| { | |
| "best_metric": 0.8896, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0559/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": 232.36160278320312, | |
| "learning_rate": 9e-05, | |
| "loss": 2.7281, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7762666666666667, | |
| "eval_loss": 0.839801013469696, | |
| "eval_runtime": 7.8425, | |
| "eval_samples_per_second": 478.166, | |
| "eval_steps_per_second": 7.523, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 110.48180389404297, | |
| "learning_rate": 9e-05, | |
| "loss": 0.6264, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8541333333333333, | |
| "eval_loss": 0.4764212667942047, | |
| "eval_runtime": 7.7006, | |
| "eval_samples_per_second": 486.976, | |
| "eval_steps_per_second": 7.662, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 114.79721069335938, | |
| "learning_rate": 9e-05, | |
| "loss": 0.3894, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8794666666666666, | |
| "eval_loss": 0.3910215497016907, | |
| "eval_runtime": 7.7365, | |
| "eval_samples_per_second": 484.718, | |
| "eval_steps_per_second": 7.626, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 100.42691040039062, | |
| "learning_rate": 9e-05, | |
| "loss": 0.2812, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8896, | |
| "eval_loss": 0.3581624925136566, | |
| "eval_runtime": 7.66, | |
| "eval_samples_per_second": 489.553, | |
| "eval_steps_per_second": 7.702, | |
| "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 | |
| } | |