| { | |
| "best_metric": 2.003491163253784, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.014900908955446282, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00029801817910892565, | |
| "grad_norm": 1.4378103017807007, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7429, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00029801817910892565, | |
| "eval_loss": 2.89186429977417, | |
| "eval_runtime": 2.9563, | |
| "eval_samples_per_second": 16.913, | |
| "eval_steps_per_second": 4.397, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005960363582178513, | |
| "grad_norm": 1.5283856391906738, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7683, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000894054537326777, | |
| "grad_norm": 1.417280673980713, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.7067, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011920727164357026, | |
| "grad_norm": 0.8284478187561035, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.5004, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014900908955446282, | |
| "grad_norm": 1.5029010772705078, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.5042, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001788109074653554, | |
| "grad_norm": 1.4401094913482666, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.4484, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0020861272537624795, | |
| "grad_norm": 1.0341869592666626, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.384, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0023841454328714052, | |
| "grad_norm": 0.655907928943634, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.3202, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002682163611980331, | |
| "grad_norm": 0.5951255559921265, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.3046, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0029801817910892563, | |
| "grad_norm": 0.6929669380187988, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.269, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003278199970198182, | |
| "grad_norm": 0.7978423833847046, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.3061, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003576218149307108, | |
| "grad_norm": 0.6575497388839722, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.2067, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003874236328416033, | |
| "grad_norm": 0.5472825169563293, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.3087, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004172254507524959, | |
| "grad_norm": 0.5186141729354858, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.1952, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004470272686633884, | |
| "grad_norm": 0.517930269241333, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.1748, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0047682908657428105, | |
| "grad_norm": 0.49700576066970825, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.1844, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.005066309044851736, | |
| "grad_norm": 0.5437249541282654, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.0521, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005364327223960662, | |
| "grad_norm": 0.48748552799224854, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.1151, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005662345403069587, | |
| "grad_norm": 0.5019696950912476, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.0675, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005960363582178513, | |
| "grad_norm": 0.48214608430862427, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.0507, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006258381761287439, | |
| "grad_norm": 0.46700602769851685, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.0569, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006556399940396364, | |
| "grad_norm": 0.49726152420043945, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.1015, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0068544181195052895, | |
| "grad_norm": 0.4804721474647522, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.0625, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.007152436298614216, | |
| "grad_norm": 0.5244660377502441, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.0452, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007450454477723141, | |
| "grad_norm": 0.5558761954307556, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.0891, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007450454477723141, | |
| "eval_loss": 2.087225914001465, | |
| "eval_runtime": 2.3411, | |
| "eval_samples_per_second": 21.358, | |
| "eval_steps_per_second": 5.553, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007748472656832066, | |
| "grad_norm": 0.47236016392707825, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.156, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.008046490835940992, | |
| "grad_norm": 0.5345865488052368, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.1204, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.008344509015049918, | |
| "grad_norm": 0.4965778887271881, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.0456, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.008642527194158844, | |
| "grad_norm": 0.45029252767562866, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 2.0003, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008940545373267769, | |
| "grad_norm": 0.4446468949317932, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.0242, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009238563552376695, | |
| "grad_norm": 0.48782452940940857, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.9474, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.009536581731485621, | |
| "grad_norm": 0.46959659457206726, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.9684, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.009834599910594547, | |
| "grad_norm": 0.4955771565437317, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 2.0053, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.010132618089703472, | |
| "grad_norm": 0.4691748023033142, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.9942, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.010430636268812398, | |
| "grad_norm": 0.5127565264701843, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 2.0143, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010728654447921324, | |
| "grad_norm": 0.516806423664093, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 2.0691, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.011026672627030248, | |
| "grad_norm": 0.533613920211792, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 2.0478, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.011324690806139175, | |
| "grad_norm": 0.42579934000968933, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.0956, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0116227089852481, | |
| "grad_norm": 0.4248853623867035, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.1222, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.011920727164357025, | |
| "grad_norm": 0.41036468744277954, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.0217, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.012218745343465951, | |
| "grad_norm": 0.42496877908706665, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 2.0106, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.012516763522574878, | |
| "grad_norm": 0.4574867784976959, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.9419, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.012814781701683802, | |
| "grad_norm": 0.4341859221458435, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.9376, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.013112799880792728, | |
| "grad_norm": 0.40266716480255127, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.0011, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.013410818059901655, | |
| "grad_norm": 0.4303281009197235, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.998, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.013708836239010579, | |
| "grad_norm": 0.4447619616985321, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.999, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.014006854418119505, | |
| "grad_norm": 0.4733419716358185, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 2.0109, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.014304872597228431, | |
| "grad_norm": 0.5527592301368713, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.956, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.014602890776337356, | |
| "grad_norm": 0.5123348832130432, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.9812, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.014900908955446282, | |
| "grad_norm": 0.5983260273933411, | |
| "learning_rate": 1e-05, | |
| "loss": 2.1283, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.014900908955446282, | |
| "eval_loss": 2.003491163253784, | |
| "eval_runtime": 2.3523, | |
| "eval_samples_per_second": 21.256, | |
| "eval_steps_per_second": 5.527, | |
| "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": 5.969951863666115e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |