| { | |
| "best_metric": 1.3384273052215576, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.027018811847748996, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005403762369549799, | |
| "grad_norm": 0.8042336702346802, | |
| "learning_rate": 5e-05, | |
| "loss": 1.297, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005403762369549799, | |
| "eval_loss": 2.17419171333313, | |
| "eval_runtime": 4.219, | |
| "eval_samples_per_second": 11.851, | |
| "eval_steps_per_second": 3.081, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010807524739099598, | |
| "grad_norm": 1.1598894596099854, | |
| "learning_rate": 0.0001, | |
| "loss": 1.583, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016211287108649397, | |
| "grad_norm": 1.079237461090088, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.5357, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0021615049478199196, | |
| "grad_norm": 0.9333255887031555, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.6001, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0027018811847748995, | |
| "grad_norm": 0.7734662294387817, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.5488, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0032422574217298794, | |
| "grad_norm": 1.0766327381134033, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.4086, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0037826336586848593, | |
| "grad_norm": 0.9116091132164001, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.3989, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004323009895639839, | |
| "grad_norm": 0.5602995157241821, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.3108, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004863386132594819, | |
| "grad_norm": 0.3873656392097473, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.3457, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005403762369549799, | |
| "grad_norm": 0.4487011432647705, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.4237, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0059441386065047785, | |
| "grad_norm": 0.5015619993209839, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.3125, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.006484514843459759, | |
| "grad_norm": 0.5078799724578857, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.397, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007024891080414738, | |
| "grad_norm": 0.3308199942111969, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.1429, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007565267317369719, | |
| "grad_norm": 0.347027063369751, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.2361, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008105643554324698, | |
| "grad_norm": 0.3196849822998047, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.2581, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008646019791279679, | |
| "grad_norm": 0.31211787462234497, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.2067, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.009186396028234659, | |
| "grad_norm": 0.3472338318824768, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.2871, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.009726772265189637, | |
| "grad_norm": 0.3617914617061615, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.2789, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010267148502144618, | |
| "grad_norm": 0.34249281883239746, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.308, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.010807524739099598, | |
| "grad_norm": 0.36734694242477417, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.2857, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011347900976054578, | |
| "grad_norm": 0.3690188229084015, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.3313, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.011888277213009557, | |
| "grad_norm": 0.365241676568985, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.332, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.012428653449964537, | |
| "grad_norm": 0.3784826695919037, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.365, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.012969029686919518, | |
| "grad_norm": 0.3792647123336792, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.3362, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.013509405923874498, | |
| "grad_norm": 0.4010039269924164, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.3102, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013509405923874498, | |
| "eval_loss": 1.3463994264602661, | |
| "eval_runtime": 3.874, | |
| "eval_samples_per_second": 12.907, | |
| "eval_steps_per_second": 3.356, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014049782160829477, | |
| "grad_norm": 0.21748431026935577, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.2172, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.014590158397784457, | |
| "grad_norm": 0.29222214221954346, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.249, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.015130534634739437, | |
| "grad_norm": 0.29130834341049194, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.3289, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.015670910871694418, | |
| "grad_norm": 0.29046890139579773, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.2298, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.016211287108649396, | |
| "grad_norm": 0.31192153692245483, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.2679, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01675166334560438, | |
| "grad_norm": 0.32285210490226746, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.3251, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.017292039582559357, | |
| "grad_norm": 0.31385868787765503, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.2645, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.017832415819514336, | |
| "grad_norm": 0.32815828919410706, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.3109, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.018372792056469318, | |
| "grad_norm": 0.3067333400249481, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.2784, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.018913168293424296, | |
| "grad_norm": 0.3107113540172577, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.3586, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.019453544530379275, | |
| "grad_norm": 0.3673906922340393, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.2515, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.019993920767334257, | |
| "grad_norm": 0.3637937903404236, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.2213, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.020534297004289236, | |
| "grad_norm": 0.24307753145694733, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.2029, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.021074673241244218, | |
| "grad_norm": 0.21791911125183105, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.1932, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.021615049478199196, | |
| "grad_norm": 0.24849295616149902, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.2393, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.022155425715154175, | |
| "grad_norm": 0.24978457391262054, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.2362, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.022695801952109157, | |
| "grad_norm": 0.2769562304019928, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.3149, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.023236178189064136, | |
| "grad_norm": 0.2753388285636902, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.2839, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.023776554426019114, | |
| "grad_norm": 0.3100898861885071, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.2743, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.024316930662974096, | |
| "grad_norm": 0.2863754332065582, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.2911, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.024857306899929075, | |
| "grad_norm": 0.2963234782218933, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.2549, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.025397683136884057, | |
| "grad_norm": 0.3099575340747833, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.2917, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.025938059373839036, | |
| "grad_norm": 0.32685086131095886, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.3653, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.026478435610794014, | |
| "grad_norm": 0.34813255071640015, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.3915, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.027018811847748996, | |
| "grad_norm": 0.3984713852405548, | |
| "learning_rate": 1e-05, | |
| "loss": 1.3408, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.027018811847748996, | |
| "eval_loss": 1.3384273052215576, | |
| "eval_runtime": 3.8377, | |
| "eval_samples_per_second": 13.029, | |
| "eval_steps_per_second": 3.387, | |
| "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": 6.061338191368028e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |