| { |
| "best_metric": 0.9306666666666666, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0370/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": 15.979398727416992, |
| "learning_rate": 7e-05, |
| "loss": 0.7077, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9274666666666667, |
| "eval_loss": 0.25632378458976746, |
| "eval_runtime": 6.6323, |
| "eval_samples_per_second": 565.416, |
| "eval_steps_per_second": 8.896, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.7647436261177063, |
| "learning_rate": 7e-05, |
| "loss": 0.1382, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9298666666666666, |
| "eval_loss": 0.2452465295791626, |
| "eval_runtime": 6.2961, |
| "eval_samples_per_second": 595.604, |
| "eval_steps_per_second": 9.371, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.10529882460832596, |
| "learning_rate": 7e-05, |
| "loss": 0.0655, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9277333333333333, |
| "eval_loss": 0.2461380660533905, |
| "eval_runtime": 6.308, |
| "eval_samples_per_second": 594.486, |
| "eval_steps_per_second": 9.353, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.1081412136554718, |
| "learning_rate": 7e-05, |
| "loss": 0.037, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9288, |
| "eval_loss": 0.28756627440452576, |
| "eval_runtime": 6.3442, |
| "eval_samples_per_second": 591.095, |
| "eval_steps_per_second": 9.3, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.02238733135163784, |
| "learning_rate": 7e-05, |
| "loss": 0.0226, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9306666666666666, |
| "eval_loss": 0.3017961084842682, |
| "eval_runtime": 6.3, |
| "eval_samples_per_second": 595.238, |
| "eval_steps_per_second": 9.365, |
| "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 |
| } |
|
|
