{ "best_metric": 6.884387969970703, "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": 0.2808712124824524, "learning_rate": 5e-05, "loss": 6.9367, "step": 1 }, { "epoch": 0.004501336334224223, "eval_loss": 6.9341044425964355, "eval_runtime": 0.1634, "eval_samples_per_second": 305.927, "eval_steps_per_second": 79.541, "step": 1 }, { "epoch": 0.009002672668448446, "grad_norm": 0.26504793763160706, "learning_rate": 0.0001, "loss": 6.9358, "step": 2 }, { "epoch": 0.013504009002672668, "grad_norm": 0.26658204197883606, "learning_rate": 9.990365154573717e-05, "loss": 6.9353, "step": 3 }, { "epoch": 0.01800534533689689, "grad_norm": 0.27592623233795166, "learning_rate": 9.961501876182148e-05, "loss": 6.9325, "step": 4 }, { "epoch": 0.022506681671121114, "grad_norm": 0.26554349064826965, "learning_rate": 9.913533761814537e-05, "loss": 6.9318, "step": 5 }, { "epoch": 0.027008018005345337, "grad_norm": 0.2666162848472595, "learning_rate": 9.846666218300807e-05, "loss": 6.9288, "step": 6 }, { "epoch": 0.031509354339569556, "grad_norm": 0.26951131224632263, "learning_rate": 9.761185582727977e-05, "loss": 6.9282, "step": 7 }, { "epoch": 0.03601069067379378, "grad_norm": 0.26709139347076416, "learning_rate": 9.657457896300791e-05, "loss": 6.9263, "step": 8 }, { "epoch": 0.040512027008018, "grad_norm": 0.2755928039550781, "learning_rate": 9.535927336897098e-05, "loss": 6.9234, "step": 9 }, { "epoch": 0.04501336334224223, "grad_norm": 0.2812337577342987, "learning_rate": 9.397114317029975e-05, "loss": 6.9213, "step": 10 }, { "epoch": 0.04951469967646645, "grad_norm": 0.2759346067905426, "learning_rate": 9.241613255361455e-05, "loss": 6.9216, "step": 11 }, { "epoch": 0.054016036010690674, "grad_norm": 0.3198561370372772, "learning_rate": 9.070090031310558e-05, "loss": 6.9133, "step": 12 }, { "epoch": 0.05851737234491489, "grad_norm": 0.28667303919792175, "learning_rate": 8.883279133655399e-05, "loss": 6.9182, "step": 13 }, { "epoch": 0.06301870867913911, "grad_norm": 0.2683602273464203, "learning_rate": 8.681980515339464e-05, "loss": 6.9177, "step": 14 }, { "epoch": 0.06752004501336334, "grad_norm": 0.2684856951236725, "learning_rate": 8.467056167950311e-05, "loss": 6.9157, "step": 15 }, { "epoch": 0.07202138134758757, "grad_norm": 0.2700405716896057, "learning_rate": 8.239426430539243e-05, "loss": 6.9151, "step": 16 }, { "epoch": 0.07652271768181179, "grad_norm": 0.28459614515304565, "learning_rate": 8.000066048588211e-05, "loss": 6.9101, "step": 17 }, { "epoch": 0.081024054016036, "grad_norm": 0.28437161445617676, "learning_rate": 7.75e-05, "loss": 6.9089, "step": 18 }, { "epoch": 0.08552539035026023, "grad_norm": 0.28443124890327454, "learning_rate": 7.490299105985507e-05, "loss": 6.9082, "step": 19 }, { "epoch": 0.09002672668448446, "grad_norm": 0.2778397500514984, "learning_rate": 7.222075445642904e-05, "loss": 6.9079, "step": 20 }, { "epoch": 0.09452806301870868, "grad_norm": 0.2845655083656311, "learning_rate": 6.946477593864228e-05, "loss": 6.9051, "step": 21 }, { "epoch": 0.0990293993529329, "grad_norm": 0.2921813726425171, "learning_rate": 6.664685702961344e-05, "loss": 6.9022, "step": 22 }, { "epoch": 0.10353073568715712, "grad_norm": 0.28363725543022156, "learning_rate": 6.377906449072578e-05, "loss": 6.9022, "step": 23 }, { "epoch": 0.10803207202138135, "grad_norm": 0.29650917649269104, "learning_rate": 6.087367864990233e-05, "loss": 6.898, "step": 24 }, { "epoch": 0.11253340835560557, "grad_norm": 0.33996957540512085, "learning_rate": 5.794314081535644e-05, "loss": 6.892, "step": 25 }, { "epoch": 0.11253340835560557, "eval_loss": 6.8990583419799805, "eval_runtime": 0.1636, "eval_samples_per_second": 305.639, "eval_steps_per_second": 79.466, "step": 25 }, { "epoch": 0.11703474468982979, "grad_norm": 0.3027767539024353, "learning_rate": 5.500000000000001e-05, "loss": 6.9021, "step": 26 }, { "epoch": 0.12153608102405401, "grad_norm": 0.2898428738117218, "learning_rate": 5.205685918464356e-05, "loss": 6.8995, "step": 27 }, { "epoch": 0.12603741735827823, "grad_norm": 0.27990737557411194, "learning_rate": 4.912632135009769e-05, "loss": 6.9008, "step": 28 }, { "epoch": 0.13053875369250245, "grad_norm": 0.29302507638931274, "learning_rate": 4.6220935509274235e-05, "loss": 6.8963, "step": 29 }, { "epoch": 0.13504009002672668, "grad_norm": 0.2960253655910492, "learning_rate": 4.3353142970386564e-05, "loss": 6.8934, "step": 30 }, { "epoch": 0.1395414263609509, "grad_norm": 0.2894373834133148, "learning_rate": 4.053522406135775e-05, "loss": 6.8945, "step": 31 }, { "epoch": 0.14404276269517513, "grad_norm": 0.29182955622673035, "learning_rate": 3.777924554357096e-05, "loss": 6.8926, "step": 32 }, { "epoch": 0.14854409902939936, "grad_norm": 0.29192373156547546, "learning_rate": 3.509700894014496e-05, "loss": 6.8918, "step": 33 }, { "epoch": 0.15304543536362358, "grad_norm": 0.2958221733570099, "learning_rate": 3.250000000000001e-05, "loss": 6.89, "step": 34 }, { "epoch": 0.1575467716978478, "grad_norm": 0.29976916313171387, "learning_rate": 2.9999339514117912e-05, "loss": 6.8893, "step": 35 }, { "epoch": 0.162048108032072, "grad_norm": 0.28821298480033875, "learning_rate": 2.760573569460757e-05, "loss": 6.8906, "step": 36 }, { "epoch": 0.16654944436629623, "grad_norm": 0.32392418384552, "learning_rate": 2.53294383204969e-05, "loss": 6.885, "step": 37 }, { "epoch": 0.17105078070052046, "grad_norm": 0.31561553478240967, "learning_rate": 2.3180194846605367e-05, "loss": 6.89, "step": 38 }, { "epoch": 0.1755521170347447, "grad_norm": 0.2910025417804718, "learning_rate": 2.1167208663446025e-05, "loss": 6.8909, "step": 39 }, { "epoch": 0.1800534533689689, "grad_norm": 0.28736042976379395, "learning_rate": 1.9299099686894423e-05, "loss": 6.8916, "step": 40 }, { "epoch": 0.18455478970319314, "grad_norm": 0.29170575737953186, "learning_rate": 1.758386744638546e-05, "loss": 6.8888, "step": 41 }, { "epoch": 0.18905612603741737, "grad_norm": 0.2956409752368927, "learning_rate": 1.602885682970026e-05, "loss": 6.8871, "step": 42 }, { "epoch": 0.1935574623716416, "grad_norm": 0.3005565106868744, "learning_rate": 1.464072663102903e-05, "loss": 6.8849, "step": 43 }, { "epoch": 0.1980587987058658, "grad_norm": 0.29543253779411316, "learning_rate": 1.3425421036992098e-05, "loss": 6.8857, "step": 44 }, { "epoch": 0.20256013504009002, "grad_norm": 0.288479208946228, "learning_rate": 1.2388144172720251e-05, "loss": 6.8869, "step": 45 }, { "epoch": 0.20706147137431424, "grad_norm": 0.2988308072090149, "learning_rate": 1.1533337816991932e-05, "loss": 6.8835, "step": 46 }, { "epoch": 0.21156280770853847, "grad_norm": 0.29880666732788086, "learning_rate": 1.0864662381854632e-05, "loss": 6.883, "step": 47 }, { "epoch": 0.2160641440427627, "grad_norm": 0.29033946990966797, "learning_rate": 1.0384981238178534e-05, "loss": 6.8861, "step": 48 }, { "epoch": 0.22056548037698692, "grad_norm": 0.2861062288284302, "learning_rate": 1.0096348454262845e-05, "loss": 6.8875, "step": 49 }, { "epoch": 0.22506681671121115, "grad_norm": 0.3452097773551941, "learning_rate": 1e-05, "loss": 6.8749, "step": 50 }, { "epoch": 0.22506681671121115, "eval_loss": 6.884387969970703, "eval_runtime": 0.1671, "eval_samples_per_second": 299.175, "eval_steps_per_second": 77.785, "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 }