| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10354646647683148, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0020709293295366298, | |
| "grad_norm": 0.045056477189064026, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3707, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020709293295366298, | |
| "eval_loss": 10.361930847167969, | |
| "eval_runtime": 0.1159, | |
| "eval_samples_per_second": 431.312, | |
| "eval_steps_per_second": 112.141, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0041418586590732595, | |
| "grad_norm": 0.04978666082024574, | |
| "learning_rate": 0.0001, | |
| "loss": 10.37, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006212787988609888, | |
| "grad_norm": 0.05308021232485771, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.3674, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008283717318146519, | |
| "grad_norm": 0.05408896878361702, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.3666, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010354646647683147, | |
| "grad_norm": 0.06031319126486778, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.3655, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012425575977219777, | |
| "grad_norm": 0.0579414963722229, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.367, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014496505306756407, | |
| "grad_norm": 0.06090519577264786, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.3672, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.016567434636293038, | |
| "grad_norm": 0.05870482325553894, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.3643, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.018638363965829668, | |
| "grad_norm": 0.06792615354061127, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.3634, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020709293295366294, | |
| "grad_norm": 0.056748706847429276, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.3634, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.022780222624902924, | |
| "grad_norm": 0.06064929440617561, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.3615, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.024851151954439554, | |
| "grad_norm": 0.08019900321960449, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.353, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.026922081283976183, | |
| "grad_norm": 0.05464833229780197, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.3646, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.028993010613512813, | |
| "grad_norm": 0.05624043941497803, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.3657, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.031063939943049443, | |
| "grad_norm": 0.05316159501671791, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 10.368, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.033134869272586076, | |
| "grad_norm": 0.054998233914375305, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 10.3664, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0352057986021227, | |
| "grad_norm": 0.06356601417064667, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 10.363, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.037276727931659336, | |
| "grad_norm": 0.06791956722736359, | |
| "learning_rate": 7.75e-05, | |
| "loss": 10.3619, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03934765726119596, | |
| "grad_norm": 0.07910221815109253, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 10.3644, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04141858659073259, | |
| "grad_norm": 0.0784899890422821, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 10.3634, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04348951592026922, | |
| "grad_norm": 0.07258301228284836, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 10.3619, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04556044524980585, | |
| "grad_norm": 0.07916148751974106, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 10.358, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04763137457934248, | |
| "grad_norm": 0.06938778609037399, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 10.3541, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04970230390887911, | |
| "grad_norm": 0.08537527918815613, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 10.3491, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05177323323841574, | |
| "grad_norm": 0.09421907365322113, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 10.3459, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05177323323841574, | |
| "eval_loss": 10.354440689086914, | |
| "eval_runtime": 0.1021, | |
| "eval_samples_per_second": 489.586, | |
| "eval_steps_per_second": 127.292, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05384416256795237, | |
| "grad_norm": 0.07036886364221573, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 10.365, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.055915091897489, | |
| "grad_norm": 0.07155968248844147, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 10.3636, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.057986021227025626, | |
| "grad_norm": 0.07233037799596786, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 10.3615, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06005695055656226, | |
| "grad_norm": 0.07332813739776611, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 10.3617, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.062127879886098886, | |
| "grad_norm": 0.08408806473016739, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 10.3586, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06419880921563552, | |
| "grad_norm": 0.08621294796466827, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 10.3598, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06626973854517215, | |
| "grad_norm": 0.09366805106401443, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 10.3571, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06834066787470877, | |
| "grad_norm": 0.08554507046937943, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 10.3542, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0704115972042454, | |
| "grad_norm": 0.0863196849822998, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 10.358, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07248252653378204, | |
| "grad_norm": 0.07560539990663528, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 10.356, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07455345586331867, | |
| "grad_norm": 0.07912243157625198, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 10.3522, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07662438519285529, | |
| "grad_norm": 0.10135304182767868, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 10.3471, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07869531452239192, | |
| "grad_norm": 0.07534138858318329, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 10.3633, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08076624385192856, | |
| "grad_norm": 0.08607956022024155, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 10.3608, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.08283717318146518, | |
| "grad_norm": 0.08546745032072067, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 10.3591, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08490810251100181, | |
| "grad_norm": 0.08086901903152466, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 10.3608, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.08697903184053844, | |
| "grad_norm": 0.0830010324716568, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 10.3568, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08904996117007508, | |
| "grad_norm": 0.08770516514778137, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 10.3598, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0911208904996117, | |
| "grad_norm": 0.09759978950023651, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 10.3554, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.09319181982914833, | |
| "grad_norm": 0.09384226053953171, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 10.3581, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09526274915868496, | |
| "grad_norm": 0.08818507939577103, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 10.3546, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0973336784882216, | |
| "grad_norm": 0.09831733256578445, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 10.3542, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.09940460781775821, | |
| "grad_norm": 0.09170574694871902, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 10.353, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.10147553714729485, | |
| "grad_norm": 0.09404172748327255, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 10.3514, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.10354646647683148, | |
| "grad_norm": 0.11998723447322845, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3416, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10354646647683148, | |
| "eval_loss": 10.350510597229004, | |
| "eval_runtime": 0.1091, | |
| "eval_samples_per_second": 458.113, | |
| "eval_steps_per_second": 119.109, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "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": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |