| { | |
| "best_metric": 0.07815484702587128, | |
| "best_model_checkpoint": "./vit-base-beans/checkpoint-80", | |
| "epoch": 3.6363636363636362, | |
| "global_step": 80, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00017727272727272728, | |
| "loss": 1.0553, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00015454545454545454, | |
| "loss": 0.5754, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0001318181818181818, | |
| "loss": 0.3398, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00010909090909090909, | |
| "loss": 0.1949, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.16914454102516174, | |
| "eval_runtime": 0.7601, | |
| "eval_samples_per_second": 32.891, | |
| "eval_steps_per_second": 5.263, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 8.636363636363637e-05, | |
| "loss": 0.1191, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 6.363636363636364e-05, | |
| "loss": 0.0847, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 4.0909090909090915e-05, | |
| "loss": 0.0727, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 0.0585, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.07815484702587128, | |
| "eval_runtime": 0.359, | |
| "eval_samples_per_second": 69.634, | |
| "eval_steps_per_second": 11.141, | |
| "step": 80 | |
| } | |
| ], | |
| "max_steps": 88, | |
| "num_train_epochs": 4, | |
| "total_flos": 9.872656444720742e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |