| { | |
| "best_metric": 2.1184535026550293, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.08787346221441125, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017574692442882249, | |
| "grad_norm": 8.197124481201172, | |
| "learning_rate": 5e-05, | |
| "loss": 41.5996, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017574692442882249, | |
| "eval_loss": 2.67146635055542, | |
| "eval_runtime": 1.9945, | |
| "eval_samples_per_second": 25.069, | |
| "eval_steps_per_second": 6.518, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0035149384885764497, | |
| "grad_norm": 8.175345420837402, | |
| "learning_rate": 0.0001, | |
| "loss": 41.7819, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005272407732864675, | |
| "grad_norm": 7.782145977020264, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 41.4354, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007029876977152899, | |
| "grad_norm": 6.955953598022461, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 41.4572, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008787346221441126, | |
| "grad_norm": 6.188976764678955, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 40.7239, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01054481546572935, | |
| "grad_norm": 6.627973556518555, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 40.2346, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012302284710017574, | |
| "grad_norm": 7.199131488800049, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 40.0303, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.014059753954305799, | |
| "grad_norm": 6.509369850158691, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 39.3336, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015817223198594025, | |
| "grad_norm": 5.756955623626709, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 38.5489, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01757469244288225, | |
| "grad_norm": 5.405374050140381, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 39.4141, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.019332161687170474, | |
| "grad_norm": 5.918015003204346, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 38.2517, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0210896309314587, | |
| "grad_norm": 6.271076679229736, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 37.0873, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.022847100175746926, | |
| "grad_norm": 7.2467522621154785, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 37.3231, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02460456942003515, | |
| "grad_norm": 6.07332706451416, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 36.9542, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.026362038664323375, | |
| "grad_norm": 5.141885280609131, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 36.7673, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.028119507908611598, | |
| "grad_norm": 4.824089050292969, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 36.6982, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.029876977152899824, | |
| "grad_norm": 4.891728401184082, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 36.8259, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03163444639718805, | |
| "grad_norm": 4.810305118560791, | |
| "learning_rate": 7.75e-05, | |
| "loss": 36.0425, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.033391915641476276, | |
| "grad_norm": 4.6905517578125, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 36.3803, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0351493848857645, | |
| "grad_norm": 4.8916730880737305, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 35.6215, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03690685413005272, | |
| "grad_norm": 5.4649200439453125, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 35.9459, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03866432337434095, | |
| "grad_norm": 4.950930118560791, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 35.3764, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.040421792618629174, | |
| "grad_norm": 4.891223907470703, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 35.791, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0421792618629174, | |
| "grad_norm": 4.985620975494385, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 35.3101, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.043936731107205626, | |
| "grad_norm": 7.151154518127441, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 34.113, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.043936731107205626, | |
| "eval_loss": 2.184957981109619, | |
| "eval_runtime": 2.0461, | |
| "eval_samples_per_second": 24.437, | |
| "eval_steps_per_second": 6.354, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04569420035149385, | |
| "grad_norm": 6.682544231414795, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 35.104, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04745166959578207, | |
| "grad_norm": 5.638045787811279, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 35.0024, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0492091388400703, | |
| "grad_norm": 5.364726543426514, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 34.663, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.050966608084358524, | |
| "grad_norm": 5.238322734832764, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 35.3332, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05272407732864675, | |
| "grad_norm": 4.853617191314697, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 34.6261, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.054481546572934976, | |
| "grad_norm": 4.672550678253174, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 34.2556, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.056239015817223195, | |
| "grad_norm": 5.044317722320557, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 35.2622, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05799648506151142, | |
| "grad_norm": 4.753660202026367, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 34.329, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05975395430579965, | |
| "grad_norm": 5.342644691467285, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 33.9036, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.061511423550087874, | |
| "grad_norm": 5.310150146484375, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 34.2209, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0632688927943761, | |
| "grad_norm": 5.2009806632995605, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 34.3841, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06502636203866433, | |
| "grad_norm": 6.031763076782227, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 34.0815, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06678383128295255, | |
| "grad_norm": 6.2134504318237305, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 34.21, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06854130052724078, | |
| "grad_norm": 5.3948974609375, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 34.3695, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.070298769771529, | |
| "grad_norm": 5.243184566497803, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 33.6793, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07205623901581722, | |
| "grad_norm": 4.971773624420166, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 34.1816, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07381370826010544, | |
| "grad_norm": 4.651072025299072, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 33.9473, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07557117750439367, | |
| "grad_norm": 4.51092529296875, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 34.2455, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0773286467486819, | |
| "grad_norm": 4.373141288757324, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 34.1921, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07908611599297012, | |
| "grad_norm": 4.692596912384033, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 34.3758, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08084358523725835, | |
| "grad_norm": 4.683785438537598, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 33.96, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08260105448154657, | |
| "grad_norm": 5.398478031158447, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 34.4189, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0843585237258348, | |
| "grad_norm": 5.291502952575684, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 34.3325, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08611599297012303, | |
| "grad_norm": 5.439122200012207, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 33.6364, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08787346221441125, | |
| "grad_norm": 7.769702434539795, | |
| "learning_rate": 1e-05, | |
| "loss": 33.6672, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08787346221441125, | |
| "eval_loss": 2.1184535026550293, | |
| "eval_runtime": 2.0483, | |
| "eval_samples_per_second": 24.411, | |
| "eval_steps_per_second": 6.347, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.967137622687744e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |