| { | |
| "best_metric": 0.8784, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0686/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": 80.45594787597656, | |
| "learning_rate": 6.531088913245535e-05, | |
| "loss": 3.1734, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6954666666666667, | |
| "eval_loss": 1.5021666288375854, | |
| "eval_runtime": 7.0459, | |
| "eval_samples_per_second": 532.222, | |
| "eval_steps_per_second": 8.374, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 62.99401092529297, | |
| "learning_rate": 5.2499999999999995e-05, | |
| "loss": 0.8793, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8426666666666667, | |
| "eval_loss": 0.5368277430534363, | |
| "eval_runtime": 7.2472, | |
| "eval_samples_per_second": 517.439, | |
| "eval_steps_per_second": 8.141, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 155.7782440185547, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.4768, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8586666666666667, | |
| "eval_loss": 0.4688965380191803, | |
| "eval_runtime": 7.4092, | |
| "eval_samples_per_second": 506.125, | |
| "eval_steps_per_second": 7.963, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 156.42311096191406, | |
| "learning_rate": 1.7500000000000005e-05, | |
| "loss": 0.348, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8784, | |
| "eval_loss": 0.4125138819217682, | |
| "eval_runtime": 7.0267, | |
| "eval_samples_per_second": 533.676, | |
| "eval_steps_per_second": 8.397, | |
| "step": 1332 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1998, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "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 | |
| } | |