| { |
| "best_metric": 0.9501333333333334, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0868/checkpoints/checkpoint-1998", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 1998, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 3.989887237548828, |
| "learning_rate": 6.531088913245535e-05, |
| "loss": 0.6795, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9288, |
| "eval_loss": 0.2544325292110443, |
| "eval_runtime": 10.7201, |
| "eval_samples_per_second": 349.811, |
| "eval_steps_per_second": 5.504, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.14861595630645752, |
| "learning_rate": 5.2499999999999995e-05, |
| "loss": 0.1099, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9386666666666666, |
| "eval_loss": 0.21240019798278809, |
| "eval_runtime": 10.5568, |
| "eval_samples_per_second": 355.22, |
| "eval_steps_per_second": 5.589, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.02257157303392887, |
| "learning_rate": 3.5e-05, |
| "loss": 0.0336, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9405333333333333, |
| "eval_loss": 0.20791512727737427, |
| "eval_runtime": 10.5296, |
| "eval_samples_per_second": 356.138, |
| "eval_steps_per_second": 5.603, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.06165315583348274, |
| "learning_rate": 1.7500000000000005e-05, |
| "loss": 0.0089, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9498666666666666, |
| "eval_loss": 0.19978083670139313, |
| "eval_runtime": 10.5788, |
| "eval_samples_per_second": 354.481, |
| "eval_steps_per_second": 5.577, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.013658159412443638, |
| "learning_rate": 4.689110867544645e-06, |
| "loss": 0.004, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9482666666666667, |
| "eval_loss": 0.19659298658370972, |
| "eval_runtime": 10.5815, |
| "eval_samples_per_second": 354.392, |
| "eval_steps_per_second": 5.576, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.01935264840722084, |
| "learning_rate": 0.0, |
| "loss": 0.0027, |
| "step": 1998 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9501333333333334, |
| "eval_loss": 0.19581086933612823, |
| "eval_runtime": 10.5809, |
| "eval_samples_per_second": 354.412, |
| "eval_steps_per_second": 5.576, |
| "step": 1998 |
| } |
| ], |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9.88447923735552e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
