| { | |
| "best_metric": 10.351131439208984, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.857449088960343, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01714898177920686, | |
| "grad_norm": 0.2781277894973755, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3751, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01714898177920686, | |
| "eval_loss": 10.376319885253906, | |
| "eval_runtime": 0.1561, | |
| "eval_samples_per_second": 320.218, | |
| "eval_steps_per_second": 83.257, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03429796355841372, | |
| "grad_norm": 0.26635631918907166, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3769, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05144694533762058, | |
| "grad_norm": 0.24324455857276917, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.3756, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06859592711682744, | |
| "grad_norm": 0.2410132884979248, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.3753, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0857449088960343, | |
| "grad_norm": 0.25901633501052856, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.3756, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10289389067524116, | |
| "grad_norm": 0.23864327371120453, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.3734, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12004287245444802, | |
| "grad_norm": 0.23465383052825928, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.3733, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13719185423365488, | |
| "grad_norm": 0.21229125559329987, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.3719, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.15434083601286175, | |
| "grad_norm": 0.143875390291214, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.3747, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1714898177920686, | |
| "grad_norm": 0.15762226283550262, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.3733, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18863879957127547, | |
| "grad_norm": 0.1492721140384674, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.3706, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2057877813504823, | |
| "grad_norm": 0.16960009932518005, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.3702, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.22293676312968919, | |
| "grad_norm": 0.3049704432487488, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.3648, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.24008574490889603, | |
| "grad_norm": 0.3048405647277832, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.3644, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2572347266881029, | |
| "grad_norm": 0.29572442173957825, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 10.3678, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.27438370846730975, | |
| "grad_norm": 0.2956143319606781, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 10.3662, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2915326902465166, | |
| "grad_norm": 0.31987524032592773, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 10.3641, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3086816720257235, | |
| "grad_norm": 0.2845809757709503, | |
| "learning_rate": 7.75e-05, | |
| "loss": 10.3642, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3258306538049303, | |
| "grad_norm": 0.3056682348251343, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 10.3616, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3429796355841372, | |
| "grad_norm": 0.26883333921432495, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 10.3639, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.36012861736334406, | |
| "grad_norm": 0.23084214329719543, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 10.3648, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.37727759914255093, | |
| "grad_norm": 0.19078941643238068, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 10.3663, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.39442658092175775, | |
| "grad_norm": 0.2088453471660614, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 10.3629, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4115755627009646, | |
| "grad_norm": 0.21084749698638916, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 10.3645, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4287245444801715, | |
| "grad_norm": 0.286233514547348, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 10.3571, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4287245444801715, | |
| "eval_loss": 10.359770774841309, | |
| "eval_runtime": 0.1536, | |
| "eval_samples_per_second": 325.57, | |
| "eval_steps_per_second": 84.648, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.44587352625937837, | |
| "grad_norm": 0.3661450147628784, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 10.3536, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4630225080385852, | |
| "grad_norm": 0.3774856925010681, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 10.3521, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.48017148981779206, | |
| "grad_norm": 0.36771613359451294, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 10.3541, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.49732047159699894, | |
| "grad_norm": 0.3387458324432373, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 10.3558, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5144694533762058, | |
| "grad_norm": 0.36350730061531067, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 10.3544, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5316184351554126, | |
| "grad_norm": 0.3397047817707062, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 10.355, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5487674169346195, | |
| "grad_norm": 0.33397170901298523, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 10.3552, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5659163987138264, | |
| "grad_norm": 0.30027225613594055, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 10.3592, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5830653804930332, | |
| "grad_norm": 0.2578124403953552, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 10.3582, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6002143622722401, | |
| "grad_norm": 0.23600928485393524, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 10.3588, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.617363344051447, | |
| "grad_norm": 0.20688872039318085, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 10.3605, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6345123258306538, | |
| "grad_norm": 0.22976522147655487, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 10.3583, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6516613076098606, | |
| "grad_norm": 0.409728080034256, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 10.3465, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6688102893890675, | |
| "grad_norm": 0.3956170976161957, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 10.3464, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6859592711682744, | |
| "grad_norm": 0.4047352373600006, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 10.3489, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7031082529474812, | |
| "grad_norm": 0.3896724581718445, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 10.3492, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7202572347266881, | |
| "grad_norm": 0.4095645248889923, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 10.3469, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.737406216505895, | |
| "grad_norm": 0.3700507581233978, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 10.3496, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7545551982851019, | |
| "grad_norm": 0.3776719868183136, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 10.3502, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7717041800643086, | |
| "grad_norm": 0.31713807582855225, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 10.3525, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7888531618435155, | |
| "grad_norm": 0.2858991324901581, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 10.3553, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8060021436227224, | |
| "grad_norm": 0.22458294034004211, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 10.3588, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8231511254019293, | |
| "grad_norm": 0.25443997979164124, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 10.3567, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8403001071811361, | |
| "grad_norm": 0.20725396275520325, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 10.3592, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.857449088960343, | |
| "grad_norm": 0.24995845556259155, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3557, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.857449088960343, | |
| "eval_loss": 10.351131439208984, | |
| "eval_runtime": 0.1482, | |
| "eval_samples_per_second": 337.425, | |
| "eval_steps_per_second": 87.73, | |
| "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": 51188021329920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |