| { |
| "best_metric": 0.9312, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0489/checkpoints/checkpoint-1332", |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 1332, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.338900089263916, |
| "learning_rate": 7e-05, |
| "loss": 0.7139, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.924, |
| "eval_loss": 0.2672473192214966, |
| "eval_runtime": 4.1574, |
| "eval_samples_per_second": 901.999, |
| "eval_steps_per_second": 14.191, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 7.810544967651367, |
| "learning_rate": 7e-05, |
| "loss": 0.141, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9213333333333333, |
| "eval_loss": 0.28368666768074036, |
| "eval_runtime": 16.1893, |
| "eval_samples_per_second": 231.634, |
| "eval_steps_per_second": 3.644, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.03997994586825371, |
| "learning_rate": 7e-05, |
| "loss": 0.0659, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9282666666666667, |
| "eval_loss": 0.2853700518608093, |
| "eval_runtime": 4.4629, |
| "eval_samples_per_second": 840.263, |
| "eval_steps_per_second": 13.22, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.4413781762123108, |
| "learning_rate": 7e-05, |
| "loss": 0.0324, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9312, |
| "eval_loss": 0.27730244398117065, |
| "eval_runtime": 4.2316, |
| "eval_samples_per_second": 886.2, |
| "eval_steps_per_second": 13.943, |
| "step": 1332 |
| } |
| ], |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.58965282490368e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
