| { | |
| "best_metric": 6.922262191772461, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.010162214346506104, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00020324428693012207, | |
| "grad_norm": 0.0864366888999939, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9387, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00020324428693012207, | |
| "eval_loss": 6.9412922859191895, | |
| "eval_runtime": 0.1152, | |
| "eval_samples_per_second": 433.952, | |
| "eval_steps_per_second": 112.828, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00040648857386024414, | |
| "grad_norm": 0.09229685366153717, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9386, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006097328607903663, | |
| "grad_norm": 0.08876536786556244, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 6.9382, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008129771477204883, | |
| "grad_norm": 0.09444393962621689, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.9385, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010162214346506103, | |
| "grad_norm": 0.09883809089660645, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 6.9373, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012194657215807325, | |
| "grad_norm": 0.10104647278785706, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 6.9395, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0014227100085108546, | |
| "grad_norm": 0.104464590549469, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 6.9373, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0016259542954409766, | |
| "grad_norm": 0.1082078069448471, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 6.9355, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0018291985823710986, | |
| "grad_norm": 0.11329925060272217, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 6.9349, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0020324428693012206, | |
| "grad_norm": 0.12252409011125565, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 6.932, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0022356871562313426, | |
| "grad_norm": 0.13089820742607117, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 6.9329, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002438931443161465, | |
| "grad_norm": 0.14660504460334778, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 6.9331, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002642175730091587, | |
| "grad_norm": 0.10294277966022491, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 6.9351, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002845420017021709, | |
| "grad_norm": 0.08976927399635315, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 6.9347, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003048664303951831, | |
| "grad_norm": 0.09647569060325623, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 6.9331, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003251908590881953, | |
| "grad_norm": 0.10085231810808182, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 6.9332, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.003455152877812075, | |
| "grad_norm": 0.099821537733078, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 6.9311, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003658397164742197, | |
| "grad_norm": 0.10807564109563828, | |
| "learning_rate": 7.75e-05, | |
| "loss": 6.9302, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003861641451672319, | |
| "grad_norm": 0.11626134067773819, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 6.9317, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004064885738602441, | |
| "grad_norm": 0.11859715729951859, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 6.9305, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004268130025532563, | |
| "grad_norm": 0.12148137390613556, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 6.9301, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004471374312462685, | |
| "grad_norm": 0.12696881592273712, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 6.9274, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004674618599392807, | |
| "grad_norm": 0.12968197464942932, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 6.9253, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00487786288632293, | |
| "grad_norm": 0.1422685831785202, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 6.928, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005081107173253052, | |
| "grad_norm": 0.16362857818603516, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 6.9261, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005081107173253052, | |
| "eval_loss": 6.928445339202881, | |
| "eval_runtime": 0.1168, | |
| "eval_samples_per_second": 428.252, | |
| "eval_steps_per_second": 111.345, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005284351460183174, | |
| "grad_norm": 0.10173824429512024, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 6.9298, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.005487595747113296, | |
| "grad_norm": 0.09903073310852051, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 6.9305, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.005690840034043418, | |
| "grad_norm": 0.1100124791264534, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 6.9288, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.00589408432097354, | |
| "grad_norm": 0.10994076728820801, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 6.9273, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.006097328607903662, | |
| "grad_norm": 0.11028490960597992, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 6.9263, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006300572894833784, | |
| "grad_norm": 0.12503692507743835, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 6.9262, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.006503817181763906, | |
| "grad_norm": 0.1286182403564453, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 6.9259, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.006707061468694028, | |
| "grad_norm": 0.1266760230064392, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 6.9235, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00691030575562415, | |
| "grad_norm": 0.13184915482997894, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 6.9238, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.007113550042554272, | |
| "grad_norm": 0.13333794474601746, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 6.9248, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007316794329484394, | |
| "grad_norm": 0.15316350758075714, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 6.9234, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.007520038616414516, | |
| "grad_norm": 0.16106532514095306, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 6.9206, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.007723282903344638, | |
| "grad_norm": 0.12021785229444504, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 6.9246, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.00792652719027476, | |
| "grad_norm": 0.11034441739320755, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 6.9263, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.008129771477204882, | |
| "grad_norm": 0.12417405098676682, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 6.9265, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008333015764135004, | |
| "grad_norm": 0.12451718002557755, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 6.9247, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.008536260051065126, | |
| "grad_norm": 0.12620998919010162, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 6.923, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.008739504337995248, | |
| "grad_norm": 0.13083547353744507, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 6.9236, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.00894274862492537, | |
| "grad_norm": 0.13513882458209991, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 6.9225, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.009145992911855493, | |
| "grad_norm": 0.13428464531898499, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 6.9205, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.009349237198785615, | |
| "grad_norm": 0.13905799388885498, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 6.9226, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.009552481485715738, | |
| "grad_norm": 0.13711297512054443, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 6.9225, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.00975572577264586, | |
| "grad_norm": 0.1469506174325943, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 6.9202, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.009958970059575982, | |
| "grad_norm": 0.15293125808238983, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 6.92, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.010162214346506104, | |
| "grad_norm": 0.1723209023475647, | |
| "learning_rate": 1e-05, | |
| "loss": 6.9183, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010162214346506104, | |
| "eval_loss": 6.922262191772461, | |
| "eval_runtime": 0.1192, | |
| "eval_samples_per_second": 419.437, | |
| "eval_steps_per_second": 109.054, | |
| "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": 5705957376000.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |