| { | |
| "best_metric": 1.2715656083628346e-08, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.168021680216802, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04336043360433604, | |
| "grad_norm": 371.2434387207031, | |
| "learning_rate": 5e-05, | |
| "loss": 205.3925, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04336043360433604, | |
| "eval_loss": 6.242215156555176, | |
| "eval_runtime": 3.0088, | |
| "eval_samples_per_second": 16.618, | |
| "eval_steps_per_second": 4.321, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08672086720867209, | |
| "grad_norm": 373.3104553222656, | |
| "learning_rate": 0.0001, | |
| "loss": 205.8218, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13008130081300814, | |
| "grad_norm": 383.17333984375, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 189.7029, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.17344173441734417, | |
| "grad_norm": 339.6163330078125, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 121.1905, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.21680216802168023, | |
| "grad_norm": 223.272216796875, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 74.4462, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2601626016260163, | |
| "grad_norm": 161.62481689453125, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 45.4484, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3035230352303523, | |
| "grad_norm": 152.62930297851562, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 23.4934, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.34688346883468835, | |
| "grad_norm": 84.8270263671875, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 9.2346, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 37.752017974853516, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 3.018, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.43360433604336046, | |
| "grad_norm": 11.284980773925781, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.6811, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.47696476964769646, | |
| "grad_norm": 2.51175594329834, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.1071, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5203252032520326, | |
| "grad_norm": 5.760996341705322, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.0338, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5636856368563685, | |
| "grad_norm": 0.04148336499929428, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.0011, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6070460704607046, | |
| "grad_norm": 0.010921904817223549, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0003, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6504065040650406, | |
| "grad_norm": 0.010230816900730133, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0002, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6937669376693767, | |
| "grad_norm": 0.010902239009737968, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0001, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7371273712737128, | |
| "grad_norm": 0.009099959395825863, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0001, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 0.02559913881123066, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0003, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8238482384823849, | |
| "grad_norm": 0.03879300877451897, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0003, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.8672086720867209, | |
| "grad_norm": 0.0037171724252402782, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9105691056910569, | |
| "grad_norm": 0.0010168474400416017, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.9539295392953929, | |
| "grad_norm": 0.0019982210360467434, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.997289972899729, | |
| "grad_norm": 0.0006124463980086148, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.040650406504065, | |
| "grad_norm": 0.0005714279250241816, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.084010840108401, | |
| "grad_norm": 0.00020625919569283724, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.084010840108401, | |
| "eval_loss": 4.371005957182206e-08, | |
| "eval_runtime": 3.0347, | |
| "eval_samples_per_second": 16.476, | |
| "eval_steps_per_second": 4.284, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.127371273712737, | |
| "grad_norm": 0.00014739223115611821, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.170731707317073, | |
| "grad_norm": 0.00013095480971969664, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.2140921409214092, | |
| "grad_norm": 8.817133493721485e-05, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.2574525745257452, | |
| "grad_norm": 0.0008000514935702085, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.3008130081300813, | |
| "grad_norm": 0.0004873626457992941, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.3441734417344173, | |
| "grad_norm": 7.253765943460166e-05, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.3875338753387534, | |
| "grad_norm": 5.642367614200339e-05, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.4308943089430894, | |
| "grad_norm": 0.00024370582832489163, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.4742547425474255, | |
| "grad_norm": 0.0003627138212323189, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.5176151761517616, | |
| "grad_norm": 0.0016840276075527072, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.5609756097560976, | |
| "grad_norm": 0.00012992291885893792, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.6043360433604335, | |
| "grad_norm": 3.316146103315987e-05, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.6476964769647697, | |
| "grad_norm": 0.000102144134871196, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.6910569105691056, | |
| "grad_norm": 0.00013834628043696284, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.7344173441734418, | |
| "grad_norm": 0.0001972516329260543, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.0009772982448339462, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.821138211382114, | |
| "grad_norm": 0.00010596256470307708, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.8644986449864498, | |
| "grad_norm": 3.764119173865765e-05, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.907859078590786, | |
| "grad_norm": 9.031497029354796e-05, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.951219512195122, | |
| "grad_norm": 0.00020561007841024548, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.994579945799458, | |
| "grad_norm": 0.0001520053920103237, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.037940379403794, | |
| "grad_norm": 0.00019084154337178916, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.08130081300813, | |
| "grad_norm": 5.529891495825723e-05, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.124661246612466, | |
| "grad_norm": 2.304013651155401e-05, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.168021680216802, | |
| "grad_norm": 7.780615851515904e-05, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.168021680216802, | |
| "eval_loss": 1.2715656083628346e-08, | |
| "eval_runtime": 3.0875, | |
| "eval_samples_per_second": 16.194, | |
| "eval_steps_per_second": 4.211, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 5.259156315439104e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |