| { | |
| "best_metric": 1.1219658851623535, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4022121669180493, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008044243338360985, | |
| "grad_norm": 276.51837158203125, | |
| "learning_rate": 5e-05, | |
| "loss": 58.2707, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008044243338360985, | |
| "eval_loss": 3.8774163722991943, | |
| "eval_runtime": 2.7573, | |
| "eval_samples_per_second": 18.134, | |
| "eval_steps_per_second": 4.715, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01608848667672197, | |
| "grad_norm": 341.03070068359375, | |
| "learning_rate": 0.0001, | |
| "loss": 58.4191, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.024132730015082957, | |
| "grad_norm": 165.2897491455078, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 41.7478, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03217697335344394, | |
| "grad_norm": 129.20782470703125, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 31.1492, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04022121669180493, | |
| "grad_norm": 97.55905151367188, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 27.2171, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.048265460030165915, | |
| "grad_norm": 68.95755767822266, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 27.3345, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0563097033685269, | |
| "grad_norm": 76.70074462890625, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 23.4648, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06435394670688788, | |
| "grad_norm": 56.85124588012695, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 22.4514, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07239819004524888, | |
| "grad_norm": 64.37816619873047, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 21.1626, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08044243338360986, | |
| "grad_norm": 56.276947021484375, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 20.2978, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08848667672197084, | |
| "grad_norm": 52.24300765991211, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 19.6329, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09653092006033183, | |
| "grad_norm": 52.54556655883789, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 20.5756, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10457516339869281, | |
| "grad_norm": 63.013954162597656, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 20.903, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1126194067370538, | |
| "grad_norm": 48.15736389160156, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 21.7344, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12066365007541478, | |
| "grad_norm": 84.32194519042969, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 22.2889, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12870789341377575, | |
| "grad_norm": 61.27325439453125, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 21.9157, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 55.58039855957031, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 23.2988, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14479638009049775, | |
| "grad_norm": 58.08642578125, | |
| "learning_rate": 7.75e-05, | |
| "loss": 20.7507, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15284062342885874, | |
| "grad_norm": 56.254878997802734, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 20.9819, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.16088486676721972, | |
| "grad_norm": 51.816707611083984, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 19.996, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1689291101055807, | |
| "grad_norm": 64.46934509277344, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 19.5894, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1769733534439417, | |
| "grad_norm": 56.03032684326172, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 18.6722, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.18501759678230267, | |
| "grad_norm": 51.18653106689453, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 20.3201, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.19306184012066366, | |
| "grad_norm": 49.40555953979492, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 19.6936, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.20110608345902464, | |
| "grad_norm": 47.789215087890625, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 17.5918, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.20110608345902464, | |
| "eval_loss": 1.1888800859451294, | |
| "eval_runtime": 2.8449, | |
| "eval_samples_per_second": 17.575, | |
| "eval_steps_per_second": 4.57, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.20915032679738563, | |
| "grad_norm": 56.16391372680664, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 20.0174, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2171945701357466, | |
| "grad_norm": 68.69602966308594, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 19.5351, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2252388134741076, | |
| "grad_norm": 62.31421661376953, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 18.7906, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.23328305681246858, | |
| "grad_norm": 53.402610778808594, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 18.4947, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.24132730015082957, | |
| "grad_norm": 70.05078125, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 20.6999, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.24937154348919055, | |
| "grad_norm": 54.77640151977539, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 20.1772, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2574157868275515, | |
| "grad_norm": 98.4924087524414, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 19.2579, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2654600301659125, | |
| "grad_norm": 53.991050720214844, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 18.3679, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 57.84612274169922, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 18.6821, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2815485168426345, | |
| "grad_norm": 90.99256134033203, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 17.9972, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2895927601809955, | |
| "grad_norm": 52.215545654296875, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 19.1813, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.29763700351935646, | |
| "grad_norm": 57.910064697265625, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 18.8931, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.30568124685771747, | |
| "grad_norm": 61.40287399291992, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 18.1066, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3137254901960784, | |
| "grad_norm": 68.80261993408203, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 19.6066, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.32176973353443944, | |
| "grad_norm": 76.48763275146484, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 18.5249, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3298139768728004, | |
| "grad_norm": 77.12066650390625, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 18.2736, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3378582202111614, | |
| "grad_norm": 56.564598083496094, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 19.7781, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.34590246354952237, | |
| "grad_norm": 54.434967041015625, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 18.5295, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3539467068878834, | |
| "grad_norm": 43.34243392944336, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 19.221, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.36199095022624433, | |
| "grad_norm": 49.38004684448242, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 18.6659, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.37003519356460535, | |
| "grad_norm": 47.048587799072266, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 19.2094, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3780794369029663, | |
| "grad_norm": 39.93241882324219, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 18.0108, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3861236802413273, | |
| "grad_norm": 31.25848388671875, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 17.8436, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3941679235796883, | |
| "grad_norm": 41.93825912475586, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 18.9396, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4022121669180493, | |
| "grad_norm": 42.091880798339844, | |
| "learning_rate": 1e-05, | |
| "loss": 17.6779, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4022121669180493, | |
| "eval_loss": 1.1219658851623535, | |
| "eval_runtime": 2.8474, | |
| "eval_samples_per_second": 17.56, | |
| "eval_steps_per_second": 4.566, | |
| "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": 5.658021338284032e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |