loss": 0.247, "step": 43 }, { "epoch": 0.2277580071174377, "grad_norm": 0.06131530553102493, "learning_rate": 1.3425421036992098e-05, "loss": 0.2211, "step": 44 }, { "epoch": 0.23293432546101586, "grad_norm": 0.066093310713768, "learning_rate": 1.2388144172720251e-05, "loss": 0.2444, "step": 45 }, { "epoch": 0.23811064380459399, "grad_norm": 0.06885978579521179, "learning_rate": 1.1533337816991932e-05, "loss": 0.2602, "step": 46 }, { "epoch": 0.2432869621481721, "grad_norm": 0.07169124484062195, "learning_rate": 1.0864662381854632e-05, "loss": 0.2462, "step": 47 }, { "epoch": 0.24846328049175023, "grad_norm": 0.08826154470443726, "learning_rate": 1.0384981238178534e-05, "loss": 0.2691, "step": 48 }, { "epoch": 0.2536395988353284, "grad_norm": 0.08812335878610611, "learning_rate": 1.0096348454262845e-05, "loss": 0.2274, "step": 49 }, { "epoch": 0.2588159171789065, "grad_norm": 0.11969379335641861, "learning_rate": 1e-05, "loss": 0.2547, "step": 50 }, { "epoch": 0.2588159171789065, "eval_loss": 0.2419588714838028, "eval_runtime": 1.4385, "eval_samples_per_second": 34.758, "eval_steps_per_second": 9.037, "step": 50 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 25, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 1, "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": 5.6275728548338074e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }