| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01365280906546522, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.82640453273261e-05, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 39.8428, | |
| "eval_samples_per_second": 154.808, | |
| "eval_steps_per_second": 77.404, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00034132022663663046, | |
| "grad_norm": 6.134134309832007e-06, | |
| "learning_rate": 5e-05, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006826404532732609, | |
| "grad_norm": 8.372618140128907e-06, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0010239606799098914, | |
| "grad_norm": 1.1834586075565312e-05, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 46.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013652809065465218, | |
| "grad_norm": 2.3055159545037895e-05, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 46.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0017066011331831525, | |
| "grad_norm": 1.307930415350711e-05, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 46.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0020479213598197828, | |
| "grad_norm": 2.247202974103857e-05, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 46.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0023892415864564132, | |
| "grad_norm": 2.9169659683248028e-05, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 46.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0027305618130930437, | |
| "grad_norm": 1.3439716894936282e-05, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 46.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0030718820397296746, | |
| "grad_norm": 2.1866031602257863e-05, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 46.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003413202266366305, | |
| "grad_norm": 0.00011945933511015028, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 46.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003413202266366305, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 39.8304, | |
| "eval_samples_per_second": 154.856, | |
| "eval_steps_per_second": 77.428, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0037545224930029355, | |
| "grad_norm": 8.429522495134734e-06, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 46.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0040958427196395655, | |
| "grad_norm": 0.00011730953701771796, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 46.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.004437162946276196, | |
| "grad_norm": 6.865215709694894e-06, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 46.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0047784831729128265, | |
| "grad_norm": 2.0274861526559107e-05, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 46.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.005119803399549457, | |
| "grad_norm": 1.2971031537745148e-05, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 46.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.005461123626186087, | |
| "grad_norm": 1.1721951523213647e-05, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 46.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.005802443852822719, | |
| "grad_norm": 2.270527693326585e-05, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 46.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.006143764079459349, | |
| "grad_norm": 2.3270096789929084e-05, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 46.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.00648508430609598, | |
| "grad_norm": 2.1603875211440027e-05, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 46.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.00682640453273261, | |
| "grad_norm": 8.086462185019627e-05, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 46.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.00682640453273261, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 39.8356, | |
| "eval_samples_per_second": 154.836, | |
| "eval_steps_per_second": 77.418, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0071677247593692405, | |
| "grad_norm": 6.222313459147699e-06, | |
| "learning_rate": 5e-05, | |
| "loss": 46.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.007509044986005871, | |
| "grad_norm": 7.018183623586083e-06, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 46.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0078503652126425, | |
| "grad_norm": 1.9251558114774525e-05, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 46.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.008191685439279131, | |
| "grad_norm": 1.491564489697339e-05, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 46.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.008533005665915762, | |
| "grad_norm": 9.031605259224307e-06, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 46.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.008874325892552392, | |
| "grad_norm": 3.6259119951864704e-05, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 46.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.009215646119189022, | |
| "grad_norm": 1.2036460248054937e-05, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 46.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.009556966345825653, | |
| "grad_norm": 2.4530565497116186e-05, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 46.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.009898286572462283, | |
| "grad_norm": 2.766398392850533e-05, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 46.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.010239606799098914, | |
| "grad_norm": 0.00010287680197507143, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 46.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.010239606799098914, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 39.858, | |
| "eval_samples_per_second": 154.749, | |
| "eval_steps_per_second": 77.375, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.010580927025735544, | |
| "grad_norm": 8.121592145471368e-06, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 46.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.010922247252372175, | |
| "grad_norm": 1.0248715625493787e-05, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 46.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.011263567479008805, | |
| "grad_norm": 1.2492489076976199e-05, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 46.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.011604887705645437, | |
| "grad_norm": 1.3179823326936457e-05, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 46.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.011946207932282068, | |
| "grad_norm": 1.670161509537138e-05, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 46.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.012287528158918698, | |
| "grad_norm": 1.661049827816896e-05, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 46.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.012628848385555329, | |
| "grad_norm": 2.649528323672712e-05, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 46.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.01297016861219196, | |
| "grad_norm": 2.0151897842879407e-05, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 46.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.01331148883882859, | |
| "grad_norm": 2.3215472538140602e-05, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 46.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.01365280906546522, | |
| "grad_norm": 0.00013992290769238025, | |
| "learning_rate": 0.0, | |
| "loss": 46.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01365280906546522, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 39.9188, | |
| "eval_samples_per_second": 154.514, | |
| "eval_steps_per_second": 77.257, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8088688656384.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |