| { | |
| "best_metric": 0.8412864208221436, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.125, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025, | |
| "grad_norm": 0.39660322666168213, | |
| "learning_rate": 5e-05, | |
| "loss": 0.537, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025, | |
| "eval_loss": 1.134306788444519, | |
| "eval_runtime": 2.2627, | |
| "eval_samples_per_second": 22.097, | |
| "eval_steps_per_second": 5.745, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005, | |
| "grad_norm": 0.4997485876083374, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6564, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0075, | |
| "grad_norm": 0.40851354598999023, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.691, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.0516798496246338, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.7611, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0125, | |
| "grad_norm": 0.6961551308631897, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.772, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015, | |
| "grad_norm": 0.7225443124771118, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.8629, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0175, | |
| "grad_norm": 0.40385228395462036, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.7852, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.495491087436676, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.8354, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0225, | |
| "grad_norm": 0.5331441760063171, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.9303, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.025, | |
| "grad_norm": 0.6330355405807495, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.0356, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0275, | |
| "grad_norm": 0.6601823568344116, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.0411, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.869492769241333, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.1601, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0325, | |
| "grad_norm": 0.42124900221824646, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.5752, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.035, | |
| "grad_norm": 0.383492112159729, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.5592, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0375, | |
| "grad_norm": 0.32786792516708374, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.5813, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.39821332693099976, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.66, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0425, | |
| "grad_norm": 0.39010098576545715, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.6779, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.045, | |
| "grad_norm": 0.3517184853553772, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.6842, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0475, | |
| "grad_norm": 0.3789606988430023, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.7565, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.39365527033805847, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.7404, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0525, | |
| "grad_norm": 0.4418632686138153, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.8163, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.055, | |
| "grad_norm": 0.49089720845222473, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.8311, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0575, | |
| "grad_norm": 0.5605911612510681, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.8919, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.695058286190033, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.0374, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 0.9899892210960388, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.2162, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "eval_loss": 0.8656136393547058, | |
| "eval_runtime": 2.3261, | |
| "eval_samples_per_second": 21.495, | |
| "eval_steps_per_second": 5.589, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.065, | |
| "grad_norm": 0.2663879692554474, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.4851, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0675, | |
| "grad_norm": 0.2828787863254547, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.6305, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3093838691711426, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.6392, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0725, | |
| "grad_norm": 0.33329126238822937, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.6667, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.075, | |
| "grad_norm": 0.3540312647819519, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.6825, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0775, | |
| "grad_norm": 0.3708834946155548, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.7007, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.37742483615875244, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.7389, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0825, | |
| "grad_norm": 0.41441866755485535, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.745, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.085, | |
| "grad_norm": 0.5062286257743835, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.8639, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0875, | |
| "grad_norm": 0.614949643611908, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.865, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.7550729513168335, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.8755, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0925, | |
| "grad_norm": 0.8111172914505005, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.1576, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.095, | |
| "grad_norm": 0.3536604642868042, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.5238, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0975, | |
| "grad_norm": 0.33883461356163025, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.5649, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.37112748622894287, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.5962, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1025, | |
| "grad_norm": 0.3818936049938202, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.6846, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.105, | |
| "grad_norm": 0.3865486979484558, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.7252, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1075, | |
| "grad_norm": 0.35471948981285095, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.6879, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.38089480996131897, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.715, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1125, | |
| "grad_norm": 0.3577588200569153, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.6943, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.115, | |
| "grad_norm": 0.40845608711242676, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.7526, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1175, | |
| "grad_norm": 0.48637714982032776, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.8287, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.5862032175064087, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.891, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1225, | |
| "grad_norm": 0.7420929074287415, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.0351, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 1.0091607570648193, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1372, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "eval_loss": 0.8412864208221436, | |
| "eval_runtime": 2.3229, | |
| "eval_samples_per_second": 21.525, | |
| "eval_steps_per_second": 5.596, | |
| "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": 6.189915553566556e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |