| { | |
| "best_metric": 0.9669813513755798, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06415911460421846, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012831822920843692, | |
| "grad_norm": 3.5345535278320312, | |
| "learning_rate": 5e-05, | |
| "loss": 38.0642, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012831822920843692, | |
| "eval_loss": 1.1701257228851318, | |
| "eval_runtime": 1.9057, | |
| "eval_samples_per_second": 26.237, | |
| "eval_steps_per_second": 6.822, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025663645841687384, | |
| "grad_norm": 3.669259786605835, | |
| "learning_rate": 0.0001, | |
| "loss": 37.1715, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0038495468762531075, | |
| "grad_norm": 3.515411138534546, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 37.364, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005132729168337477, | |
| "grad_norm": 3.9850051403045654, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 36.108, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006415911460421846, | |
| "grad_norm": 4.171756267547607, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 35.0949, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007699093752506215, | |
| "grad_norm": 3.1119837760925293, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 33.8759, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008982276044590584, | |
| "grad_norm": 4.50632905960083, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 34.068, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010265458336674953, | |
| "grad_norm": 5.083990573883057, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 34.5506, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011548640628759323, | |
| "grad_norm": 5.132439613342285, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 33.2934, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012831822920843693, | |
| "grad_norm": 3.916484832763672, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 32.4104, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014115005212928062, | |
| "grad_norm": 2.4255878925323486, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 32.3686, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01539818750501243, | |
| "grad_norm": 2.369929552078247, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 31.8053, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0166813697970968, | |
| "grad_norm": 2.6247308254241943, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 32.3517, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.017964552089181168, | |
| "grad_norm": 3.2126903533935547, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 33.238, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01924773438126554, | |
| "grad_norm": 2.6321258544921875, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 33.4018, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020530916673349907, | |
| "grad_norm": 2.1531386375427246, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 32.5685, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021814098965434278, | |
| "grad_norm": 1.888481855392456, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 31.1734, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.023097281257518646, | |
| "grad_norm": 1.7277491092681885, | |
| "learning_rate": 7.75e-05, | |
| "loss": 31.66, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.024380463549603014, | |
| "grad_norm": 1.7912100553512573, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 31.0256, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.025663645841687385, | |
| "grad_norm": 1.8502416610717773, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 30.776, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026946828133771753, | |
| "grad_norm": 2.072106122970581, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 30.05, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.028230010425856124, | |
| "grad_norm": 1.9093363285064697, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 29.555, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.029513192717940492, | |
| "grad_norm": 2.0280885696411133, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 29.988, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03079637501002486, | |
| "grad_norm": 2.303346872329712, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 32.021, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03207955730210923, | |
| "grad_norm": 2.2593610286712646, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 29.1695, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03207955730210923, | |
| "eval_loss": 0.989615261554718, | |
| "eval_runtime": 1.831, | |
| "eval_samples_per_second": 27.308, | |
| "eval_steps_per_second": 7.1, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0333627395941936, | |
| "grad_norm": 2.4259300231933594, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 33.1251, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03464592188627797, | |
| "grad_norm": 1.9009075164794922, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 31.923, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.035929104178362335, | |
| "grad_norm": 1.9029998779296875, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 30.9763, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03721228647044671, | |
| "grad_norm": 1.6665700674057007, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 29.9786, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03849546876253108, | |
| "grad_norm": 1.5933430194854736, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 30.5074, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03977865105461545, | |
| "grad_norm": 1.5921006202697754, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 30.9787, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.041061833346699814, | |
| "grad_norm": 1.6825135946273804, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 29.4713, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.042345015638784185, | |
| "grad_norm": 1.7640290260314941, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 29.3274, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.043628197930868556, | |
| "grad_norm": 1.6936829090118408, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 29.7702, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04491138022295292, | |
| "grad_norm": 1.7560760974884033, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 30.3689, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04619456251503729, | |
| "grad_norm": 1.730417251586914, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 29.5927, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04747774480712166, | |
| "grad_norm": 1.891713261604309, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 30.0994, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04876092709920603, | |
| "grad_norm": 1.935252070426941, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 30.6733, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0500441093912904, | |
| "grad_norm": 1.701902985572815, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 31.3318, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05132729168337477, | |
| "grad_norm": 1.5853103399276733, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 30.9148, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05261047397545914, | |
| "grad_norm": 1.5667396783828735, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 30.8344, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.053893656267543506, | |
| "grad_norm": 1.5070350170135498, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 30.1059, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05517683855962788, | |
| "grad_norm": 1.4857155084609985, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 30.039, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05646002085171225, | |
| "grad_norm": 1.5021370649337769, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 30.441, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05774320314379661, | |
| "grad_norm": 1.5308558940887451, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 28.8641, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.059026385435880985, | |
| "grad_norm": 1.572772741317749, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 30.0764, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.060309567727965356, | |
| "grad_norm": 1.5550898313522339, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 30.2535, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06159275002004972, | |
| "grad_norm": 1.7037779092788696, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 29.5456, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06287593231213409, | |
| "grad_norm": 1.7626756429672241, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 30.1327, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06415911460421846, | |
| "grad_norm": 1.985012412071228, | |
| "learning_rate": 1e-05, | |
| "loss": 30.0777, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06415911460421846, | |
| "eval_loss": 0.9669813513755798, | |
| "eval_runtime": 1.9069, | |
| "eval_samples_per_second": 26.221, | |
| "eval_steps_per_second": 6.817, | |
| "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": 5.694680215595254e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |