| { | |
| "best_metric": 1.5878689289093018, | |
| "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": 15.861693382263184, | |
| "learning_rate": 5e-05, | |
| "loss": 25.6742, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024926000934725034, | |
| "eval_loss": 2.1383278369903564, | |
| "eval_runtime": 3.5297, | |
| "eval_samples_per_second": 14.165, | |
| "eval_steps_per_second": 3.683, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004985200186945007, | |
| "grad_norm": 16.223535537719727, | |
| "learning_rate": 0.0001, | |
| "loss": 26.5887, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00747780028041751, | |
| "grad_norm": 14.062836647033691, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 26.0886, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009970400373890013, | |
| "grad_norm": 10.553086280822754, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 25.0048, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012463000467362517, | |
| "grad_norm": 25.181081771850586, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 26.4825, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01495560056083502, | |
| "grad_norm": 24.858774185180664, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 26.967, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017448200654307525, | |
| "grad_norm": 13.078153610229492, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 26.268, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019940800747780027, | |
| "grad_norm": 10.554128646850586, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 25.887, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022433400841252532, | |
| "grad_norm": 6.891944408416748, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 26.739, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024926000934725034, | |
| "grad_norm": 10.072796821594238, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 27.6732, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02741860102819754, | |
| "grad_norm": 12.784634590148926, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 27.863, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02991120112167004, | |
| "grad_norm": 13.896557807922363, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 28.4117, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.032403801215142546, | |
| "grad_norm": 11.378755569458008, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 27.947, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03489640130861505, | |
| "grad_norm": 10.711633682250977, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 22.6648, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.037389001402087556, | |
| "grad_norm": 8.984170913696289, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 22.5617, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.039881601495560054, | |
| "grad_norm": 6.228872776031494, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 22.9266, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04237420158903256, | |
| "grad_norm": 4.873310089111328, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 23.5637, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.044866801682505064, | |
| "grad_norm": 4.540409564971924, | |
| "learning_rate": 7.75e-05, | |
| "loss": 23.3018, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04735940177597757, | |
| "grad_norm": 5.02693510055542, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 23.6285, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04985200186945007, | |
| "grad_norm": 5.829559803009033, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 24.1336, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05234460196292257, | |
| "grad_norm": 5.613421440124512, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 23.9964, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05483720205639508, | |
| "grad_norm": 5.806504726409912, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 25.3697, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05732980214986758, | |
| "grad_norm": 8.350503921508789, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 25.5133, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05982240224334008, | |
| "grad_norm": 10.837132453918457, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 27.775, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.062315002336812586, | |
| "grad_norm": 17.211402893066406, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 29.4658, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.062315002336812586, | |
| "eval_loss": 1.6876567602157593, | |
| "eval_runtime": 3.5687, | |
| "eval_samples_per_second": 14.011, | |
| "eval_steps_per_second": 3.643, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06480760243028509, | |
| "grad_norm": 5.439934253692627, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 19.7855, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0673002025237576, | |
| "grad_norm": 4.207176685333252, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 20.4741, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0697928026172301, | |
| "grad_norm": 3.8984763622283936, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 20.3979, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0722854027107026, | |
| "grad_norm": 5.220901012420654, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 20.7536, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07477800280417511, | |
| "grad_norm": 5.235278129577637, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 20.9558, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0772706028976476, | |
| "grad_norm": 3.8804500102996826, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 22.0987, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07976320299112011, | |
| "grad_norm": 4.0022406578063965, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 21.0463, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08225580308459261, | |
| "grad_norm": 4.649126052856445, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 21.102, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08474840317806512, | |
| "grad_norm": 4.967099666595459, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 22.072, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08724100327153762, | |
| "grad_norm": 5.563882827758789, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 22.531, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08973360336501013, | |
| "grad_norm": 7.969014644622803, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 23.6819, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09222620345848263, | |
| "grad_norm": 10.51347541809082, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 25.2001, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09471880355195514, | |
| "grad_norm": 12.85457706451416, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 24.4643, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09721140364542763, | |
| "grad_norm": 3.841174602508545, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 18.7518, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09970400373890013, | |
| "grad_norm": 3.515620231628418, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 19.236, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10219660383237264, | |
| "grad_norm": 3.0310733318328857, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 19.8089, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10468920392584515, | |
| "grad_norm": 2.838557720184326, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 20.2579, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10718180401931765, | |
| "grad_norm": 3.141146659851074, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 20.6255, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10967440411279016, | |
| "grad_norm": 3.739708185195923, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 20.5905, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11216700420626266, | |
| "grad_norm": 4.207951068878174, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 21.4834, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11465960429973517, | |
| "grad_norm": 5.091900825500488, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 20.8686, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11715220439320767, | |
| "grad_norm": 5.662145137786865, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 22.0861, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11964480448668016, | |
| "grad_norm": 6.919090270996094, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 22.5946, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12213740458015267, | |
| "grad_norm": 8.793493270874023, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 23.2693, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12463000467362517, | |
| "grad_norm": 14.914314270019531, | |
| "learning_rate": 1e-05, | |
| "loss": 26.3377, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12463000467362517, | |
| "eval_loss": 1.5878689289093018, | |
| "eval_runtime": 3.7543, | |
| "eval_samples_per_second": 13.318, | |
| "eval_steps_per_second": 3.463, | |
| "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": 5.5762945316172595e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |