| { |
| "best_metric": 0.908, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0653/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": 0.6023081541061401, |
| "learning_rate": 0.0004522542485937369, |
| "loss": 0.8608, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7981333333333334, |
| "eval_loss": 0.6725133657455444, |
| "eval_runtime": 11.2259, |
| "eval_samples_per_second": 334.048, |
| "eval_steps_per_second": 5.256, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.31951677799224854, |
| "learning_rate": 0.00032725424859373687, |
| "loss": 0.4447, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8248, |
| "eval_loss": 0.5977997183799744, |
| "eval_runtime": 12.0196, |
| "eval_samples_per_second": 311.99, |
| "eval_steps_per_second": 4.909, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.7919105887413025, |
| "learning_rate": 0.00017274575140626317, |
| "loss": 0.2236, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.868, |
| "eval_loss": 0.4641987979412079, |
| "eval_runtime": 10.9266, |
| "eval_samples_per_second": 343.2, |
| "eval_steps_per_second": 5.4, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.0659094974398613, |
| "learning_rate": 4.7745751406263163e-05, |
| "loss": 0.066, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8981333333333333, |
| "eval_loss": 0.3625294864177704, |
| "eval_runtime": 11.4378, |
| "eval_samples_per_second": 327.86, |
| "eval_steps_per_second": 5.158, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.1734384298324585, |
| "learning_rate": 0.0, |
| "loss": 0.0153, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.908, |
| "eval_loss": 0.3468440771102905, |
| "eval_runtime": 12.0489, |
| "eval_samples_per_second": 311.231, |
| "eval_steps_per_second": 4.897, |
| "step": 1665 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1665, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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": 8.2370660311296e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
