| { | |
| "best_metric": 0.5926051735877991, | |
| "best_model_checkpoint": "./plant-classification/checkpoint-160", | |
| "epoch": 1.951219512195122, | |
| "global_step": 160, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001878048780487805, | |
| "loss": 2.4403, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.000175609756097561, | |
| "loss": 1.9498, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00016341463414634147, | |
| "loss": 1.5422, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00015121951219512197, | |
| "loss": 1.2802, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_accuracy": 0.7532467532467533, | |
| "eval_loss": 1.1777054071426392, | |
| "eval_runtime": 245.0854, | |
| "eval_samples_per_second": 2.199, | |
| "eval_steps_per_second": 0.277, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00013902439024390245, | |
| "loss": 1.1818, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00012682926829268293, | |
| "loss": 1.0576, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00011463414634146342, | |
| "loss": 0.9448, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0001024390243902439, | |
| "loss": 0.9498, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_accuracy": 0.8311688311688312, | |
| "eval_loss": 0.820961058139801, | |
| "eval_runtime": 244.7769, | |
| "eval_samples_per_second": 2.202, | |
| "eval_steps_per_second": 0.278, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 9.02439024390244e-05, | |
| "loss": 0.6939, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 7.804878048780489e-05, | |
| "loss": 0.6009, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 6.585365853658538e-05, | |
| "loss": 0.593, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 5.365853658536586e-05, | |
| "loss": 0.5132, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_accuracy": 0.8330241187384044, | |
| "eval_loss": 0.6491296887397766, | |
| "eval_runtime": 247.5801, | |
| "eval_samples_per_second": 2.177, | |
| "eval_steps_per_second": 0.275, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 4.146341463414634e-05, | |
| "loss": 0.5321, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.926829268292683e-05, | |
| "loss": 0.4869, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.707317073170732e-05, | |
| "loss": 0.4651, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 4.8780487804878055e-06, | |
| "loss": 0.5354, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.5926051735877991, | |
| "eval_runtime": 248.1335, | |
| "eval_samples_per_second": 2.172, | |
| "eval_steps_per_second": 0.274, | |
| "step": 160 | |
| } | |
| ], | |
| "max_steps": 164, | |
| "num_train_epochs": 2, | |
| "total_flos": 1.9809082826897818e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |