| { |
| "best_metric": 0.7157333333333333, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0955/checkpoints/checkpoint-999", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 999, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 124.85334777832031, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 3.6977, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5541333333333334, |
| "eval_loss": 3.2853853702545166, |
| "eval_runtime": 9.0174, |
| "eval_samples_per_second": 415.861, |
| "eval_steps_per_second": 6.543, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 98.25236511230469, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 2.4339, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.6674666666666667, |
| "eval_loss": 1.804331660270691, |
| "eval_runtime": 8.8024, |
| "eval_samples_per_second": 426.019, |
| "eval_steps_per_second": 6.703, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 158.86061096191406, |
| "learning_rate": 0.0, |
| "loss": 1.4645, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.7157333333333333, |
| "eval_loss": 1.359083890914917, |
| "eval_runtime": 8.8478, |
| "eval_samples_per_second": 423.836, |
| "eval_steps_per_second": 6.668, |
| "step": 999 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 999, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 2.4529287718656e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
