| { | |
| "best_metric": 1.1199095752090216e-05, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.12101043715020421, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002420208743004084, | |
| "grad_norm": 129.8616485595703, | |
| "learning_rate": 5e-05, | |
| "loss": 111.0611, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002420208743004084, | |
| "eval_loss": 7.585880279541016, | |
| "eval_runtime": 2.9412, | |
| "eval_samples_per_second": 17.0, | |
| "eval_steps_per_second": 4.42, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004840417486008168, | |
| "grad_norm": 131.14813232421875, | |
| "learning_rate": 0.0001, | |
| "loss": 112.1903, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007260626229012252, | |
| "grad_norm": 124.35859680175781, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 106.1069, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009680834972016336, | |
| "grad_norm": 120.47513580322266, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 83.1738, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01210104371502042, | |
| "grad_norm": 112.5082015991211, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 61.3049, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014521252458024504, | |
| "grad_norm": 123.15609741210938, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 37.9838, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016941461201028588, | |
| "grad_norm": 94.98416900634766, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 25.1704, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019361669944032673, | |
| "grad_norm": 70.09339141845703, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 14.7809, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02178187868703676, | |
| "grad_norm": 41.6122932434082, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 7.1772, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02420208743004084, | |
| "grad_norm": 18.32343101501465, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.5514, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026622296173044926, | |
| "grad_norm": 10.826604843139648, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.1709, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.029042504916049008, | |
| "grad_norm": 9.567692756652832, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.4779, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03146271365905309, | |
| "grad_norm": 6.14838981628418, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.2559, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.033882922402057175, | |
| "grad_norm": 3.8644745349884033, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0832, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.036303131145061264, | |
| "grad_norm": 0.16630400717258453, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0068, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.038723339888065346, | |
| "grad_norm": 0.0314423143863678, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0016, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04114354863106943, | |
| "grad_norm": 0.04940410330891609, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0018, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04356375737407352, | |
| "grad_norm": 0.05370471999049187, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0016, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0459839661170776, | |
| "grad_norm": 0.022832291200757027, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0008, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04840417486008168, | |
| "grad_norm": 0.01467802096158266, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0005, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05082438360308577, | |
| "grad_norm": 0.007455690763890743, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0003, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05324459234608985, | |
| "grad_norm": 0.011481430381536484, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0004, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.055664801089093933, | |
| "grad_norm": 0.015557793900370598, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0005, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.058085009832098015, | |
| "grad_norm": 0.009874274022877216, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0003, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.060505218575102104, | |
| "grad_norm": 0.013874717056751251, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0005, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.060505218575102104, | |
| "eval_loss": 1.1199095752090216e-05, | |
| "eval_runtime": 2.9887, | |
| "eval_samples_per_second": 16.73, | |
| "eval_steps_per_second": 4.35, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06292542731810619, | |
| "grad_norm": 4.933608055114746, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.735, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06534563606111027, | |
| "grad_norm": 0.0033409451134502888, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0001, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06776584480411435, | |
| "grad_norm": 0.003721554297953844, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0001, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07018605354711843, | |
| "grad_norm": 0.20777276158332825, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0009, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07260626229012253, | |
| "grad_norm": 0.0037672524340450764, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0002, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07502647103312661, | |
| "grad_norm": 0.0027831741608679295, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0001, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07744667977613069, | |
| "grad_norm": 18.835296630859375, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0246, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07986688851913477, | |
| "grad_norm": 4.418979644775391, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0289, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08228709726213886, | |
| "grad_norm": 0.002538805129006505, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0001, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08470730600514294, | |
| "grad_norm": 0.003876280738040805, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0002, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08712751474814703, | |
| "grad_norm": 0.004658486228436232, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0002, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08954772349115112, | |
| "grad_norm": 0.005029450170695782, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0002, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0919679322341552, | |
| "grad_norm": 7.445037841796875, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.0627, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09438814097715928, | |
| "grad_norm": 0.004267706535756588, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0001, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09680834972016336, | |
| "grad_norm": 0.0033585778437554836, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0001, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09922855846316744, | |
| "grad_norm": 0.004535750951617956, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0001, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10164876720617154, | |
| "grad_norm": 0.0062608541920781136, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0001, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10406897594917562, | |
| "grad_norm": 0.007605577353388071, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0001, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1064891846921797, | |
| "grad_norm": 0.006068273447453976, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0001, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.10890939343518379, | |
| "grad_norm": 0.004641711246222258, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0001, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11132960217818787, | |
| "grad_norm": 0.007844093255698681, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0002, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11374981092119195, | |
| "grad_norm": 39.069679260253906, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.6565, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11617001966419603, | |
| "grad_norm": 0.010749392211437225, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0002, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11859022840720013, | |
| "grad_norm": 0.7709367275238037, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0029, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12101043715020421, | |
| "grad_norm": 17.80816078186035, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0825, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12101043715020421, | |
| "eval_loss": 1.2612003047252074e-05, | |
| "eval_runtime": 2.9705, | |
| "eval_samples_per_second": 16.832, | |
| "eval_steps_per_second": 4.376, | |
| "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": 5.262443296860406e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |