| { |
| "best_metric": 0.9437333333333333, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0320/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": 12.020645141601562, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.645, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9133333333333333, |
| "eval_loss": 0.29997381567955017, |
| "eval_runtime": 13.0456, |
| "eval_samples_per_second": 287.454, |
| "eval_steps_per_second": 4.523, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.03683370724320412, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.1499, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9213333333333333, |
| "eval_loss": 0.2723117768764496, |
| "eval_runtime": 13.04, |
| "eval_samples_per_second": 287.577, |
| "eval_steps_per_second": 4.525, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.05616510659456253, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.0735, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9250666666666667, |
| "eval_loss": 0.28449317812919617, |
| "eval_runtime": 13.0781, |
| "eval_samples_per_second": 286.739, |
| "eval_steps_per_second": 4.511, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.014232357032597065, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.0315, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.932, |
| "eval_loss": 0.2637251615524292, |
| "eval_runtime": 13.0249, |
| "eval_samples_per_second": 287.911, |
| "eval_steps_per_second": 4.53, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.014060921035706997, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.011, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9416, |
| "eval_loss": 0.23087777197360992, |
| "eval_runtime": 13.0148, |
| "eval_samples_per_second": 288.133, |
| "eval_steps_per_second": 4.533, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.008774442598223686, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.0053, |
| "step": 1998 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9437333333333333, |
| "eval_loss": 0.23553477227687836, |
| "eval_runtime": 13.0215, |
| "eval_samples_per_second": 287.985, |
| "eval_steps_per_second": 4.531, |
| "step": 1998 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2331, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 7, |
| "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": 9.88447923735552e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
