| { | |
| "best_metric": 10.364083290100098, | |
| "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": 0.07003617286682129, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3766, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004655358026128197, | |
| "eval_loss": 10.37507438659668, | |
| "eval_runtime": 0.1041, | |
| "eval_samples_per_second": 480.247, | |
| "eval_steps_per_second": 124.864, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009310716052256394, | |
| "grad_norm": 0.06633172929286957, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3809, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001396607407838459, | |
| "grad_norm": 0.06385575979948044, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.3767, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018621432104512787, | |
| "grad_norm": 0.06392941623926163, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.3765, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0023276790130640984, | |
| "grad_norm": 0.06652949750423431, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.374, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002793214815676918, | |
| "grad_norm": 0.06727387756109238, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.3737, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003258750618289738, | |
| "grad_norm": 0.06856495887041092, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.3732, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0037242864209025574, | |
| "grad_norm": 0.0683828741312027, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.3749, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004189822223515377, | |
| "grad_norm": 0.07546210289001465, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.3734, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004655358026128197, | |
| "grad_norm": 0.07882942259311676, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.3742, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005120893828741016, | |
| "grad_norm": 0.08385184407234192, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.3728, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005586429631353836, | |
| "grad_norm": 0.07669893652200699, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.3744, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006051965433966656, | |
| "grad_norm": 0.07453416287899017, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.3744, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006517501236579476, | |
| "grad_norm": 0.07334843277931213, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.3745, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006983037039192295, | |
| "grad_norm": 0.07185767590999603, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 10.3732, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007448572841805115, | |
| "grad_norm": 0.07012451440095901, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 10.3732, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007914108644417935, | |
| "grad_norm": 0.07619670033454895, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 10.3738, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008379644447030755, | |
| "grad_norm": 0.08127602189779282, | |
| "learning_rate": 7.75e-05, | |
| "loss": 10.3711, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008845180249643574, | |
| "grad_norm": 0.08808059990406036, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 10.3702, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009310716052256394, | |
| "grad_norm": 0.08417017012834549, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 10.369, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009776251854869213, | |
| "grad_norm": 0.09743878245353699, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 10.3694, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010241787657482033, | |
| "grad_norm": 0.09524812549352646, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 10.3644, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.010707323460094852, | |
| "grad_norm": 0.09621316194534302, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 10.3679, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011172859262707672, | |
| "grad_norm": 0.11406976729631424, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 10.3716, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011638395065320493, | |
| "grad_norm": 0.12067130208015442, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 10.3726, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011638395065320493, | |
| "eval_loss": 10.368042945861816, | |
| "eval_runtime": 0.0906, | |
| "eval_samples_per_second": 551.66, | |
| "eval_steps_per_second": 143.432, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012103930867933313, | |
| "grad_norm": 0.088835708796978, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 10.3711, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.012569466670546132, | |
| "grad_norm": 0.08981330692768097, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 10.3715, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013035002473158952, | |
| "grad_norm": 0.09010516852140427, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 10.3703, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.013500538275771771, | |
| "grad_norm": 0.09101559221744537, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 10.3702, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01396607407838459, | |
| "grad_norm": 0.10025133192539215, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 10.366, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01443160988099741, | |
| "grad_norm": 0.10704360902309418, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 10.3676, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01489714568361023, | |
| "grad_norm": 0.1047937422990799, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 10.3676, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01536268148622305, | |
| "grad_norm": 0.11303725093603134, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 10.3647, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01582821728883587, | |
| "grad_norm": 0.1116722822189331, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 10.3672, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01629375309144869, | |
| "grad_norm": 0.11525017023086548, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 10.3665, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01675928889406151, | |
| "grad_norm": 0.1219276413321495, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 10.365, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01722482469667433, | |
| "grad_norm": 0.11378883570432663, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 10.3676, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01769036049928715, | |
| "grad_norm": 0.10344327986240387, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 10.3703, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.018155896301899968, | |
| "grad_norm": 0.10504771023988724, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 10.3691, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.018621432104512788, | |
| "grad_norm": 0.10149096697568893, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 10.3687, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.019086967907125607, | |
| "grad_norm": 0.10587392747402191, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 10.3699, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.019552503709738427, | |
| "grad_norm": 0.11104900389909744, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 10.3664, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.020018039512351246, | |
| "grad_norm": 0.11142737418413162, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 10.3642, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.020483575314964066, | |
| "grad_norm": 0.11694959551095963, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 10.3663, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.020949111117576885, | |
| "grad_norm": 0.12871791422367096, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 10.3631, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.021414646920189705, | |
| "grad_norm": 0.12332888692617416, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 10.3643, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.021880182722802524, | |
| "grad_norm": 0.1396578997373581, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 10.3664, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.022345718525415344, | |
| "grad_norm": 0.13164079189300537, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 10.3642, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.022811254328028163, | |
| "grad_norm": 0.13550512492656708, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 10.3674, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.023276790130640986, | |
| "grad_norm": 0.16089946031570435, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3669, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.023276790130640986, | |
| "eval_loss": 10.364083290100098, | |
| "eval_runtime": 0.0915, | |
| "eval_samples_per_second": 546.639, | |
| "eval_steps_per_second": 142.126, | |
| "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 | |
| } | |