| { |
| "best_metric": 0.9408, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0994/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": 0.3271588385105133, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.6002, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9221333333333334, |
| "eval_loss": 0.26400327682495117, |
| "eval_runtime": 10.4098, |
| "eval_samples_per_second": 360.239, |
| "eval_steps_per_second": 5.668, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.4088621139526367, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.1331, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9269333333333334, |
| "eval_loss": 0.25214821100234985, |
| "eval_runtime": 10.3266, |
| "eval_samples_per_second": 363.14, |
| "eval_steps_per_second": 5.713, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.014552690088748932, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.0623, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9378666666666666, |
| "eval_loss": 0.2416219562292099, |
| "eval_runtime": 11.685, |
| "eval_samples_per_second": 320.926, |
| "eval_steps_per_second": 5.049, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.08816514909267426, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.0238, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9354666666666667, |
| "eval_loss": 0.2560092806816101, |
| "eval_runtime": 10.289, |
| "eval_samples_per_second": 364.466, |
| "eval_steps_per_second": 5.734, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 2.592259168624878, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.0074, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9408, |
| "eval_loss": 0.2391885668039322, |
| "eval_runtime": 10.5108, |
| "eval_samples_per_second": 356.777, |
| "eval_steps_per_second": 5.613, |
| "step": 1665 |
| } |
| ], |
| "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": 8.2370660311296e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
