| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.13513513513513514, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "eval_acc1": 92.08203125, | |
| "eval_acc5": 100.0, | |
| "eval_loss": 0.3436393737792969, | |
| "eval_runtime": 21.3181, | |
| "eval_samples_per_second": 164.696, | |
| "eval_steps_per_second": 0.657, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0, | |
| "loss": 0.4914, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_acc1": 95.21504211425781, | |
| "eval_acc5": 100.0, | |
| "eval_loss": 0.2510463297367096, | |
| "eval_runtime": 20.9889, | |
| "eval_samples_per_second": 167.279, | |
| "eval_steps_per_second": 0.667, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "step": 10, | |
| "total_flos": 0.0, | |
| "train_loss": 0.49140148162841796, | |
| "train_runtime": 64.5205, | |
| "train_samples_per_second": 39.677, | |
| "train_steps_per_second": 0.155 | |
| } | |
| ], | |
| "max_steps": 10, | |
| "num_train_epochs": 1, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |