| { |
| "best_metric": 0.9061333333333333, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0549/checkpoints/checkpoint-2331", |
| "epoch": 7.0, |
| "eval_steps": 500, |
| "global_step": 2331, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 2.37607479095459, |
| "learning_rate": 9.507764069616767e-05, |
| "loss": 1.4412, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8165333333333333, |
| "eval_loss": 0.6453579664230347, |
| "eval_runtime": 6.1408, |
| "eval_samples_per_second": 610.672, |
| "eval_steps_per_second": 9.608, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 4.8892741203308105, |
| "learning_rate": 8.122714722185695e-05, |
| "loss": 0.4595, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8458666666666667, |
| "eval_loss": 0.5236265063285828, |
| "eval_runtime": 5.7182, |
| "eval_samples_per_second": 655.798, |
| "eval_steps_per_second": 10.318, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.9596530795097351, |
| "learning_rate": 6.119173426442958e-05, |
| "loss": 0.2517, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8666666666666667, |
| "eval_loss": 0.4390570819377899, |
| "eval_runtime": 5.6467, |
| "eval_samples_per_second": 664.103, |
| "eval_steps_per_second": 10.449, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.15629169344902039, |
| "learning_rate": 3.893966107831872e-05, |
| "loss": 0.1276, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8802666666666666, |
| "eval_loss": 0.41293978691101074, |
| "eval_runtime": 5.6077, |
| "eval_samples_per_second": 668.724, |
| "eval_steps_per_second": 10.521, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 12.159905433654785, |
| "learning_rate": 1.887822366180192e-05, |
| "loss": 0.0574, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8981333333333333, |
| "eval_loss": 0.35833996534347534, |
| "eval_runtime": 5.643, |
| "eval_samples_per_second": 664.541, |
| "eval_steps_per_second": 10.455, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 1.8932682275772095, |
| "learning_rate": 4.980835732604045e-06, |
| "loss": 0.0226, |
| "step": 1998 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9032, |
| "eval_loss": 0.3556669354438782, |
| "eval_runtime": 5.6744, |
| "eval_samples_per_second": 660.858, |
| "eval_steps_per_second": 10.398, |
| "step": 1998 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 0.2523907423019409, |
| "learning_rate": 4.5410380539179233e-11, |
| "loss": 0.0114, |
| "step": 2331 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.9061333333333333, |
| "eval_loss": 0.34620368480682373, |
| "eval_runtime": 5.681, |
| "eval_samples_per_second": 660.093, |
| "eval_steps_per_second": 10.385, |
| "step": 2331 |
| } |
| ], |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.153189244358144e+19, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
