| { | |
| "best_metric": 0.11191346496343613, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5194805194805194, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01038961038961039, | |
| "grad_norm": 28.486879348754883, | |
| "learning_rate": 5e-05, | |
| "loss": 12.5804, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01038961038961039, | |
| "eval_loss": 12.917760848999023, | |
| "eval_runtime": 2.0615, | |
| "eval_samples_per_second": 24.254, | |
| "eval_steps_per_second": 6.306, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02077922077922078, | |
| "grad_norm": 27.35738754272461, | |
| "learning_rate": 0.0001, | |
| "loss": 12.6136, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03116883116883117, | |
| "grad_norm": 29.368932723999023, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.1211, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04155844155844156, | |
| "grad_norm": 16.969623565673828, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.5609, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05194805194805195, | |
| "grad_norm": 13.911603927612305, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.2736, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06233766233766234, | |
| "grad_norm": 11.471969604492188, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.6157, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07272727272727272, | |
| "grad_norm": 7.600925922393799, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.6604, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08311688311688312, | |
| "grad_norm": 6.118250846862793, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.0122, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09350649350649351, | |
| "grad_norm": 21.522790908813477, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.0105, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1038961038961039, | |
| "grad_norm": 6.143969535827637, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.6796, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11428571428571428, | |
| "grad_norm": 2.42429256439209, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.6191, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.12467532467532468, | |
| "grad_norm": 2.489107847213745, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.6218, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.13506493506493505, | |
| "grad_norm": 0.9331566095352173, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.5814, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.14545454545454545, | |
| "grad_norm": 0.9218307137489319, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.5615, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.15584415584415584, | |
| "grad_norm": 1.182883858680725, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.5296, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16623376623376623, | |
| "grad_norm": 1.2131173610687256, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.5056, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.17662337662337663, | |
| "grad_norm": 2.1901192665100098, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.4665, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.18701298701298702, | |
| "grad_norm": 2.1342835426330566, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.3724, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1974025974025974, | |
| "grad_norm": 2.6826727390289307, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.3278, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2077922077922078, | |
| "grad_norm": 3.3224539756774902, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.2767, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21818181818181817, | |
| "grad_norm": 4.129552364349365, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.3239, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 3.2705585956573486, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.2766, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.23896103896103896, | |
| "grad_norm": 3.935323476791382, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.2731, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.24935064935064935, | |
| "grad_norm": 3.1204378604888916, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.2364, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2597402597402597, | |
| "grad_norm": 2.0985143184661865, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.2235, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2597402597402597, | |
| "eval_loss": 0.2061881422996521, | |
| "eval_runtime": 2.0916, | |
| "eval_samples_per_second": 23.905, | |
| "eval_steps_per_second": 6.215, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2701298701298701, | |
| "grad_norm": 1.8239445686340332, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.1851, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2805194805194805, | |
| "grad_norm": 1.5958229303359985, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.181, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2909090909090909, | |
| "grad_norm": 1.5911153554916382, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.2248, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3012987012987013, | |
| "grad_norm": 1.8410097360610962, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.2173, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3116883116883117, | |
| "grad_norm": 1.519921064376831, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.2138, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3220779220779221, | |
| "grad_norm": 1.644580364227295, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.2149, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.33246753246753247, | |
| "grad_norm": 1.4669926166534424, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.1716, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.34285714285714286, | |
| "grad_norm": 1.3145791292190552, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.1769, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.35324675324675325, | |
| "grad_norm": 1.5595966577529907, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.1775, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 1.5390815734863281, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.1712, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.37402597402597404, | |
| "grad_norm": 1.0273857116699219, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.195, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.38441558441558443, | |
| "grad_norm": 0.9481903314590454, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.1387, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3948051948051948, | |
| "grad_norm": 1.0735758543014526, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.1442, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4051948051948052, | |
| "grad_norm": 1.3054051399230957, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.1906, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4155844155844156, | |
| "grad_norm": 1.3446217775344849, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.1826, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.42597402597402595, | |
| "grad_norm": 1.1781445741653442, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.1747, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.43636363636363634, | |
| "grad_norm": 1.1007606983184814, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.187, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.44675324675324674, | |
| "grad_norm": 1.232513666152954, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.1438, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 1.1253693103790283, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.1622, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4675324675324675, | |
| "grad_norm": 0.9642559885978699, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.1817, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4779220779220779, | |
| "grad_norm": 0.9171271324157715, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.1687, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4883116883116883, | |
| "grad_norm": 1.2926783561706543, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.1738, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4987012987012987, | |
| "grad_norm": 1.2792022228240967, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.2063, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.509090909090909, | |
| "grad_norm": 0.9798829555511475, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.1324, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5194805194805194, | |
| "grad_norm": 1.1944818496704102, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1829, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5194805194805194, | |
| "eval_loss": 0.11191346496343613, | |
| "eval_runtime": 2.1059, | |
| "eval_samples_per_second": 23.743, | |
| "eval_steps_per_second": 6.173, | |
| "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": 1.62480894509056e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |