| { | |
| "best_metric": 10.363058090209961, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.023276790130640986, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004655358026128197, | |
| "grad_norm": 0.06980670243501663, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3766, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004655358026128197, | |
| "eval_loss": 10.37507438659668, | |
| "eval_runtime": 0.1074, | |
| "eval_samples_per_second": 465.442, | |
| "eval_steps_per_second": 121.015, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009310716052256394, | |
| "grad_norm": 0.06614995747804642, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3809, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001396607407838459, | |
| "grad_norm": 0.06357283890247345, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.3767, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018621432104512787, | |
| "grad_norm": 0.06370236724615097, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.3765, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0023276790130640984, | |
| "grad_norm": 0.06445769220590591, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.374, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002793214815676918, | |
| "grad_norm": 0.06619281321763992, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.3736, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003258750618289738, | |
| "grad_norm": 0.0674276053905487, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.3731, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0037242864209025574, | |
| "grad_norm": 0.06736472994089127, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.3748, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004189822223515377, | |
| "grad_norm": 0.07391330599784851, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.3733, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004655358026128197, | |
| "grad_norm": 0.07708167284727097, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.3741, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005120893828741016, | |
| "grad_norm": 0.08154844492673874, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.3726, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005586429631353836, | |
| "grad_norm": 0.07513256371021271, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.3743, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006051965433966656, | |
| "grad_norm": 0.07839248329401016, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.3741, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006517501236579476, | |
| "grad_norm": 0.0781266838312149, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.3742, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006983037039192295, | |
| "grad_norm": 0.07699058204889297, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 10.3728, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007448572841805115, | |
| "grad_norm": 0.07425542920827866, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 10.3729, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007914108644417935, | |
| "grad_norm": 0.08060536533594131, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 10.3734, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008379644447030755, | |
| "grad_norm": 0.08557744324207306, | |
| "learning_rate": 7.75e-05, | |
| "loss": 10.3706, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008845180249643574, | |
| "grad_norm": 0.09127987921237946, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 10.3697, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009310716052256394, | |
| "grad_norm": 0.08883974701166153, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 10.3685, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009776251854869213, | |
| "grad_norm": 0.10015919059515, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 10.3688, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010241787657482033, | |
| "grad_norm": 0.09624467045068741, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 10.3639, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.010707323460094852, | |
| "grad_norm": 0.10034345835447311, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 10.3672, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011172859262707672, | |
| "grad_norm": 0.11496331542730331, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 10.371, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011638395065320493, | |
| "grad_norm": 0.12424255162477493, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 10.372, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011638395065320493, | |
| "eval_loss": 10.367488861083984, | |
| "eval_runtime": 0.1066, | |
| "eval_samples_per_second": 469.159, | |
| "eval_steps_per_second": 121.981, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012103930867933313, | |
| "grad_norm": 0.09990290552377701, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 10.3701, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.012569466670546132, | |
| "grad_norm": 0.09984984248876572, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 10.3706, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013035002473158952, | |
| "grad_norm": 0.09987977892160416, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 10.3693, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.013500538275771771, | |
| "grad_norm": 0.10009489953517914, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 10.3693, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01396607407838459, | |
| "grad_norm": 0.10767821967601776, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 10.3651, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01443160988099741, | |
| "grad_norm": 0.11570969969034195, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 10.3666, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01489714568361023, | |
| "grad_norm": 0.11085572093725204, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 10.3667, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01536268148622305, | |
| "grad_norm": 0.12019263952970505, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 10.3635, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01582821728883587, | |
| "grad_norm": 0.11959924548864365, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 10.366, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01629375309144869, | |
| "grad_norm": 0.12096071988344193, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 10.3655, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01675928889406151, | |
| "grad_norm": 0.12719549238681793, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 10.364, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01722482469667433, | |
| "grad_norm": 0.11730485409498215, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 10.3665, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01769036049928715, | |
| "grad_norm": 0.11693225800991058, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 10.3689, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.018155896301899968, | |
| "grad_norm": 0.1199287474155426, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 10.3677, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.018621432104512788, | |
| "grad_norm": 0.11629414558410645, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 10.3673, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.019086967907125607, | |
| "grad_norm": 0.1186600923538208, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 10.3685, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.019552503709738427, | |
| "grad_norm": 0.12448820471763611, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 10.365, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.020018039512351246, | |
| "grad_norm": 0.12146018445491791, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 10.3628, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.020483575314964066, | |
| "grad_norm": 0.1260601282119751, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 10.3651, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.020949111117576885, | |
| "grad_norm": 0.1349717080593109, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 10.3619, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.021414646920189705, | |
| "grad_norm": 0.13254471123218536, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 10.363, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.021880182722802524, | |
| "grad_norm": 0.14555320143699646, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 10.3652, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.022345718525415344, | |
| "grad_norm": 0.13951937854290009, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 10.3629, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.022811254328028163, | |
| "grad_norm": 0.1416473686695099, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 10.3661, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.023276790130640986, | |
| "grad_norm": 0.170250803232193, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3652, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.023276790130640986, | |
| "eval_loss": 10.363058090209961, | |
| "eval_runtime": 0.0961, | |
| "eval_samples_per_second": 520.394, | |
| "eval_steps_per_second": 135.302, | |
| "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": 42768059596800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |