| { | |
| "best_metric": 4.055038928985596, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.8703374777975132, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.056838365896980464, | |
| "grad_norm": 2.367138385772705, | |
| "learning_rate": 5e-05, | |
| "loss": 4.171, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.056838365896980464, | |
| "eval_loss": 5.347789287567139, | |
| "eval_runtime": 0.6628, | |
| "eval_samples_per_second": 75.442, | |
| "eval_steps_per_second": 19.615, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11367673179396093, | |
| "grad_norm": 1.7986496686935425, | |
| "learning_rate": 0.0001, | |
| "loss": 4.8151, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1705150976909414, | |
| "grad_norm": 2.638974189758301, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 5.1541, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.22735346358792186, | |
| "grad_norm": 1.8616949319839478, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 5.3469, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2841918294849023, | |
| "grad_norm": 1.141082525253296, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.1468, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3410301953818828, | |
| "grad_norm": 0.741497814655304, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 4.4591, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3978685612788632, | |
| "grad_norm": 2.0674901008605957, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 4.7593, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4547069271758437, | |
| "grad_norm": 1.6636701822280884, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 5.0494, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5115452930728241, | |
| "grad_norm": 0.8816699981689453, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 3.9727, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5683836589698046, | |
| "grad_norm": 0.7183719873428345, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 4.2175, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6252220248667851, | |
| "grad_norm": 0.9039377570152283, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 4.5158, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6820603907637656, | |
| "grad_norm": 0.9982225894927979, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.6965, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.738898756660746, | |
| "grad_norm": 0.729877769947052, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 3.9675, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7957371225577264, | |
| "grad_norm": 0.6320289969444275, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 4.0934, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8525754884547069, | |
| "grad_norm": 0.7548869848251343, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 4.2215, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9094138543516874, | |
| "grad_norm": 0.8287147879600525, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 4.4881, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9662522202486679, | |
| "grad_norm": 1.3373353481292725, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 4.9756, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0373001776198933, | |
| "grad_norm": 1.2438440322875977, | |
| "learning_rate": 7.75e-05, | |
| "loss": 6.8019, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0941385435168738, | |
| "grad_norm": 0.6422521471977234, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.8283, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1509769094138544, | |
| "grad_norm": 0.694166898727417, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 4.2743, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2078152753108349, | |
| "grad_norm": 1.107782244682312, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 4.476, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2646536412078153, | |
| "grad_norm": 0.6780546307563782, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.8396, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.3214920071047958, | |
| "grad_norm": 0.6974961757659912, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.9458, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3783303730017762, | |
| "grad_norm": 0.7146793603897095, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 4.1038, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4351687388987566, | |
| "grad_norm": 0.9049580693244934, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 4.2719, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4351687388987566, | |
| "eval_loss": 4.227850437164307, | |
| "eval_runtime": 0.6571, | |
| "eval_samples_per_second": 76.093, | |
| "eval_steps_per_second": 19.784, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.492007104795737, | |
| "grad_norm": 0.514370858669281, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 3.031, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5488454706927177, | |
| "grad_norm": 1.1798518896102905, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 4.6368, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.605683836589698, | |
| "grad_norm": 0.7508013844490051, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 3.8476, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.6625222024866786, | |
| "grad_norm": 0.7122344374656677, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 4.1605, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.7193605683836588, | |
| "grad_norm": 0.45820507407188416, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.2039, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7761989342806395, | |
| "grad_norm": 1.2526981830596924, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 5.6394, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.83303730017762, | |
| "grad_norm": 0.5841005444526672, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.823, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.8898756660746003, | |
| "grad_norm": 0.6095443367958069, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 4.0752, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.9467140319715808, | |
| "grad_norm": 1.193407654762268, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 4.4321, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0177619893428065, | |
| "grad_norm": 1.1657941341400146, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 6.658, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.0746003552397867, | |
| "grad_norm": 0.54337477684021, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 3.3645, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.1314387211367674, | |
| "grad_norm": 0.5608218908309937, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 3.8492, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.1882770870337476, | |
| "grad_norm": 0.7258840203285217, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 4.1457, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.2451154529307282, | |
| "grad_norm": 0.7750731110572815, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 3.4016, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.301953818827709, | |
| "grad_norm": 0.67059725522995, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 4.313, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.358792184724689, | |
| "grad_norm": 0.5662630796432495, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.813, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.4156305506216698, | |
| "grad_norm": 0.6992785334587097, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 4.0543, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.47246891651865, | |
| "grad_norm": 0.6731230616569519, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 2.8761, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.5293072824156306, | |
| "grad_norm": 0.8138448596000671, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 4.7918, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.586145648312611, | |
| "grad_norm": 0.5428887009620667, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 3.7575, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.6429840142095915, | |
| "grad_norm": 0.6178069710731506, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 4.0502, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.699822380106572, | |
| "grad_norm": 0.6623405814170837, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.0481, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.7566607460035524, | |
| "grad_norm": 0.7139769196510315, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 4.5405, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.8134991119005326, | |
| "grad_norm": 0.7384081482887268, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 3.6188, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.8703374777975132, | |
| "grad_norm": 0.5655322074890137, | |
| "learning_rate": 1e-05, | |
| "loss": 3.9295, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.8703374777975132, | |
| "eval_loss": 4.055038928985596, | |
| "eval_runtime": 0.6379, | |
| "eval_samples_per_second": 78.385, | |
| "eval_steps_per_second": 20.38, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 1.13737243557888e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |