| { | |
| "best_metric": 0.8552, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0519/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": 120.55445098876953, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.8755, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7133333333333334, | |
| "eval_loss": 1.075509786605835, | |
| "eval_runtime": 13.4321, | |
| "eval_samples_per_second": 279.182, | |
| "eval_steps_per_second": 4.392, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 86.57672882080078, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.793, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8168, | |
| "eval_loss": 0.6264945268630981, | |
| "eval_runtime": 13.2773, | |
| "eval_samples_per_second": 282.438, | |
| "eval_steps_per_second": 4.444, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 78.28886413574219, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.5031, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8410666666666666, | |
| "eval_loss": 0.5079292058944702, | |
| "eval_runtime": 13.1299, | |
| "eval_samples_per_second": 285.608, | |
| "eval_steps_per_second": 4.494, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 75.15872955322266, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.401, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8552, | |
| "eval_loss": 0.4700816869735718, | |
| "eval_runtime": 13.5796, | |
| "eval_samples_per_second": 276.15, | |
| "eval_steps_per_second": 4.345, | |
| "step": 1332 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1665, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.2705716958208e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |