| { |
| "best_metric": 0.9514666666666667, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0276/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": 0.2921385169029236, |
| "learning_rate": 8.397114317029975e-05, |
| "loss": 0.6362, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9208, |
| "eval_loss": 0.26804161071777344, |
| "eval_runtime": 6.3295, |
| "eval_samples_per_second": 592.467, |
| "eval_steps_per_second": 9.321, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 18.89255714416504, |
| "learning_rate": 6.756124916644227e-05, |
| "loss": 0.1468, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9392, |
| "eval_loss": 0.22345410287380219, |
| "eval_runtime": 7.1097, |
| "eval_samples_per_second": 527.445, |
| "eval_steps_per_second": 8.298, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.05850633606314659, |
| "learning_rate": 4.5070756562141305e-05, |
| "loss": 0.0642, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9450666666666667, |
| "eval_loss": 0.20822714269161224, |
| "eval_runtime": 6.5771, |
| "eval_samples_per_second": 570.156, |
| "eval_steps_per_second": 8.97, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 2.6928634643554688, |
| "learning_rate": 2.2561304794155375e-05, |
| "loss": 0.0233, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.948, |
| "eval_loss": 0.20811690390110016, |
| "eval_runtime": 6.3893, |
| "eval_samples_per_second": 586.923, |
| "eval_steps_per_second": 9.234, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.019678659737110138, |
| "learning_rate": 6.06428328578363e-06, |
| "loss": 0.0085, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9488, |
| "eval_loss": 0.19325514137744904, |
| "eval_runtime": 6.371, |
| "eval_samples_per_second": 588.6, |
| "eval_steps_per_second": 9.261, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.017939580604434013, |
| "learning_rate": 5.5627713115846694e-11, |
| "loss": 0.0047, |
| "step": 1998 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9514666666666667, |
| "eval_loss": 0.1830330342054367, |
| "eval_runtime": 6.7358, |
| "eval_samples_per_second": 556.726, |
| "eval_steps_per_second": 8.759, |
| "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 |
| } |
|
|
