| { | |
| "best_metric": 0.8688, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0627/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": 132.95437622070312, | |
| "learning_rate": 6.331559480312315e-05, | |
| "loss": 3.2648, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6536, | |
| "eval_loss": 1.7060596942901611, | |
| "eval_runtime": 7.4704, | |
| "eval_samples_per_second": 501.979, | |
| "eval_steps_per_second": 7.898, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 87.43492126464844, | |
| "learning_rate": 4.581559480312316e-05, | |
| "loss": 0.9652, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8181333333333334, | |
| "eval_loss": 0.6533979177474976, | |
| "eval_runtime": 7.5171, | |
| "eval_samples_per_second": 498.865, | |
| "eval_steps_per_second": 7.849, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 154.795654296875, | |
| "learning_rate": 2.4184405196876842e-05, | |
| "loss": 0.5261, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8501333333333333, | |
| "eval_loss": 0.5169150233268738, | |
| "eval_runtime": 7.5366, | |
| "eval_samples_per_second": 497.575, | |
| "eval_steps_per_second": 7.829, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 113.77701568603516, | |
| "learning_rate": 6.684405196876842e-06, | |
| "loss": 0.4081, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8688, | |
| "eval_loss": 0.4632032513618469, | |
| "eval_runtime": 7.5839, | |
| "eval_samples_per_second": 494.469, | |
| "eval_steps_per_second": 7.78, | |
| "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 | |
| } | |