| { |
| "best_metric": 0.904, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0113/checkpoints/checkpoint-1665", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 1665, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 99.47377014160156, |
| "learning_rate": 9.330127018922194e-05, |
| "loss": 2.6206, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7856, |
| "eval_loss": 0.8408695459365845, |
| "eval_runtime": 7.8032, |
| "eval_samples_per_second": 480.574, |
| "eval_steps_per_second": 7.561, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 162.46365356445312, |
| "learning_rate": 7.500000000000001e-05, |
| "loss": 0.6115, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8682666666666666, |
| "eval_loss": 0.4587727189064026, |
| "eval_runtime": 7.8484, |
| "eval_samples_per_second": 477.806, |
| "eval_steps_per_second": 7.517, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 79.1037368774414, |
| "learning_rate": 5e-05, |
| "loss": 0.3751, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8949333333333334, |
| "eval_loss": 0.3770202398300171, |
| "eval_runtime": 7.8426, |
| "eval_samples_per_second": 478.161, |
| "eval_steps_per_second": 7.523, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 32.4449462890625, |
| "learning_rate": 2.500000000000001e-05, |
| "loss": 0.275, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9018666666666667, |
| "eval_loss": 0.3432467579841614, |
| "eval_runtime": 7.8329, |
| "eval_samples_per_second": 478.748, |
| "eval_steps_per_second": 7.532, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 59.6260986328125, |
| "learning_rate": 6.698729810778065e-06, |
| "loss": 0.2199, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.904, |
| "eval_loss": 0.32820746302604675, |
| "eval_runtime": 7.9904, |
| "eval_samples_per_second": 469.314, |
| "eval_steps_per_second": 7.384, |
| "step": 1665 |
| } |
| ], |
| "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": 4.088214619776e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
