| { | |
| "best_metric": 0.5279020071029663, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.05275652862041678, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010551305724083356, | |
| "grad_norm": 0.4281352460384369, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8965, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010551305724083356, | |
| "eval_loss": 0.9586341381072998, | |
| "eval_runtime": 4.169, | |
| "eval_samples_per_second": 11.993, | |
| "eval_steps_per_second": 3.118, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021102611448166712, | |
| "grad_norm": 0.29026857018470764, | |
| "learning_rate": 0.0001, | |
| "loss": 0.639, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0031653917172250064, | |
| "grad_norm": 0.3161293566226959, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.6838, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0042205222896333425, | |
| "grad_norm": 0.3332209885120392, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.6492, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005275652862041678, | |
| "grad_norm": 0.36165592074394226, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.7081, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006330783434450013, | |
| "grad_norm": 0.2794589102268219, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.6293, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0073859140068583485, | |
| "grad_norm": 0.2409287691116333, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.6119, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008441044579266685, | |
| "grad_norm": 0.2479231059551239, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.6632, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00949617515167502, | |
| "grad_norm": 0.2698189318180084, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.6301, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010551305724083356, | |
| "grad_norm": 0.31561294198036194, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.6754, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01160643629649169, | |
| "grad_norm": 0.37313395738601685, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.6542, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.012661566868900026, | |
| "grad_norm": 0.5618394613265991, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.7457, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013716697441308361, | |
| "grad_norm": 0.1917598992586136, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.7431, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.014771828013716697, | |
| "grad_norm": 0.31957706809043884, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.5296, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.015826958586125033, | |
| "grad_norm": 0.33083251118659973, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.5659, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01688208915853337, | |
| "grad_norm": 0.27629193663597107, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.5431, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.017937219730941704, | |
| "grad_norm": 0.1941889226436615, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.5402, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01899235030335004, | |
| "grad_norm": 0.17646503448486328, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.533, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.020047480875758375, | |
| "grad_norm": 0.1546628177165985, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.5383, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.021102611448166712, | |
| "grad_norm": 0.17784352600574493, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.5391, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022157742020575046, | |
| "grad_norm": 0.2392064332962036, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.5325, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02321287259298338, | |
| "grad_norm": 0.2687932848930359, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.5555, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.024268003165391717, | |
| "grad_norm": 0.3332011103630066, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.6259, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02532313373780005, | |
| "grad_norm": 0.3589456379413605, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.5674, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02637826431020839, | |
| "grad_norm": 0.6719586253166199, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.739, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02637826431020839, | |
| "eval_loss": 0.5484013557434082, | |
| "eval_runtime": 4.1219, | |
| "eval_samples_per_second": 12.13, | |
| "eval_steps_per_second": 3.154, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.027433394882616723, | |
| "grad_norm": 0.07289852946996689, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.5593, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02848852545502506, | |
| "grad_norm": 0.08839188516139984, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.4778, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.029543656027433394, | |
| "grad_norm": 0.11575295776128769, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.488, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03059878659984173, | |
| "grad_norm": 0.13782840967178345, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.4859, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.031653917172250065, | |
| "grad_norm": 0.1619933396577835, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.5444, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0327090477446584, | |
| "grad_norm": 0.16837561130523682, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.4611, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03376417831706674, | |
| "grad_norm": 0.20290729403495789, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.5121, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03481930888947507, | |
| "grad_norm": 0.1916610151529312, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.5318, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03587443946188341, | |
| "grad_norm": 0.1870730072259903, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.5786, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.036929570034291745, | |
| "grad_norm": 0.18408150970935822, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.5097, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03798470060670008, | |
| "grad_norm": 0.2160324901342392, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.5729, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03903983117910841, | |
| "grad_norm": 0.2902812063694, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.5586, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04009496175151675, | |
| "grad_norm": 0.08496986329555511, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.6287, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04115009232392509, | |
| "grad_norm": 0.07178401201963425, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.5104, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.042205222896333425, | |
| "grad_norm": 0.07889658957719803, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.4683, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.043260353468741755, | |
| "grad_norm": 0.09609430283308029, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.5244, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04431548404115009, | |
| "grad_norm": 0.10648704320192337, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.4995, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04537061461355843, | |
| "grad_norm": 0.10775868594646454, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.4853, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04642574518596676, | |
| "grad_norm": 0.11588826030492783, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.5183, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0474808757583751, | |
| "grad_norm": 0.12094197422266006, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.4873, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.048536006330783435, | |
| "grad_norm": 0.14708101749420166, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.5095, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04959113690319177, | |
| "grad_norm": 0.15230223536491394, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.4941, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0506462674756001, | |
| "grad_norm": 0.195496067404747, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.5174, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05170139804800844, | |
| "grad_norm": 0.2706495225429535, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.5762, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05275652862041678, | |
| "grad_norm": 0.5856199860572815, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6912, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05275652862041678, | |
| "eval_loss": 0.5279020071029663, | |
| "eval_runtime": 4.2496, | |
| "eval_samples_per_second": 11.766, | |
| "eval_steps_per_second": 3.059, | |
| "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": 5.2730742643359744e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |