| { |
| "best_metric": 0.8770666666666667, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0200/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": 0.995459258556366, |
| "learning_rate": 7e-05, |
| "loss": 0.7902, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8581333333333333, |
| "eval_loss": 0.46647170186042786, |
| "eval_runtime": 13.2153, |
| "eval_samples_per_second": 283.762, |
| "eval_steps_per_second": 4.465, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.6342968344688416, |
| "learning_rate": 7e-05, |
| "loss": 0.2759, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8589333333333333, |
| "eval_loss": 0.48971685767173767, |
| "eval_runtime": 13.0324, |
| "eval_samples_per_second": 287.744, |
| "eval_steps_per_second": 4.527, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 43.26783752441406, |
| "learning_rate": 7e-05, |
| "loss": 0.172, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8565333333333334, |
| "eval_loss": 0.532924234867096, |
| "eval_runtime": 12.8529, |
| "eval_samples_per_second": 291.763, |
| "eval_steps_per_second": 4.59, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.06227998435497284, |
| "learning_rate": 7e-05, |
| "loss": 0.1311, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8584, |
| "eval_loss": 0.5443786382675171, |
| "eval_runtime": 13.2264, |
| "eval_samples_per_second": 283.523, |
| "eval_steps_per_second": 4.461, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 9.866678237915039, |
| "learning_rate": 7e-05, |
| "loss": 0.1155, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8770666666666667, |
| "eval_loss": 0.49617499113082886, |
| "eval_runtime": 13.1187, |
| "eval_samples_per_second": 285.852, |
| "eval_steps_per_second": 4.497, |
| "step": 1665 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2997, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9, |
| "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": 8.2370660311296e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
