| { | |
| "best_metric": 2.3883349895477295, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.099601593625498, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00199203187250996, | |
| "grad_norm": 3.060537099838257, | |
| "learning_rate": 2e-05, | |
| "loss": 2.6532, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00199203187250996, | |
| "eval_loss": 3.0966973304748535, | |
| "eval_runtime": 49.5482, | |
| "eval_samples_per_second": 17.074, | |
| "eval_steps_per_second": 2.139, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00398406374501992, | |
| "grad_norm": 2.955268383026123, | |
| "learning_rate": 4e-05, | |
| "loss": 2.5533, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00597609561752988, | |
| "grad_norm": 3.9355242252349854, | |
| "learning_rate": 6e-05, | |
| "loss": 2.5509, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00796812749003984, | |
| "grad_norm": 0.8899661302566528, | |
| "learning_rate": 8e-05, | |
| "loss": 2.3379, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0099601593625498, | |
| "grad_norm": 1.4026936292648315, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3826, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01195219123505976, | |
| "grad_norm": 1.3345900774002075, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.3676, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013944223107569721, | |
| "grad_norm": 0.6455169320106506, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.3442, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01593625498007968, | |
| "grad_norm": 0.6353403329849243, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.4438, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.017928286852589643, | |
| "grad_norm": 0.6737397313117981, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.3535, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0199203187250996, | |
| "grad_norm": 0.6299540996551514, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.4047, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021912350597609563, | |
| "grad_norm": 0.5763957500457764, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.3587, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02390438247011952, | |
| "grad_norm": 0.562707781791687, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.3096, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.025896414342629483, | |
| "grad_norm": 0.5606508255004883, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 2.3347, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.027888446215139442, | |
| "grad_norm": 0.5767633318901062, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.3877, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.029880478087649404, | |
| "grad_norm": 0.5732268691062927, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.3068, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03187250996015936, | |
| "grad_norm": 0.5585348606109619, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 2.4579, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03386454183266932, | |
| "grad_norm": 0.5565980672836304, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 2.2514, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.035856573705179286, | |
| "grad_norm": 0.6131947636604309, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 2.3154, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.037848605577689244, | |
| "grad_norm": 0.6132572293281555, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 2.3829, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0398406374501992, | |
| "grad_norm": 0.6029161214828491, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.3377, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04183266932270916, | |
| "grad_norm": 0.6010351181030273, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 2.291, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.043824701195219126, | |
| "grad_norm": 0.6133670806884766, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 2.3569, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.045816733067729085, | |
| "grad_norm": 0.6248342990875244, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.3803, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04780876494023904, | |
| "grad_norm": 0.6222149133682251, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 2.4423, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.049800796812749, | |
| "grad_norm": 0.6287333369255066, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 2.3078, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.049800796812749, | |
| "eval_loss": 2.398249864578247, | |
| "eval_runtime": 49.8315, | |
| "eval_samples_per_second": 16.977, | |
| "eval_steps_per_second": 2.127, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05179282868525897, | |
| "grad_norm": 0.6311869621276855, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 2.3933, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.053784860557768925, | |
| "grad_norm": 0.6403253674507141, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 2.4848, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.055776892430278883, | |
| "grad_norm": 0.6760746836662292, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 2.4764, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05776892430278884, | |
| "grad_norm": 0.6906132698059082, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 2.2475, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05976095617529881, | |
| "grad_norm": 0.7040736079216003, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 2.2269, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.061752988047808766, | |
| "grad_norm": 0.738384485244751, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 2.317, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06374501992031872, | |
| "grad_norm": 0.7270307540893555, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 2.4087, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06573705179282868, | |
| "grad_norm": 0.7789244055747986, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 2.3811, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06772908366533864, | |
| "grad_norm": 0.794619619846344, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 2.4352, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0697211155378486, | |
| "grad_norm": 0.8093376159667969, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.3914, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07171314741035857, | |
| "grad_norm": 0.852516770362854, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 2.5234, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07370517928286853, | |
| "grad_norm": 0.8440489172935486, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 2.3944, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07569721115537849, | |
| "grad_norm": 0.86625736951828, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 2.4375, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07768924302788845, | |
| "grad_norm": 0.8949872851371765, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 2.2835, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0796812749003984, | |
| "grad_norm": 0.9124184250831604, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 2.336, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08167330677290836, | |
| "grad_norm": 0.9732345342636108, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 2.3924, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.08366533864541832, | |
| "grad_norm": 1.0318710803985596, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 2.4338, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08565737051792828, | |
| "grad_norm": 1.102707028388977, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 2.5275, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.08764940239043825, | |
| "grad_norm": 1.0906025171279907, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 2.4058, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.08964143426294821, | |
| "grad_norm": 1.1357632875442505, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 2.3399, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09163346613545817, | |
| "grad_norm": 1.230342984199524, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 2.497, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.09362549800796813, | |
| "grad_norm": 1.4080559015274048, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 2.5829, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.09561752988047809, | |
| "grad_norm": 1.4965413808822632, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 2.5955, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.09760956175298804, | |
| "grad_norm": 2.0199639797210693, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 2.7102, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.099601593625498, | |
| "grad_norm": 3.439603090286255, | |
| "learning_rate": 0.0, | |
| "loss": 2.9058, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.099601593625498, | |
| "eval_loss": 2.3883349895477295, | |
| "eval_runtime": 49.826, | |
| "eval_samples_per_second": 16.979, | |
| "eval_steps_per_second": 2.127, | |
| "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": 5, | |
| "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": 4.659464274916147e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |