| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.10738255033557047, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002147651006711409, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002147651006711409, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0044, | |
| "eval_samples_per_second": 24.946, | |
| "eval_steps_per_second": 6.486, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004295302013422818, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006442953020134228, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008590604026845637, | |
| "grad_norm": 4.530643463134766, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.8069, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010738255033557046, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012885906040268456, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015033557046979866, | |
| "grad_norm": 6.896298885345459, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 4.9784, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.017181208053691274, | |
| "grad_norm": 2.4473958015441895, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.3513, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.019328859060402683, | |
| "grad_norm": 9.119861602783203, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 9.6751, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.021476510067114093, | |
| "grad_norm": 11.046996116638184, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 9.292, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023624161073825502, | |
| "grad_norm": 17.58078384399414, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 8.5724, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.025771812080536912, | |
| "grad_norm": 26.206045150756836, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 8.0451, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02791946308724832, | |
| "grad_norm": 21.75663185119629, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 7.9167, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03006711409395973, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.032214765100671144, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03436241610738255, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03651006711409396, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.038657718120805366, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.040805369127516776, | |
| "grad_norm": 6.113626480102539, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.8237, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.042953020134228186, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.045100671140939595, | |
| "grad_norm": 17.390596389770508, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 5.0601, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.047248322147651005, | |
| "grad_norm": 15.040576934814453, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 4.2181, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.049395973154362414, | |
| "grad_norm": 16.709522247314453, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.3738, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.051543624161073824, | |
| "grad_norm": 17.071434020996094, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.473, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.053691275167785234, | |
| "grad_norm": 10.45024585723877, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.2805, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.053691275167785234, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.013, | |
| "eval_samples_per_second": 24.838, | |
| "eval_steps_per_second": 6.458, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05583892617449664, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05798657718120805, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06013422818791946, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06228187919463087, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06442953020134229, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06657718120805368, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0687248322147651, | |
| "grad_norm": 17.758140563964844, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.9235, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0708724832214765, | |
| "grad_norm": 18.05216407775879, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 2.9561, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07302013422818791, | |
| "grad_norm": 12.09702205657959, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.6542, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07516778523489932, | |
| "grad_norm": 8.332193374633789, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 2.2896, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07731543624161073, | |
| "grad_norm": 7.144294261932373, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.7258, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07946308724832214, | |
| "grad_norm": 6.225759029388428, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.7284, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08161073825503355, | |
| "grad_norm": 5.70999002456665, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.4476, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08375838926174496, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.08590604026845637, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08805369127516778, | |
| "grad_norm": 13.675680160522461, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.8872, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09020134228187919, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0923489932885906, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.09449664429530201, | |
| "grad_norm": 19.001270294189453, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.0711, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.09664429530201342, | |
| "grad_norm": 5.015544414520264, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.7845, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09879194630872483, | |
| "grad_norm": 14.717562675476074, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 2.2785, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10093959731543624, | |
| "grad_norm": 11.277101516723633, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.848, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.10308724832214765, | |
| "grad_norm": 6.0920562744140625, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.8882, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.10523489932885906, | |
| "grad_norm": 5.014962673187256, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.2657, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.10738255033557047, | |
| "grad_norm": 3.8420026302337646, | |
| "learning_rate": 1e-05, | |
| "loss": 1.5918, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10738255033557047, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.9967, | |
| "eval_samples_per_second": 25.041, | |
| "eval_steps_per_second": 6.511, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |