| { | |
| "best_metric": 0.35768580436706543, | |
| "best_model_checkpoint": "attractive_faces_celebs_detection/checkpoint-11398", | |
| "epoch": 2.0, | |
| "global_step": 11398, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.60345435318999e-06, | |
| "loss": 0.4577, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.162848078956645e-06, | |
| "loss": 0.3936, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 8.7222418047233e-06, | |
| "loss": 0.3873, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.281635530489955e-06, | |
| "loss": 0.3764, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 7.841029256256609e-06, | |
| "loss": 0.3706, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 7.400422982023265e-06, | |
| "loss": 0.371, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 6.95981670778992e-06, | |
| "loss": 0.3661, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.519210433556575e-06, | |
| "loss": 0.3673, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 6.0786041593232295e-06, | |
| "loss": 0.3646, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 5.6379978850898845e-06, | |
| "loss": 0.3651, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 5.1973916108565395e-06, | |
| "loss": 0.3579, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.83035538005923, | |
| "eval_loss": 0.3584788739681244, | |
| "eval_runtime": 238.6769, | |
| "eval_samples_per_second": 84.885, | |
| "eval_steps_per_second": 21.221, | |
| "step": 5699 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.7567853366231936e-06, | |
| "loss": 0.3575, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.3161790623898485e-06, | |
| "loss": 0.3529, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.8755727881565035e-06, | |
| "loss": 0.3404, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.4349665139231585e-06, | |
| "loss": 0.3487, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.9943602396898134e-06, | |
| "loss": 0.3547, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.553753965456468e-06, | |
| "loss": 0.35, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.1131476912231233e-06, | |
| "loss": 0.3437, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 1.672541416989778e-06, | |
| "loss": 0.3479, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 1.231935142756433e-06, | |
| "loss": 0.3452, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 7.913288685230879e-07, | |
| "loss": 0.344, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 3.507225942897427e-07, | |
| "loss": 0.3415, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8329713721618953, | |
| "eval_loss": 0.35768580436706543, | |
| "eval_runtime": 239.4803, | |
| "eval_samples_per_second": 84.6, | |
| "eval_steps_per_second": 21.15, | |
| "step": 11398 | |
| } | |
| ], | |
| "max_steps": 11398, | |
| "num_train_epochs": 2, | |
| "total_flos": 2.825962378867018e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |