{ "best_metric": 6.882252216339111, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.22506681671121115, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004501336334224223, "grad_norm": 0.29213276505470276, "learning_rate": 5e-05, "loss": 6.9366, "step": 1 }, { "epoch": 0.004501336334224223, "eval_loss": 6.934077262878418, "eval_runtime": 0.1042, "eval_samples_per_second": 479.955, "eval_steps_per_second": 124.788, "step": 1 }, { "epoch": 0.009002672668448446, "grad_norm": 0.271996408700943, "learning_rate": 0.0001, "loss": 6.9357, "step": 2 }, { "epoch": 0.013504009002672668, "grad_norm": 0.27347683906555176, "learning_rate": 9.990365154573717e-05, "loss": 6.9353, "step": 3 }, { "epoch": 0.01800534533689689, "grad_norm": 0.27974188327789307, "learning_rate": 9.961501876182148e-05, "loss": 6.9325, "step": 4 }, { "epoch": 0.022506681671121114, "grad_norm": 0.2688376307487488, "learning_rate": 9.913533761814537e-05, "loss": 6.9317, "step": 5 }, { "epoch": 0.027008018005345337, "grad_norm": 0.2703593969345093, "learning_rate": 9.846666218300807e-05, "loss": 6.9287, "step": 6 }, { "epoch": 0.031509354339569556, "grad_norm": 0.2745017111301422, "learning_rate": 9.761185582727977e-05, "loss": 6.928, "step": 7 }, { "epoch": 0.03601069067379378, "grad_norm": 0.2704656720161438, "learning_rate": 9.657457896300791e-05, "loss": 6.9261, "step": 8 }, { "epoch": 0.040512027008018, "grad_norm": 0.2788160741329193, "learning_rate": 9.535927336897098e-05, "loss": 6.9232, "step": 9 }, { "epoch": 0.04501336334224223, "grad_norm": 0.2839667797088623, "learning_rate": 9.397114317029975e-05, "loss": 6.9211, "step": 10 }, { "epoch": 0.04951469967646645, "grad_norm": 0.27735522389411926, "learning_rate": 9.241613255361455e-05, "loss": 6.9216, "step": 11 }, { "epoch": 0.054016036010690674, "grad_norm": 0.3209490180015564, "learning_rate": 9.070090031310558e-05, "loss": 6.9132, "step": 12 }, { "epoch": 0.05851737234491489, "grad_norm": 0.29935047030448914, "learning_rate": 8.883279133655399e-05, "loss": 6.9173, "step": 13 }, { "epoch": 0.06301870867913911, "grad_norm": 0.27763044834136963, "learning_rate": 8.681980515339464e-05, "loss": 6.917, "step": 14 }, { "epoch": 0.06752004501336334, "grad_norm": 0.27863582968711853, "learning_rate": 8.467056167950311e-05, "loss": 6.9149, "step": 15 }, { "epoch": 0.07202138134758757, "grad_norm": 0.27987152338027954, "learning_rate": 8.239426430539243e-05, "loss": 6.9143, "step": 16 }, { "epoch": 0.07652271768181179, "grad_norm": 0.2940329909324646, "learning_rate": 8.000066048588211e-05, "loss": 6.9093, "step": 17 }, { "epoch": 0.081024054016036, "grad_norm": 0.29365986585617065, "learning_rate": 7.75e-05, "loss": 6.9081, "step": 18 }, { "epoch": 0.08552539035026023, "grad_norm": 0.2938484847545624, "learning_rate": 7.490299105985507e-05, "loss": 6.9073, "step": 19 }, { "epoch": 0.09002672668448446, "grad_norm": 0.2871885895729065, "learning_rate": 7.222075445642904e-05, "loss": 6.9068, "step": 20 }, { "epoch": 0.09452806301870868, "grad_norm": 0.2927285134792328, "learning_rate": 6.946477593864228e-05, "loss": 6.9042, "step": 21 }, { "epoch": 0.0990293993529329, "grad_norm": 0.298091322183609, "learning_rate": 6.664685702961344e-05, "loss": 6.9014, "step": 22 }, { "epoch": 0.10353073568715712, "grad_norm": 0.29013997316360474, "learning_rate": 6.377906449072578e-05, "loss": 6.9014, "step": 23 }, { "epoch": 0.10803207202138135, "grad_norm": 0.3019247353076935, "learning_rate": 6.087367864990233e-05, "loss": 6.8972, "step": 24 }, { "epoch": 0.11253340835560557, "grad_norm": 0.343837171792984, "learning_rate": 5.794314081535644e-05, "loss": 6.8916, "step": 25 }, { "epoch": 0.11253340835560557, "eval_loss": 6.897491455078125, "eval_runtime": 0.1034, "eval_samples_per_second": 483.446, "eval_steps_per_second": 125.696, "step": 25 }, { "epoch": 0.11703474468982979, "grad_norm": 0.3195980191230774, "learning_rate": 5.500000000000001e-05, "loss": 6.8995, "step": 26 }, { "epoch": 0.12153608102405401, "grad_norm": 0.3027236759662628, "learning_rate": 5.205685918464356e-05, "loss": 6.8975, "step": 27 }, { "epoch": 0.12603741735827823, "grad_norm": 0.2920920252799988, "learning_rate": 4.912632135009769e-05, "loss": 6.8988, "step": 28 }, { "epoch": 0.13053875369250245, "grad_norm": 0.30486103892326355, "learning_rate": 4.6220935509274235e-05, "loss": 6.8943, "step": 29 }, { "epoch": 0.13504009002672668, "grad_norm": 0.3065364956855774, "learning_rate": 4.3353142970386564e-05, "loss": 6.8918, "step": 30 }, { "epoch": 0.1395414263609509, "grad_norm": 0.2986215353012085, "learning_rate": 4.053522406135775e-05, "loss": 6.8927, "step": 31 }, { "epoch": 0.14404276269517513, "grad_norm": 0.30123046040534973, "learning_rate": 3.777924554357096e-05, "loss": 6.8908, "step": 32 }, { "epoch": 0.14854409902939936, "grad_norm": 0.30109483003616333, "learning_rate": 3.509700894014496e-05, "loss": 6.89, "step": 33 }, { "epoch": 0.15304543536362358, "grad_norm": 0.3042573928833008, "learning_rate": 3.250000000000001e-05, "loss": 6.8882, "step": 34 }, { "epoch": 0.1575467716978478, "grad_norm": 0.30715158581733704, "learning_rate": 2.9999339514117912e-05, "loss": 6.8878, "step": 35 }, { "epoch": 0.162048108032072, "grad_norm": 0.2930234372615814, "learning_rate": 2.760573569460757e-05, "loss": 6.8894, "step": 36 }, { "epoch": 0.16654944436629623, "grad_norm": 0.32819417119026184, "learning_rate": 2.53294383204969e-05, "loss": 6.884, "step": 37 }, { "epoch": 0.17105078070052046, "grad_norm": 0.32585394382476807, "learning_rate": 2.3180194846605367e-05, "loss": 6.8866, "step": 38 }, { "epoch": 0.1755521170347447, "grad_norm": 0.2999441623687744, "learning_rate": 2.1167208663446025e-05, "loss": 6.8883, "step": 39 }, { "epoch": 0.1800534533689689, "grad_norm": 0.29603469371795654, "learning_rate": 1.9299099686894423e-05, "loss": 6.8892, "step": 40 }, { "epoch": 0.18455478970319314, "grad_norm": 0.30078619718551636, "learning_rate": 1.758386744638546e-05, "loss": 6.8862, "step": 41 }, { "epoch": 0.18905612603741737, "grad_norm": 0.302124947309494, "learning_rate": 1.602885682970026e-05, "loss": 6.8851, "step": 42 }, { "epoch": 0.1935574623716416, "grad_norm": 0.3070308268070221, "learning_rate": 1.464072663102903e-05, "loss": 6.8829, "step": 43 }, { "epoch": 0.1980587987058658, "grad_norm": 0.30131006240844727, "learning_rate": 1.3425421036992098e-05, "loss": 6.8836, "step": 44 }, { "epoch": 0.20256013504009002, "grad_norm": 0.29591667652130127, "learning_rate": 1.2388144172720251e-05, "loss": 6.8846, "step": 45 }, { "epoch": 0.20706147137431424, "grad_norm": 0.303593248128891, "learning_rate": 1.1533337816991932e-05, "loss": 6.8818, "step": 46 }, { "epoch": 0.21156280770853847, "grad_norm": 0.30206286907196045, "learning_rate": 1.0864662381854632e-05, "loss": 6.8815, "step": 47 }, { "epoch": 0.2160641440427627, "grad_norm": 0.29285162687301636, "learning_rate": 1.0384981238178534e-05, "loss": 6.8847, "step": 48 }, { "epoch": 0.22056548037698692, "grad_norm": 0.2894514799118042, "learning_rate": 1.0096348454262845e-05, "loss": 6.8859, "step": 49 }, { "epoch": 0.22506681671121115, "grad_norm": 0.34442582726478577, "learning_rate": 1e-05, "loss": 6.8742, "step": 50 }, { "epoch": 0.22506681671121115, "eval_loss": 6.882252216339111, "eval_runtime": 0.1038, "eval_samples_per_second": 481.558, "eval_steps_per_second": 125.205, "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": 11411914752000.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }