| { |
| "best_metric": 0.9032, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0813/checkpoints/checkpoint-2997", |
| "epoch": 9.0, |
| "eval_steps": 500, |
| "global_step": 2997, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 5.608179569244385, |
| "learning_rate": 2.9095389311788626e-05, |
| "loss": 2.2858, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.772, |
| "eval_loss": 1.0615872144699097, |
| "eval_runtime": 9.2412, |
| "eval_samples_per_second": 405.79, |
| "eval_steps_per_second": 6.384, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 5.158117294311523, |
| "learning_rate": 2.649066664678467e-05, |
| "loss": 0.733, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8429333333333333, |
| "eval_loss": 0.5953142046928406, |
| "eval_runtime": 6.4644, |
| "eval_samples_per_second": 580.104, |
| "eval_steps_per_second": 9.127, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.144608497619629, |
| "learning_rate": 2.25e-05, |
| "loss": 0.4095, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8674666666666667, |
| "eval_loss": 0.47567370533943176, |
| "eval_runtime": 6.6962, |
| "eval_samples_per_second": 560.017, |
| "eval_steps_per_second": 8.811, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.6657236218452454, |
| "learning_rate": 1.760472266500396e-05, |
| "loss": 0.2583, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8789333333333333, |
| "eval_loss": 0.41896283626556396, |
| "eval_runtime": 6.4258, |
| "eval_samples_per_second": 583.586, |
| "eval_steps_per_second": 9.182, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.8856961727142334, |
| "learning_rate": 1.2395277334996045e-05, |
| "loss": 0.1667, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8896, |
| "eval_loss": 0.3780921697616577, |
| "eval_runtime": 6.271, |
| "eval_samples_per_second": 597.988, |
| "eval_steps_per_second": 9.408, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 3.5316805839538574, |
| "learning_rate": 7.500000000000004e-06, |
| "loss": 0.1069, |
| "step": 1998 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.8954666666666666, |
| "eval_loss": 0.3547556698322296, |
| "eval_runtime": 6.6352, |
| "eval_samples_per_second": 565.169, |
| "eval_steps_per_second": 8.892, |
| "step": 1998 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 2.0859780311584473, |
| "learning_rate": 3.519446655599853e-06, |
| "loss": 0.0695, |
| "step": 2331 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.8986666666666666, |
| "eval_loss": 0.356741726398468, |
| "eval_runtime": 6.3134, |
| "eval_samples_per_second": 593.973, |
| "eval_steps_per_second": 9.345, |
| "step": 2331 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.22913579642772675, |
| "learning_rate": 9.099962490342784e-07, |
| "loss": 0.049, |
| "step": 2664 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.8981333333333333, |
| "eval_loss": 0.3506309986114502, |
| "eval_runtime": 6.8979, |
| "eval_samples_per_second": 543.644, |
| "eval_steps_per_second": 8.553, |
| "step": 2664 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 1.5491360425949097, |
| "learning_rate": 8.24114362751871e-12, |
| "loss": 0.0414, |
| "step": 2997 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.9032, |
| "eval_loss": 0.34590741991996765, |
| "eval_runtime": 7.4357, |
| "eval_samples_per_second": 504.325, |
| "eval_steps_per_second": 7.935, |
| "step": 2997 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2997, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9, |
| "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": 1.482671885603328e+19, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
