| { |
| "best_metric": 0.8826666666666667, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0744/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": 40.9777946472168, |
| "learning_rate": 0.0005, |
| "loss": 1.2142, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8301333333333333, |
| "eval_loss": 0.5310617089271545, |
| "eval_runtime": 7.1777, |
| "eval_samples_per_second": 522.455, |
| "eval_steps_per_second": 8.22, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 21.713335037231445, |
| "learning_rate": 0.0005, |
| "loss": 0.4119, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8669333333333333, |
| "eval_loss": 0.44267329573631287, |
| "eval_runtime": 7.2032, |
| "eval_samples_per_second": 520.605, |
| "eval_steps_per_second": 8.191, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 24.762353897094727, |
| "learning_rate": 0.0005, |
| "loss": 0.2713, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8690666666666667, |
| "eval_loss": 0.452734112739563, |
| "eval_runtime": 7.1373, |
| "eval_samples_per_second": 525.41, |
| "eval_steps_per_second": 8.266, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 20.715627670288086, |
| "learning_rate": 0.0005, |
| "loss": 0.2017, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8826666666666667, |
| "eval_loss": 0.4142524003982544, |
| "eval_runtime": 7.541, |
| "eval_samples_per_second": 497.285, |
| "eval_steps_per_second": 7.824, |
| "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 |
| } |
|
|
