| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.10791852151625522, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0021583704303251047, | |
| "grad_norm": 9.589590072631836, | |
| "learning_rate": 5e-05, | |
| "loss": 14134.3311, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021583704303251047, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5063, | |
| "eval_samples_per_second": 33.193, | |
| "eval_steps_per_second": 8.63, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004316740860650209, | |
| "grad_norm": 2.6056127548217773, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5154, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006475111290975314, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008633481721300419, | |
| "grad_norm": 1.0833667516708374, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.0843, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010791852151625522, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012950222581950627, | |
| "grad_norm": 1.8674092292785645, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2838.8691, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015108593012275733, | |
| "grad_norm": 10.46643352508545, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 459.9153, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.017266963442600838, | |
| "grad_norm": 30.5323543548584, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 18.5649, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01942533387292594, | |
| "grad_norm": 52.480743408203125, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 8.4297, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.021583704303251044, | |
| "grad_norm": 14.486082077026367, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.7011, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02374207473357615, | |
| "grad_norm": 16.964412689208984, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.2177, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.025900445163901255, | |
| "grad_norm": 16.523624420166016, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.4766, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02805881559422636, | |
| "grad_norm": 79.47900390625, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 435.1353, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.030217186024551465, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03237555645487657, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.034533926885201675, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03669229731552678, | |
| "grad_norm": 6.835830211639404, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1491.1675, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03885066774585188, | |
| "grad_norm": 2.5021870136260986, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0544, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04100903817617699, | |
| "grad_norm": 10.689543724060059, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 460.1638, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04316740860650209, | |
| "grad_norm": 3.746053457260132, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.7662, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0453257790368272, | |
| "grad_norm": 32.34689712524414, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.8726, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0474841494671523, | |
| "grad_norm": 8.917804718017578, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.6354, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04964251989747741, | |
| "grad_norm": 6.496092796325684, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.2131, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05180089032780251, | |
| "grad_norm": 12.431622505187988, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.1297, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05395926075812761, | |
| "grad_norm": 5.4238176345825195, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.2167, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05395926075812761, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5674, | |
| "eval_samples_per_second": 31.9, | |
| "eval_steps_per_second": 8.294, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05611763118845272, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05827600161877782, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06043437204910293, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06259274247942803, | |
| "grad_norm": 0.00033452859497629106, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0455, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06475111290975313, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06690948334007824, | |
| "grad_norm": 0.3195914924144745, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0495, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06906785377040335, | |
| "grad_norm": 18.950136184692383, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.3005, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07122622420072845, | |
| "grad_norm": 18.768531799316406, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 51.4499, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07338459463105355, | |
| "grad_norm": 5.757758617401123, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.353, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07554296506137866, | |
| "grad_norm": 3.475687026977539, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.1307, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07770133549170376, | |
| "grad_norm": 4.415914535522461, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.2457, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07985970592202887, | |
| "grad_norm": 3.654486656188965, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.1651, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08201807635235397, | |
| "grad_norm": 2.106903553009033, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 16.0562, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08417644678267908, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.08633481721300418, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08849318764332928, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0906515580736544, | |
| "grad_norm": 0.7044157385826111, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 44.9168, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0928099285039795, | |
| "grad_norm": 0.026013152673840523, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0082, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0949682989343046, | |
| "grad_norm": 0.19379185140132904, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0175, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0971266693646297, | |
| "grad_norm": 1.7980287075042725, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 5.6403, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09928503979495482, | |
| "grad_norm": 4.9771246910095215, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 23.1134, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10144341022527992, | |
| "grad_norm": 2.0049068927764893, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.1428, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.10360178065560502, | |
| "grad_norm": 4.939352512359619, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.139, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.10576015108593012, | |
| "grad_norm": 0.6309598088264465, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0207, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.10791852151625522, | |
| "grad_norm": 2.4616317749023438, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1247, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10791852151625522, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5575, | |
| "eval_samples_per_second": 32.103, | |
| "eval_steps_per_second": 8.347, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.708814106361856e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |