| { | |
| "best_metric": 1.1570563316345215, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.10771509357748754, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0021543018715497507, | |
| "grad_norm": 17.964126586914062, | |
| "learning_rate": 5e-05, | |
| "loss": 15.5288, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021543018715497507, | |
| "eval_loss": 1.9286686182022095, | |
| "eval_runtime": 2.7481, | |
| "eval_samples_per_second": 18.195, | |
| "eval_steps_per_second": 4.731, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0043086037430995015, | |
| "grad_norm": 28.86482810974121, | |
| "learning_rate": 0.0001, | |
| "loss": 18.9981, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006462905614649253, | |
| "grad_norm": 21.66073989868164, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 20.2643, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008617207486199003, | |
| "grad_norm": 14.327391624450684, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 20.3238, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010771509357748755, | |
| "grad_norm": 15.21226692199707, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 20.0814, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012925811229298506, | |
| "grad_norm": 15.41682243347168, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 21.2177, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015080113100848256, | |
| "grad_norm": 17.68107795715332, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 21.5685, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.017234414972398006, | |
| "grad_norm": 18.524627685546875, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 21.9915, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01938871684394776, | |
| "grad_norm": 21.69429588317871, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 21.0699, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02154301871549751, | |
| "grad_norm": 21.78917121887207, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 19.753, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02369732058704726, | |
| "grad_norm": 50.425785064697266, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 19.9424, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.025851622458597012, | |
| "grad_norm": 65.48330688476562, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 18.6582, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.028005924330146762, | |
| "grad_norm": 101.25495147705078, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 22.0046, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.030160226201696512, | |
| "grad_norm": 45.48244094848633, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 17.9526, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.032314528073246265, | |
| "grad_norm": 43.77912521362305, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 18.8983, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03446882994479601, | |
| "grad_norm": 29.692161560058594, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 19.9719, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.036623131816345765, | |
| "grad_norm": 20.597618103027344, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 18.778, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03877743368789552, | |
| "grad_norm": 21.7568359375, | |
| "learning_rate": 7.75e-05, | |
| "loss": 19.6851, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.040931735559445265, | |
| "grad_norm": 17.802059173583984, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 20.3445, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04308603743099502, | |
| "grad_norm": 16.12886619567871, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 20.1161, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04524033930254477, | |
| "grad_norm": 18.30609703063965, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 18.3392, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04739464117409452, | |
| "grad_norm": 20.116926193237305, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 19.3269, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04954894304564427, | |
| "grad_norm": 29.012292861938477, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 18.7942, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.051703244917194024, | |
| "grad_norm": 38.082183837890625, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 16.3779, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05385754678874377, | |
| "grad_norm": 116.95580291748047, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 25.5449, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05385754678874377, | |
| "eval_loss": 1.2116010189056396, | |
| "eval_runtime": 2.8499, | |
| "eval_samples_per_second": 17.545, | |
| "eval_steps_per_second": 4.562, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.056011848660293524, | |
| "grad_norm": 16.40360450744629, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 14.7959, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05816615053184328, | |
| "grad_norm": 10.675568580627441, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 16.9706, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.060320452403393024, | |
| "grad_norm": 11.316140174865723, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 17.8713, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06247475427494278, | |
| "grad_norm": 15.755949974060059, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 17.6029, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06462905614649253, | |
| "grad_norm": 12.196805953979492, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 19.5617, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06678335801804228, | |
| "grad_norm": 12.657279968261719, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 19.5314, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06893765988959202, | |
| "grad_norm": 13.666502952575684, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 19.9685, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07109196176114178, | |
| "grad_norm": 15.66434097290039, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 19.0098, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07324626363269153, | |
| "grad_norm": 19.04754066467285, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 18.1732, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07540056550424128, | |
| "grad_norm": 21.20579719543457, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 18.7094, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07755486737579104, | |
| "grad_norm": 26.361967086791992, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 16.9715, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07970916924734078, | |
| "grad_norm": 47.8284797668457, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 19.8467, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08186347111889053, | |
| "grad_norm": 87.42459869384766, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 19.9201, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08401777299044029, | |
| "grad_norm": 9.333584785461426, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 16.6894, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.08617207486199004, | |
| "grad_norm": 9.861259460449219, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 16.4402, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08832637673353978, | |
| "grad_norm": 11.06502628326416, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 18.4886, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09048067860508954, | |
| "grad_norm": 27.977924346923828, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 17.8642, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09263498047663929, | |
| "grad_norm": 13.159262657165527, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 19.8223, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.09478928234818904, | |
| "grad_norm": 11.276972770690918, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 19.9521, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0969435842197388, | |
| "grad_norm": 12.780776977539062, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 18.9005, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09909788609128854, | |
| "grad_norm": 14.059585571289062, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 18.8465, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10125218796283829, | |
| "grad_norm": 16.014514923095703, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 19.1576, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.10340648983438805, | |
| "grad_norm": 23.282018661499023, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 19.4527, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1055607917059378, | |
| "grad_norm": 34.15425491333008, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 18.9092, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.10771509357748754, | |
| "grad_norm": 82.45684814453125, | |
| "learning_rate": 1e-05, | |
| "loss": 19.8975, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10771509357748754, | |
| "eval_loss": 1.1570563316345215, | |
| "eval_runtime": 2.8352, | |
| "eval_samples_per_second": 17.635, | |
| "eval_steps_per_second": 4.585, | |
| "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": 5.703992746222551e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |