| { | |
| "best_metric": 0.8981333333333333, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0549/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": 187.73239135742188, | |
| "learning_rate": 9e-05, | |
| "loss": 2.8965, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7528, | |
| "eval_loss": 1.013995885848999, | |
| "eval_runtime": 12.8512, | |
| "eval_samples_per_second": 291.802, | |
| "eval_steps_per_second": 4.591, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 75.77127838134766, | |
| "learning_rate": 9e-05, | |
| "loss": 0.6599, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8578666666666667, | |
| "eval_loss": 0.4667547643184662, | |
| "eval_runtime": 12.8169, | |
| "eval_samples_per_second": 292.582, | |
| "eval_steps_per_second": 4.603, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 100.58476257324219, | |
| "learning_rate": 9e-05, | |
| "loss": 0.381, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8778666666666667, | |
| "eval_loss": 0.3879088759422302, | |
| "eval_runtime": 12.8255, | |
| "eval_samples_per_second": 292.386, | |
| "eval_steps_per_second": 4.6, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 63.062320709228516, | |
| "learning_rate": 9e-05, | |
| "loss": 0.2629, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8981333333333333, | |
| "eval_loss": 0.34435221552848816, | |
| "eval_runtime": 12.6478, | |
| "eval_samples_per_second": 296.495, | |
| "eval_steps_per_second": 4.665, | |
| "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 | |
| } | |