| { | |
| "best_metric": 2.6504759788513184, | |
| "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": 1.451959252357483, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8421, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024926000934725034, | |
| "eval_loss": 3.069533109664917, | |
| "eval_runtime": 1.2432, | |
| "eval_samples_per_second": 40.217, | |
| "eval_steps_per_second": 10.457, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004985200186945007, | |
| "grad_norm": 1.5435776710510254, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8506, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00747780028041751, | |
| "grad_norm": 1.144106149673462, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.8459, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009970400373890013, | |
| "grad_norm": 0.5294735431671143, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.803, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012463000467362517, | |
| "grad_norm": 0.6309822201728821, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.9006, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01495560056083502, | |
| "grad_norm": 0.7704012989997864, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.875, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017448200654307525, | |
| "grad_norm": 0.8097622990608215, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.8185, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019940800747780027, | |
| "grad_norm": 0.8507678508758545, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.8665, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022433400841252532, | |
| "grad_norm": 1.0542703866958618, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.7638, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024926000934725034, | |
| "grad_norm": 1.4424937963485718, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.9919, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02741860102819754, | |
| "grad_norm": 1.6479023694992065, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.8585, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02991120112167004, | |
| "grad_norm": 1.7326816320419312, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 3.0825, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.032403801215142546, | |
| "grad_norm": 0.6241318583488464, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.6639, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03489640130861505, | |
| "grad_norm": 0.6666032075881958, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.6416, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.037389001402087556, | |
| "grad_norm": 0.6706253290176392, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.7304, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.039881601495560054, | |
| "grad_norm": 0.6377014517784119, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.7324, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04237420158903256, | |
| "grad_norm": 0.592910647392273, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.7109, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.044866801682505064, | |
| "grad_norm": 0.5970917344093323, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.7792, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04735940177597757, | |
| "grad_norm": 0.5942250490188599, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.7483, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04985200186945007, | |
| "grad_norm": 0.6065579056739807, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.6064, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05234460196292257, | |
| "grad_norm": 0.7244961261749268, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.6762, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05483720205639508, | |
| "grad_norm": 0.9187153577804565, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.705, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05732980214986758, | |
| "grad_norm": 1.2696037292480469, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.7299, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05982240224334008, | |
| "grad_norm": 1.5416902303695679, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.5448, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.062315002336812586, | |
| "grad_norm": 2.0677273273468018, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.9451, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.062315002336812586, | |
| "eval_loss": 2.707570791244507, | |
| "eval_runtime": 0.723, | |
| "eval_samples_per_second": 69.159, | |
| "eval_steps_per_second": 17.981, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06480760243028509, | |
| "grad_norm": 0.45077604055404663, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.5811, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0673002025237576, | |
| "grad_norm": 0.3960801959037781, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.6605, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0697928026172301, | |
| "grad_norm": 0.40392717719078064, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.6883, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0722854027107026, | |
| "grad_norm": 0.4010487496852875, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 2.6943, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07477800280417511, | |
| "grad_norm": 0.44553473591804504, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.7217, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0772706028976476, | |
| "grad_norm": 0.47251877188682556, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 2.6897, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07976320299112011, | |
| "grad_norm": 0.483795166015625, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.5993, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08225580308459261, | |
| "grad_norm": 0.5359827876091003, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 2.6468, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08474840317806512, | |
| "grad_norm": 0.7356964349746704, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.6997, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08724100327153762, | |
| "grad_norm": 0.931477427482605, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 2.6975, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08973360336501013, | |
| "grad_norm": 1.087597131729126, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 2.6616, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09222620345848263, | |
| "grad_norm": 1.4653799533843994, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 2.6927, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09471880355195514, | |
| "grad_norm": 0.4064444601535797, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.5191, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09721140364542763, | |
| "grad_norm": 0.33260494470596313, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.6045, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09970400373890013, | |
| "grad_norm": 0.32690829038619995, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.5739, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10219660383237264, | |
| "grad_norm": 0.3391484320163727, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 2.6839, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10468920392584515, | |
| "grad_norm": 0.34284722805023193, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 2.6149, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10718180401931765, | |
| "grad_norm": 0.38321492075920105, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 2.7208, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10967440411279016, | |
| "grad_norm": 0.4366220235824585, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.7701, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11216700420626266, | |
| "grad_norm": 0.5214863419532776, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 2.5239, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11465960429973517, | |
| "grad_norm": 0.6461559534072876, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 2.6886, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11715220439320767, | |
| "grad_norm": 0.8496044874191284, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 2.6529, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11964480448668016, | |
| "grad_norm": 1.0152771472930908, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 2.5445, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12213740458015267, | |
| "grad_norm": 1.2712960243225098, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 2.4558, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12463000467362517, | |
| "grad_norm": 1.9823209047317505, | |
| "learning_rate": 1e-05, | |
| "loss": 2.7049, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12463000467362517, | |
| "eval_loss": 2.6504759788513184, | |
| "eval_runtime": 0.7137, | |
| "eval_samples_per_second": 70.058, | |
| "eval_steps_per_second": 18.215, | |
| "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": 2.54445405339648e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |