| { |
| "best_metric": 0.7962666666666667, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0822/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": 115.82193756103516, |
| "learning_rate": 5.2499999999999995e-05, |
| "loss": 3.2386, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.6664, |
| "eval_loss": 1.8044039011001587, |
| "eval_runtime": 8.2731, |
| "eval_samples_per_second": 453.279, |
| "eval_steps_per_second": 7.132, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 81.8346939086914, |
| "learning_rate": 1.7500000000000005e-05, |
| "loss": 1.1045, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.7842666666666667, |
| "eval_loss": 0.89820396900177, |
| "eval_runtime": 8.5386, |
| "eval_samples_per_second": 439.183, |
| "eval_steps_per_second": 6.91, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 121.43077850341797, |
| "learning_rate": 0.0, |
| "loss": 0.7859, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.7962666666666667, |
| "eval_loss": 0.7599657773971558, |
| "eval_runtime": 8.3827, |
| "eval_samples_per_second": 447.349, |
| "eval_steps_per_second": 7.038, |
| "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 |
| } |
|
|
