| { | |
| "best_metric": 10.170746803283691, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.12463000467362517, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0024926000934725034, | |
| "grad_norm": 82.59060668945312, | |
| "learning_rate": 5e-05, | |
| "loss": 357.5612, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024926000934725034, | |
| "eval_loss": 11.167712211608887, | |
| "eval_runtime": 0.1498, | |
| "eval_samples_per_second": 333.835, | |
| "eval_steps_per_second": 86.797, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004985200186945007, | |
| "grad_norm": 82.80342864990234, | |
| "learning_rate": 0.0001, | |
| "loss": 357.614, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00747780028041751, | |
| "grad_norm": 82.21095275878906, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 357.1719, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009970400373890013, | |
| "grad_norm": 82.38631439208984, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 355.7737, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012463000467362517, | |
| "grad_norm": 82.47945404052734, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 354.6372, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01495560056083502, | |
| "grad_norm": 82.80762481689453, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 353.3369, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017448200654307525, | |
| "grad_norm": 83.37339782714844, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 352.1898, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019940800747780027, | |
| "grad_norm": 81.69036102294922, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 350.912, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022433400841252532, | |
| "grad_norm": 80.80045318603516, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 349.6108, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024926000934725034, | |
| "grad_norm": 78.37261199951172, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 348.746, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02741860102819754, | |
| "grad_norm": 76.90979766845703, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 347.4882, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02991120112167004, | |
| "grad_norm": 68.1639404296875, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 347.3174, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.032403801215142546, | |
| "grad_norm": 59.13226318359375, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 352.6354, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03489640130861505, | |
| "grad_norm": 79.52548217773438, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 342.4785, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.037389001402087556, | |
| "grad_norm": 77.67913055419922, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 341.5099, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.039881601495560054, | |
| "grad_norm": 75.87787628173828, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 340.3092, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04237420158903256, | |
| "grad_norm": 73.68025207519531, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 339.3081, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.044866801682505064, | |
| "grad_norm": 72.01408386230469, | |
| "learning_rate": 7.75e-05, | |
| "loss": 338.1043, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04735940177597757, | |
| "grad_norm": 69.32511138916016, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 337.5237, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04985200186945007, | |
| "grad_norm": 67.33868408203125, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 336.532, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05234460196292257, | |
| "grad_norm": 66.1492919921875, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 335.5211, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05483720205639508, | |
| "grad_norm": 63.94521713256836, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 334.999, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05732980214986758, | |
| "grad_norm": 59.73768997192383, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 334.8654, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05982240224334008, | |
| "grad_norm": 56.636207580566406, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 334.8942, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.062315002336812586, | |
| "grad_norm": 45.0466423034668, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 479.0131, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.062315002336812586, | |
| "eval_loss": 10.382533073425293, | |
| "eval_runtime": 0.1531, | |
| "eval_samples_per_second": 326.548, | |
| "eval_steps_per_second": 84.903, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06480760243028509, | |
| "grad_norm": 58.24401092529297, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 331.0769, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0673002025237576, | |
| "grad_norm": 57.016700744628906, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 330.4106, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0697928026172301, | |
| "grad_norm": 55.45833206176758, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 329.9051, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0722854027107026, | |
| "grad_norm": 53.81894302368164, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 329.6223, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07477800280417511, | |
| "grad_norm": 52.6780891418457, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 329.1109, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0772706028976476, | |
| "grad_norm": 51.28841781616211, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 328.8589, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07976320299112011, | |
| "grad_norm": 49.68301010131836, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 328.7733, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08225580308459261, | |
| "grad_norm": 48.246246337890625, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 328.7826, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08474840317806512, | |
| "grad_norm": 47.71107864379883, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 328.3093, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08724100327153762, | |
| "grad_norm": 44.84560775756836, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 329.2457, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08973360336501013, | |
| "grad_norm": 43.82417678833008, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 329.2555, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09222620345848263, | |
| "grad_norm": 41.64598083496094, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 330.7998, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09471880355195514, | |
| "grad_norm": 39.73112869262695, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 343.9659, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09721140364542763, | |
| "grad_norm": 45.642311096191406, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 325.8868, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09970400373890013, | |
| "grad_norm": 45.110870361328125, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 325.7518, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10219660383237264, | |
| "grad_norm": 44.50864028930664, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 325.5027, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10468920392584515, | |
| "grad_norm": 44.23891830444336, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 325.328, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10718180401931765, | |
| "grad_norm": 43.78203582763672, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 325.3905, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10967440411279016, | |
| "grad_norm": 42.987205505371094, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 325.5956, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11216700420626266, | |
| "grad_norm": 42.830806732177734, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 325.7647, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11465960429973517, | |
| "grad_norm": 42.426273345947266, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 325.6996, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11715220439320767, | |
| "grad_norm": 42.392818450927734, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 325.4753, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11964480448668016, | |
| "grad_norm": 39.53705978393555, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 327.3095, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12213740458015267, | |
| "grad_norm": 38.0192985534668, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 328.2975, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12463000467362517, | |
| "grad_norm": 36.17513656616211, | |
| "learning_rate": 1e-05, | |
| "loss": 334.8141, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12463000467362517, | |
| "eval_loss": 10.170746803283691, | |
| "eval_runtime": 0.1497, | |
| "eval_samples_per_second": 334.014, | |
| "eval_steps_per_second": 86.844, | |
| "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": 39843989028864.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |