| { |
| "best_metric": 0.8992, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0521/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": 31.072309494018555, |
| "learning_rate": 0.00025, |
| "loss": 1.5055, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8469333333333333, |
| "eval_loss": 0.5085816979408264, |
| "eval_runtime": 8.5251, |
| "eval_samples_per_second": 439.879, |
| "eval_steps_per_second": 6.921, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 61.0192756652832, |
| "learning_rate": 0.00019999999999999998, |
| "loss": 0.4053, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8618666666666667, |
| "eval_loss": 0.43962833285331726, |
| "eval_runtime": 8.3403, |
| "eval_samples_per_second": 449.626, |
| "eval_steps_per_second": 7.074, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 39.85857391357422, |
| "learning_rate": 0.00015, |
| "loss": 0.2443, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8816, |
| "eval_loss": 0.38223910331726074, |
| "eval_runtime": 8.6991, |
| "eval_samples_per_second": 431.08, |
| "eval_steps_per_second": 6.782, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 72.6639404296875, |
| "learning_rate": 9.999999999999999e-05, |
| "loss": 0.1537, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8992, |
| "eval_loss": 0.34266501665115356, |
| "eval_runtime": 8.1989, |
| "eval_samples_per_second": 457.38, |
| "eval_steps_per_second": 7.196, |
| "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 |
| } |
|
|
