| { | |
| "best_metric": 0.8186666666666667, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0532/checkpoints/checkpoint-1332", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 1332, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 103.05448913574219, | |
| "learning_rate": 5.2499999999999995e-05, | |
| "loss": 3.4819, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5637333333333333, | |
| "eval_loss": 2.486497402191162, | |
| "eval_runtime": 13.4681, | |
| "eval_samples_per_second": 278.435, | |
| "eval_steps_per_second": 4.381, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 144.57040405273438, | |
| "learning_rate": 3.5e-05, | |
| "loss": 1.5427, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7714666666666666, | |
| "eval_loss": 0.9429396986961365, | |
| "eval_runtime": 13.5086, | |
| "eval_samples_per_second": 277.6, | |
| "eval_steps_per_second": 4.368, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 185.06271362304688, | |
| "learning_rate": 1.75e-05, | |
| "loss": 0.8712, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8101333333333334, | |
| "eval_loss": 0.7135725021362305, | |
| "eval_runtime": 14.3812, | |
| "eval_samples_per_second": 260.756, | |
| "eval_steps_per_second": 4.103, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 195.15550231933594, | |
| "learning_rate": 0.0, | |
| "loss": 0.7217, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8186666666666667, | |
| "eval_loss": 0.6642497777938843, | |
| "eval_runtime": 13.6774, | |
| "eval_samples_per_second": 274.175, | |
| "eval_steps_per_second": 4.314, | |
| "step": 1332 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1332, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.2705716958208e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |