{ "best_metric": 0.6595383286476135, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.047891286779011645, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0009578257355802328, "grad_norm": 6.584214210510254, "learning_rate": 5e-05, "loss": 1.9653, "step": 1 }, { "epoch": 0.0009578257355802328, "eval_loss": 2.1729257106781006, "eval_runtime": 2.7356, "eval_samples_per_second": 18.278, "eval_steps_per_second": 4.752, "step": 1 }, { "epoch": 0.0019156514711604657, "grad_norm": 8.032960891723633, "learning_rate": 0.0001, "loss": 2.0349, "step": 2 }, { "epoch": 0.0028734772067406985, "grad_norm": 4.240800380706787, "learning_rate": 9.990365154573717e-05, "loss": 1.7733, "step": 3 }, { "epoch": 0.0038313029423209313, "grad_norm": 4.471002578735352, "learning_rate": 9.961501876182148e-05, "loss": 1.5056, "step": 4 }, { "epoch": 0.004789128677901164, "grad_norm": 4.604516983032227, "learning_rate": 9.913533761814537e-05, "loss": 1.3188, "step": 5 }, { "epoch": 0.005746954413481397, "grad_norm": 2.211268424987793, "learning_rate": 9.846666218300807e-05, "loss": 1.1616, "step": 6 }, { "epoch": 0.00670478014906163, "grad_norm": 1.5972967147827148, "learning_rate": 9.761185582727977e-05, "loss": 1.0508, "step": 7 }, { "epoch": 0.007662605884641863, "grad_norm": 1.7796998023986816, "learning_rate": 9.657457896300791e-05, "loss": 1.001, "step": 8 }, { "epoch": 0.008620431620222095, "grad_norm": 1.2383780479431152, "learning_rate": 9.535927336897098e-05, "loss": 0.9233, "step": 9 }, { "epoch": 0.009578257355802328, "grad_norm": 1.5014957189559937, "learning_rate": 9.397114317029975e-05, "loss": 0.8836, "step": 10 }, { "epoch": 0.010536083091382561, "grad_norm": 1.0149110555648804, "learning_rate": 9.241613255361455e-05, "loss": 0.8305, "step": 11 }, { "epoch": 0.011493908826962794, "grad_norm": 1.811235785484314, "learning_rate": 9.070090031310558e-05, "loss": 0.8482, "step": 12 }, { "epoch": 0.012451734562543027, "grad_norm": 2.5230791568756104, "learning_rate": 8.883279133655399e-05, "loss": 0.9421, "step": 13 }, { "epoch": 0.01340956029812326, "grad_norm": 2.8262531757354736, "learning_rate": 8.681980515339464e-05, "loss": 0.8897, "step": 14 }, { "epoch": 0.014367386033703492, "grad_norm": 1.3079264163970947, "learning_rate": 8.467056167950311e-05, "loss": 0.8137, "step": 15 }, { "epoch": 0.015325211769283725, "grad_norm": 2.130812168121338, "learning_rate": 8.239426430539243e-05, "loss": 0.7973, "step": 16 }, { "epoch": 0.01628303750486396, "grad_norm": 2.002680540084839, "learning_rate": 8.000066048588211e-05, "loss": 0.7924, "step": 17 }, { "epoch": 0.01724086324044419, "grad_norm": 1.0449703931808472, "learning_rate": 7.75e-05, "loss": 0.7429, "step": 18 }, { "epoch": 0.018198688976024426, "grad_norm": 1.27388334274292, "learning_rate": 7.490299105985507e-05, "loss": 0.7384, "step": 19 }, { "epoch": 0.019156514711604657, "grad_norm": 1.0604186058044434, "learning_rate": 7.222075445642904e-05, "loss": 0.7169, "step": 20 }, { "epoch": 0.02011434044718489, "grad_norm": 1.021995186805725, "learning_rate": 6.946477593864228e-05, "loss": 0.7056, "step": 21 }, { "epoch": 0.021072166182765122, "grad_norm": 0.9219874143600464, "learning_rate": 6.664685702961344e-05, "loss": 0.708, "step": 22 }, { "epoch": 0.022029991918345357, "grad_norm": 0.7598695158958435, "learning_rate": 6.377906449072578e-05, "loss": 0.7057, "step": 23 }, { "epoch": 0.022987817653925588, "grad_norm": 0.8495933413505554, "learning_rate": 6.087367864990233e-05, "loss": 0.7116, "step": 24 }, { "epoch": 0.023945643389505823, "grad_norm": 1.3555946350097656, "learning_rate": 5.794314081535644e-05, "loss": 0.7289, "step": 25 }, { "epoch": 0.023945643389505823, "eval_loss": 0.7703685760498047, "eval_runtime": 2.7601, "eval_samples_per_second": 18.115, "eval_steps_per_second": 4.71, "step": 25 }, { "epoch": 0.024903469125086054, "grad_norm": 3.212273120880127, "learning_rate": 5.500000000000001e-05, "loss": 0.8884, "step": 26 }, { "epoch": 0.025861294860666288, "grad_norm": 3.1316325664520264, "learning_rate": 5.205685918464356e-05, "loss": 0.8394, "step": 27 }, { "epoch": 0.02681912059624652, "grad_norm": 2.400233507156372, "learning_rate": 4.912632135009769e-05, "loss": 0.7776, "step": 28 }, { "epoch": 0.027776946331826754, "grad_norm": 1.5806422233581543, "learning_rate": 4.6220935509274235e-05, "loss": 0.7254, "step": 29 }, { "epoch": 0.028734772067406985, "grad_norm": 1.1703928709030151, "learning_rate": 4.3353142970386564e-05, "loss": 0.7256, "step": 30 }, { "epoch": 0.02969259780298722, "grad_norm": 1.0857999324798584, "learning_rate": 4.053522406135775e-05, "loss": 0.6946, "step": 31 }, { "epoch": 0.03065042353856745, "grad_norm": 1.0689618587493896, "learning_rate": 3.777924554357096e-05, "loss": 0.6785, "step": 32 }, { "epoch": 0.03160824927414768, "grad_norm": 1.065096378326416, "learning_rate": 3.509700894014496e-05, "loss": 0.6666, "step": 33 }, { "epoch": 0.03256607500972792, "grad_norm": 1.090894341468811, "learning_rate": 3.250000000000001e-05, "loss": 0.6828, "step": 34 }, { "epoch": 0.03352390074530815, "grad_norm": 0.8290038108825684, "learning_rate": 2.9999339514117912e-05, "loss": 0.6704, "step": 35 }, { "epoch": 0.03448172648088838, "grad_norm": 0.8014963865280151, "learning_rate": 2.760573569460757e-05, "loss": 0.6749, "step": 36 }, { "epoch": 0.03543955221646861, "grad_norm": 0.9459187984466553, "learning_rate": 2.53294383204969e-05, "loss": 0.6879, "step": 37 }, { "epoch": 0.03639737795204885, "grad_norm": 1.419850468635559, "learning_rate": 2.3180194846605367e-05, "loss": 0.7928, "step": 38 }, { "epoch": 0.03735520368762908, "grad_norm": 2.180847406387329, "learning_rate": 2.1167208663446025e-05, "loss": 0.7293, "step": 39 }, { "epoch": 0.03831302942320931, "grad_norm": 1.8599144220352173, "learning_rate": 1.9299099686894423e-05, "loss": 0.6973, "step": 40 }, { "epoch": 0.039270855158789544, "grad_norm": 1.7160967588424683, "learning_rate": 1.758386744638546e-05, "loss": 0.6738, "step": 41 }, { "epoch": 0.04022868089436978, "grad_norm": 1.5232151746749878, "learning_rate": 1.602885682970026e-05, "loss": 0.6755, "step": 42 }, { "epoch": 0.041186506629950013, "grad_norm": 1.1328383684158325, "learning_rate": 1.464072663102903e-05, "loss": 0.6505, "step": 43 }, { "epoch": 0.042144332365530245, "grad_norm": 0.9517636895179749, "learning_rate": 1.3425421036992098e-05, "loss": 0.6339, "step": 44 }, { "epoch": 0.04310215810111048, "grad_norm": 0.9324932098388672, "learning_rate": 1.2388144172720251e-05, "loss": 0.6245, "step": 45 }, { "epoch": 0.044059983836690714, "grad_norm": 0.7847539782524109, "learning_rate": 1.1533337816991932e-05, "loss": 0.6317, "step": 46 }, { "epoch": 0.045017809572270945, "grad_norm": 0.9269770383834839, "learning_rate": 1.0864662381854632e-05, "loss": 0.6517, "step": 47 }, { "epoch": 0.045975635307851176, "grad_norm": 1.0401601791381836, "learning_rate": 1.0384981238178534e-05, "loss": 0.6545, "step": 48 }, { "epoch": 0.046933461043431414, "grad_norm": 1.3331917524337769, "learning_rate": 1.0096348454262845e-05, "loss": 0.6781, "step": 49 }, { "epoch": 0.047891286779011645, "grad_norm": 1.9794204235076904, "learning_rate": 1e-05, "loss": 0.7522, "step": 50 }, { "epoch": 0.047891286779011645, "eval_loss": 0.6595383286476135, "eval_runtime": 2.7637, "eval_samples_per_second": 18.092, "eval_steps_per_second": 4.704, "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": 1.223410159976448e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }