| { | |
| "best_metric": 0.7994666666666667, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0788/checkpoints/checkpoint-666", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 666, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 149.30809020996094, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8076, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7392, | |
| "eval_loss": 1.1174710988998413, | |
| "eval_runtime": 12.4369, | |
| "eval_samples_per_second": 301.522, | |
| "eval_steps_per_second": 4.744, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 65.68598937988281, | |
| "learning_rate": 0.0, | |
| "loss": 0.9113, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7994666666666667, | |
| "eval_loss": 0.7987316250801086, | |
| "eval_runtime": 12.536, | |
| "eval_samples_per_second": 299.137, | |
| "eval_steps_per_second": 4.706, | |
| "step": 666 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 666, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1.6352858479104e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |