| { | |
| "best_metric": 0.0053038992919027805, | |
| "best_model_checkpoint": "./vit_tickers_binaryclf/checkpoint-100", | |
| "epoch": 0.04149377593360996, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001991701244813278, | |
| "loss": 0.2137, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019834024896265561, | |
| "loss": 0.0368, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019751037344398342, | |
| "loss": 0.0196, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001966804979253112, | |
| "loss": 0.0094, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.000195850622406639, | |
| "loss": 0.0087, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001950207468879668, | |
| "loss": 0.0675, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019419087136929463, | |
| "loss": 0.0069, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019336099585062243, | |
| "loss": 0.0052, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019253112033195023, | |
| "loss": 0.0046, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019170124481327803, | |
| "loss": 0.0035, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_f1": 0.995004995004995, | |
| "eval_loss": 0.0053038992919027805, | |
| "eval_runtime": 89.5482, | |
| "eval_samples_per_second": 63.095, | |
| "eval_steps_per_second": 7.895, | |
| "step": 100 | |
| } | |
| ], | |
| "max_steps": 2410, | |
| "num_train_epochs": 1, | |
| "total_flos": 1.239871833833472e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |