| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0014675237005077632, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.9350474010155263e-05, | |
| "eval_loss": 10.37808895111084, | |
| "eval_runtime": 100.35, | |
| "eval_samples_per_second": 142.96, | |
| "eval_steps_per_second": 71.48, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001467523700507763, | |
| "grad_norm": 0.014386564493179321, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3771, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002935047401015526, | |
| "grad_norm": 0.016309218481183052, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3777, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0002935047401015526, | |
| "eval_loss": 10.377997398376465, | |
| "eval_runtime": 100.4509, | |
| "eval_samples_per_second": 142.816, | |
| "eval_steps_per_second": 71.408, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000440257110152329, | |
| "grad_norm": 0.01639426499605179, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3762, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005870094802031052, | |
| "grad_norm": 0.016688033938407898, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3767, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005870094802031052, | |
| "eval_loss": 10.377758026123047, | |
| "eval_runtime": 100.4749, | |
| "eval_samples_per_second": 142.782, | |
| "eval_steps_per_second": 71.391, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007337618502538816, | |
| "grad_norm": 0.01537470705807209, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.377, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.000880514220304658, | |
| "grad_norm": 0.014839538373053074, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3771, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.000880514220304658, | |
| "eval_loss": 10.377592086791992, | |
| "eval_runtime": 100.383, | |
| "eval_samples_per_second": 142.913, | |
| "eval_steps_per_second": 71.456, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0010272665903554342, | |
| "grad_norm": 0.017507759854197502, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3784, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0011740189604062105, | |
| "grad_norm": 0.013872073031961918, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3773, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0011740189604062105, | |
| "eval_loss": 10.3774995803833, | |
| "eval_runtime": 100.3481, | |
| "eval_samples_per_second": 142.962, | |
| "eval_steps_per_second": 71.481, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.001320771330456987, | |
| "grad_norm": 0.014722499996423721, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3786, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0014675237005077632, | |
| "grad_norm": 0.01600009948015213, | |
| "learning_rate": 0.0, | |
| "loss": 10.3749, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0014675237005077632, | |
| "eval_loss": 10.377484321594238, | |
| "eval_runtime": 100.0812, | |
| "eval_samples_per_second": 143.344, | |
| "eval_steps_per_second": 71.672, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1293090816000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |