| { | |
| "best_metric": 0.4710754156112671, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.13788348845225784, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005515339538090314, | |
| "grad_norm": 92.3752670288086, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 14.1418, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005515339538090314, | |
| "eval_loss": 18.986474990844727, | |
| "eval_runtime": 2.072, | |
| "eval_samples_per_second": 24.132, | |
| "eval_steps_per_second": 6.274, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011030679076180628, | |
| "grad_norm": 92.41960144042969, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 14.1418, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.016546018614270942, | |
| "grad_norm": 91.83131408691406, | |
| "learning_rate": 0.0001, | |
| "loss": 9.4242, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.022061358152361255, | |
| "grad_norm": 17.633739471435547, | |
| "learning_rate": 9.997376600647783e-05, | |
| "loss": 5.9923, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.027576697690451568, | |
| "grad_norm": 9.156025886535645, | |
| "learning_rate": 9.989509461357426e-05, | |
| "loss": 4.2342, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.033092037228541885, | |
| "grad_norm": 14.200757026672363, | |
| "learning_rate": 9.976407754861426e-05, | |
| "loss": 5.1585, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.038607376766632194, | |
| "grad_norm": 11.900317192077637, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 6.826, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04412271630472251, | |
| "grad_norm": 12.914311408996582, | |
| "learning_rate": 9.934567829727386e-05, | |
| "loss": 6.2055, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04963805584281282, | |
| "grad_norm": 14.33440113067627, | |
| "learning_rate": 9.905878394570453e-05, | |
| "loss": 5.3226, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.055153395380903136, | |
| "grad_norm": 16.229171752929688, | |
| "learning_rate": 9.872051902290737e-05, | |
| "loss": 4.2126, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06066873491899345, | |
| "grad_norm": 18.343318939208984, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 2.8094, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06618407445708377, | |
| "grad_norm": 20.21609878540039, | |
| "learning_rate": 9.789151450663723e-05, | |
| "loss": 1.1322, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07169941399517407, | |
| "grad_norm": 8.667510986328125, | |
| "learning_rate": 9.740174149534693e-05, | |
| "loss": 1.199, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07721475353326439, | |
| "grad_norm": 16.896587371826172, | |
| "learning_rate": 9.686252995020249e-05, | |
| "loss": 2.4148, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0827300930713547, | |
| "grad_norm": 17.433048248291016, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 2.4726, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08824543260944502, | |
| "grad_norm": 18.047983169555664, | |
| "learning_rate": 9.563836295460398e-05, | |
| "loss": 2.1929, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09376077214753534, | |
| "grad_norm": 18.881397247314453, | |
| "learning_rate": 9.495483482810688e-05, | |
| "loss": 1.6352, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09927611168562564, | |
| "grad_norm": 16.9337158203125, | |
| "learning_rate": 9.422472115147382e-05, | |
| "loss": 0.8618, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10479145122371596, | |
| "grad_norm": 24.55199432373047, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.5281, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.11030679076180627, | |
| "grad_norm": 27.92365074157715, | |
| "learning_rate": 9.2628195591462e-05, | |
| "loss": 1.0844, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11582213029989659, | |
| "grad_norm": 26.889196395874023, | |
| "learning_rate": 9.176364518546989e-05, | |
| "loss": 1.218, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1213374698379869, | |
| "grad_norm": 26.291074752807617, | |
| "learning_rate": 9.08562300137157e-05, | |
| "loss": 1.0191, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1268528093760772, | |
| "grad_norm": 22.38892364501953, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 0.5982, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.13236814891416754, | |
| "grad_norm": 11.694781303405762, | |
| "learning_rate": 8.891708613973126e-05, | |
| "loss": 0.1916, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.13788348845225784, | |
| "grad_norm": 1.7668880224227905, | |
| "learning_rate": 8.788761839251559e-05, | |
| "loss": 0.025, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13788348845225784, | |
| "eval_loss": 0.4710754156112671, | |
| "eval_runtime": 2.0825, | |
| "eval_samples_per_second": 24.009, | |
| "eval_steps_per_second": 6.242, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 95, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.1240447254528e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |