| { |
| "best_metric": 0.9437333333333333, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0528/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": 7.848226070404053, |
| "learning_rate": 3e-05, |
| "loss": 1.224, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9261333333333334, |
| "eval_loss": 0.3061354458332062, |
| "eval_runtime": 13.0459, |
| "eval_samples_per_second": 287.447, |
| "eval_steps_per_second": 4.522, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 4.428913593292236, |
| "learning_rate": 3e-05, |
| "loss": 0.1825, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9394666666666667, |
| "eval_loss": 0.2248542159795761, |
| "eval_runtime": 12.2302, |
| "eval_samples_per_second": 306.618, |
| "eval_steps_per_second": 4.824, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.3008557856082916, |
| "learning_rate": 3e-05, |
| "loss": 0.0756, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9373333333333334, |
| "eval_loss": 0.22150476276874542, |
| "eval_runtime": 12.2812, |
| "eval_samples_per_second": 305.345, |
| "eval_steps_per_second": 4.804, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.06223846599459648, |
| "learning_rate": 3e-05, |
| "loss": 0.0348, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9386666666666666, |
| "eval_loss": 0.23609566688537598, |
| "eval_runtime": 12.0559, |
| "eval_samples_per_second": 311.052, |
| "eval_steps_per_second": 4.894, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.028237424790859222, |
| "learning_rate": 3e-05, |
| "loss": 0.016, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9437333333333333, |
| "eval_loss": 0.24176283180713654, |
| "eval_runtime": 12.1933, |
| "eval_samples_per_second": 307.547, |
| "eval_steps_per_second": 4.839, |
| "step": 1665 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1998, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "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 |
| } |
|
|
