| { | |
| "best_metric": 0.3067149817943573, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.6096579476861166, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03219315895372234, | |
| "grad_norm": 7.228506088256836, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9318, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03219315895372234, | |
| "eval_loss": 3.1519806385040283, | |
| "eval_runtime": 0.9631, | |
| "eval_samples_per_second": 51.916, | |
| "eval_steps_per_second": 13.498, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06438631790744467, | |
| "grad_norm": 8.405563354492188, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2823, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.096579476861167, | |
| "grad_norm": 8.201285362243652, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.2725, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12877263581488935, | |
| "grad_norm": 6.827978134155273, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.7712, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.16096579476861167, | |
| "grad_norm": 14.890569686889648, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.5384, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.193158953722334, | |
| "grad_norm": 11.423808097839355, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.3692, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.22535211267605634, | |
| "grad_norm": 11.583919525146484, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.2147, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2575452716297787, | |
| "grad_norm": 16.652841567993164, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.0257, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.289738430583501, | |
| "grad_norm": 9.97889518737793, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.9631, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.32193158953722334, | |
| "grad_norm": 3.4204070568084717, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.8501, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.35412474849094566, | |
| "grad_norm": 3.8600399494171143, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.7688, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.386317907444668, | |
| "grad_norm": 3.5231199264526367, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.7531, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.41851106639839036, | |
| "grad_norm": 2.533519983291626, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.7246, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4507042253521127, | |
| "grad_norm": 2.216571092605591, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.698, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.482897384305835, | |
| "grad_norm": 2.351508855819702, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.65, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5150905432595574, | |
| "grad_norm": 4.128256320953369, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.5418, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5472837022132797, | |
| "grad_norm": 4.277278900146484, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.6646, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.579476861167002, | |
| "grad_norm": 3.5518879890441895, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.5931, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6116700201207244, | |
| "grad_norm": 2.786076068878174, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.5317, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6438631790744467, | |
| "grad_norm": 2.5530238151550293, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.5348, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.676056338028169, | |
| "grad_norm": 2.1127734184265137, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.5195, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7082494969818913, | |
| "grad_norm": 2.1813251972198486, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.5169, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7404426559356136, | |
| "grad_norm": 4.196330547332764, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.535, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.772635814889336, | |
| "grad_norm": 3.511094331741333, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.4127, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8048289738430584, | |
| "grad_norm": 3.1819417476654053, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.483, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8048289738430584, | |
| "eval_loss": 0.4331847131252289, | |
| "eval_runtime": 0.4863, | |
| "eval_samples_per_second": 102.816, | |
| "eval_steps_per_second": 26.732, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8370221327967807, | |
| "grad_norm": 2.261975049972534, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.4783, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.869215291750503, | |
| "grad_norm": 1.3807170391082764, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.4561, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9014084507042254, | |
| "grad_norm": 1.5317381620407104, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.4011, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9336016096579477, | |
| "grad_norm": 2.0689496994018555, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.4196, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.96579476861167, | |
| "grad_norm": 2.0331664085388184, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.4052, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9979879275653923, | |
| "grad_norm": 5.181220531463623, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.4492, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.0301810865191148, | |
| "grad_norm": 2.0923736095428467, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.544, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.062374245472837, | |
| "grad_norm": 1.3229002952575684, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.4147, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.0945674044265594, | |
| "grad_norm": 1.0754610300064087, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.3707, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.1267605633802817, | |
| "grad_norm": 0.7933202981948853, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.3393, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.158953722334004, | |
| "grad_norm": 0.7941595315933228, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.3655, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.1911468812877264, | |
| "grad_norm": 1.1384649276733398, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.332, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.2233400402414487, | |
| "grad_norm": 1.9317988157272339, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.397, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.255533199195171, | |
| "grad_norm": 1.4935693740844727, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.2746, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.2877263581488934, | |
| "grad_norm": 1.1563270092010498, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.3031, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.3199195171026157, | |
| "grad_norm": 1.0263022184371948, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.3415, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.352112676056338, | |
| "grad_norm": 0.9527009725570679, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.341, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.3843058350100603, | |
| "grad_norm": 0.8192784786224365, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.3399, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.4164989939637826, | |
| "grad_norm": 0.9891771674156189, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.312, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.448692152917505, | |
| "grad_norm": 1.3020000457763672, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.349, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.4808853118712273, | |
| "grad_norm": 1.8249863386154175, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.325, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.5130784708249498, | |
| "grad_norm": 0.9550820589065552, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.2643, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.545271629778672, | |
| "grad_norm": 1.160873293876648, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.3217, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.5774647887323945, | |
| "grad_norm": 1.0742133855819702, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.2941, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.6096579476861166, | |
| "grad_norm": 0.9035133719444275, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2899, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.6096579476861166, | |
| "eval_loss": 0.3067149817943573, | |
| "eval_runtime": 0.4865, | |
| "eval_samples_per_second": 102.782, | |
| "eval_steps_per_second": 26.723, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 2.95300912644096e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |