| { |
| "best_metric": 0.9210666666666667, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0539/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": 0.8611463904380798, |
| "learning_rate": 0.0004166666666666667, |
| "loss": 0.7962, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7957333333333333, |
| "eval_loss": 0.7331413626670837, |
| "eval_runtime": 12.2736, |
| "eval_samples_per_second": 305.535, |
| "eval_steps_per_second": 4.807, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 21.171125411987305, |
| "learning_rate": 0.0003333333333333333, |
| "loss": 0.3876, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8589333333333333, |
| "eval_loss": 0.4799041748046875, |
| "eval_runtime": 14.0704, |
| "eval_samples_per_second": 266.516, |
| "eval_steps_per_second": 4.193, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.07541902363300323, |
| "learning_rate": 0.00025, |
| "loss": 0.2063, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8768, |
| "eval_loss": 0.46129846572875977, |
| "eval_runtime": 14.1724, |
| "eval_samples_per_second": 264.598, |
| "eval_steps_per_second": 4.163, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 5.696136951446533, |
| "learning_rate": 0.00016666666666666666, |
| "loss": 0.0974, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8914666666666666, |
| "eval_loss": 0.419053316116333, |
| "eval_runtime": 13.1778, |
| "eval_samples_per_second": 284.57, |
| "eval_steps_per_second": 4.477, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.004495819564908743, |
| "learning_rate": 8.333333333333333e-05, |
| "loss": 0.0338, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9170666666666667, |
| "eval_loss": 0.35307928919792175, |
| "eval_runtime": 13.2388, |
| "eval_samples_per_second": 283.258, |
| "eval_steps_per_second": 4.457, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.03436153754591942, |
| "learning_rate": 0.0, |
| "loss": 0.0075, |
| "step": 1998 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9210666666666667, |
| "eval_loss": 0.33316609263420105, |
| "eval_runtime": 12.4253, |
| "eval_samples_per_second": 301.803, |
| "eval_steps_per_second": 4.748, |
| "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 |
| } |
|
|
