| { | |
| "best_metric": 10.368376731872559, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06562756357670221, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013125512715340443, | |
| "grad_norm": 0.038570791482925415, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3798, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013125512715340443, | |
| "eval_loss": 10.376840591430664, | |
| "eval_runtime": 0.1075, | |
| "eval_samples_per_second": 465.008, | |
| "eval_steps_per_second": 120.902, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026251025430680886, | |
| "grad_norm": 0.0404408723115921, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3805, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003937653814602133, | |
| "grad_norm": 0.042241428047418594, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.3779, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005250205086136177, | |
| "grad_norm": 0.04308971017599106, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.3776, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006562756357670222, | |
| "grad_norm": 0.0456109419465065, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.3806, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007875307629204267, | |
| "grad_norm": 0.0400724783539772, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.38, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00918785890073831, | |
| "grad_norm": 0.03583625704050064, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.3762, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010500410172272354, | |
| "grad_norm": 0.040284231305122375, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.3806, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011812961443806398, | |
| "grad_norm": 0.04484258219599724, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.381, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013125512715340444, | |
| "grad_norm": 0.04239543154835701, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.3783, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014438063986874488, | |
| "grad_norm": 0.04420053958892822, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.378, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015750615258408533, | |
| "grad_norm": 0.05468428507447243, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.379, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017063166529942577, | |
| "grad_norm": 0.05054962635040283, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.3787, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01837571780147662, | |
| "grad_norm": 0.03767135739326477, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.3721, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.019688269073010665, | |
| "grad_norm": 0.0415552482008934, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 10.3793, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02100082034454471, | |
| "grad_norm": 0.04314960911870003, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 10.3755, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.022313371616078752, | |
| "grad_norm": 0.04680277779698372, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 10.3765, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.023625922887612796, | |
| "grad_norm": 0.04230505973100662, | |
| "learning_rate": 7.75e-05, | |
| "loss": 10.3748, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02493847415914684, | |
| "grad_norm": 0.04754308983683586, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 10.3778, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.026251025430680888, | |
| "grad_norm": 0.050806865096092224, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 10.3771, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02756357670221493, | |
| "grad_norm": 0.04781622439622879, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 10.3768, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.028876127973748975, | |
| "grad_norm": 0.05311872810125351, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 10.3733, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03018867924528302, | |
| "grad_norm": 0.053040653467178345, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 10.3765, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.031501230516817066, | |
| "grad_norm": 0.06266145408153534, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 10.3776, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03281378178835111, | |
| "grad_norm": 0.07380590587854385, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 10.3747, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03281378178835111, | |
| "eval_loss": 10.371474266052246, | |
| "eval_runtime": 0.0994, | |
| "eval_samples_per_second": 502.961, | |
| "eval_steps_per_second": 130.77, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.034126333059885154, | |
| "grad_norm": 0.053233131766319275, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 10.3718, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.035438884331419195, | |
| "grad_norm": 0.05241366848349571, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 10.3713, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03675143560295324, | |
| "grad_norm": 0.045514870434999466, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 10.376, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03806398687448728, | |
| "grad_norm": 0.059033963829278946, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 10.3716, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03937653814602133, | |
| "grad_norm": 0.052445072680711746, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 10.3717, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04068908941755537, | |
| "grad_norm": 0.05115202069282532, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 10.372, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04200164068908942, | |
| "grad_norm": 0.05915110930800438, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 10.3724, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.043314191960623465, | |
| "grad_norm": 0.05899716541171074, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 10.3754, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.044626743232157505, | |
| "grad_norm": 0.06602742522954941, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 10.3774, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04593929450369155, | |
| "grad_norm": 0.08038340508937836, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 10.3759, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04725184577522559, | |
| "grad_norm": 0.08238374441862106, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 10.378, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04856439704675964, | |
| "grad_norm": 0.0753418356180191, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 10.3736, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04987694831829368, | |
| "grad_norm": 0.07205703109502792, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 10.3737, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05118949958982773, | |
| "grad_norm": 0.05470695346593857, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 10.3718, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.052502050861361775, | |
| "grad_norm": 0.06746212393045425, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 10.3725, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.053814602132895815, | |
| "grad_norm": 0.06536153703927994, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 10.373, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05512715340442986, | |
| "grad_norm": 0.07258470356464386, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 10.3715, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0564397046759639, | |
| "grad_norm": 0.06972433626651764, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 10.3695, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05775225594749795, | |
| "grad_norm": 0.06809047609567642, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 10.3692, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05906480721903199, | |
| "grad_norm": 0.0657813623547554, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 10.3746, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06037735849056604, | |
| "grad_norm": 0.06854860484600067, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 10.3757, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06168990976210008, | |
| "grad_norm": 0.06397425383329391, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 10.371, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06300246103363413, | |
| "grad_norm": 0.07391654700040817, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 10.3725, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06431501230516817, | |
| "grad_norm": 0.08552011102437973, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 10.3695, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06562756357670221, | |
| "grad_norm": 0.09103067964315414, | |
| "learning_rate": 1e-05, | |
| "loss": 10.372, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06562756357670221, | |
| "eval_loss": 10.368376731872559, | |
| "eval_runtime": 0.1011, | |
| "eval_samples_per_second": 494.675, | |
| "eval_steps_per_second": 128.616, | |
| "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": 42768059596800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |