| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.16447368421052633, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006578947368421052, | |
| "grad_norm": 4.683763027191162, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 10.3874, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006578947368421052, | |
| "eval_loss": 1.5863150358200073, | |
| "eval_runtime": 12.1886, | |
| "eval_samples_per_second": 10.584, | |
| "eval_steps_per_second": 5.333, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013157894736842105, | |
| "grad_norm": 4.751871109008789, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 11.8587, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.019736842105263157, | |
| "grad_norm": 5.826901435852051, | |
| "learning_rate": 0.0001, | |
| "loss": 12.0305, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02631578947368421, | |
| "grad_norm": 5.796934127807617, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 12.1736, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03289473684210526, | |
| "grad_norm": 5.535815715789795, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 10.7405, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.039473684210526314, | |
| "grad_norm": 5.5817975997924805, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.2704, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.046052631578947366, | |
| "grad_norm": 6.0977983474731445, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.8744, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 6.505789279937744, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 10.0401, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05921052631578947, | |
| "grad_norm": 5.587679386138916, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.4585, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06578947368421052, | |
| "grad_norm": 5.400643348693848, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 11.9279, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07236842105263158, | |
| "grad_norm": 5.925045013427734, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 8.0437, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07894736842105263, | |
| "grad_norm": 5.797214984893799, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.5078, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08552631578947369, | |
| "grad_norm": 5.878451347351074, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 11.8092, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09210526315789473, | |
| "grad_norm": 6.047119617462158, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 11.2271, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09868421052631579, | |
| "grad_norm": 6.350561618804932, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.6742, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 6.4842047691345215, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 9.9198, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1118421052631579, | |
| "grad_norm": 6.810247898101807, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 10.6038, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11842105263157894, | |
| "grad_norm": 5.906208515167236, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.2307, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 6.2693772315979, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 13.0133, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": 6.6559271812438965, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 10.8347, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13815789473684212, | |
| "grad_norm": 6.143450736999512, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 12.0125, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14473684210526316, | |
| "grad_norm": 6.3912224769592285, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 10.9285, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1513157894736842, | |
| "grad_norm": 7.889128684997559, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 11.2765, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 6.0514020919799805, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.144, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16447368421052633, | |
| "grad_norm": 7.878673553466797, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 11.0654, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16447368421052633, | |
| "eval_loss": 1.369149088859558, | |
| "eval_runtime": 12.2247, | |
| "eval_samples_per_second": 10.552, | |
| "eval_steps_per_second": 5.317, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.28694048489472e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |