| { |
| "best_metric": 0.9466666666666667, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0405/checkpoints/checkpoint-1998", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 1998, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 3.149702787399292, |
| "learning_rate": 8.554359905560886e-05, |
| "loss": 0.658, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9269333333333334, |
| "eval_loss": 0.24994851648807526, |
| "eval_runtime": 15.1867, |
| "eval_samples_per_second": 246.927, |
| "eval_steps_per_second": 3.885, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.06248142197728157, |
| "learning_rate": 7.305704108364301e-05, |
| "loss": 0.1505, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9261333333333334, |
| "eval_loss": 0.25508615374565125, |
| "eval_runtime": 13.4689, |
| "eval_samples_per_second": 278.419, |
| "eval_steps_per_second": 4.38, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.6035981178283691, |
| "learning_rate": 5.501344202803415e-05, |
| "loss": 0.0783, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9357333333333333, |
| "eval_loss": 0.22897091507911682, |
| "eval_runtime": 13.4584, |
| "eval_samples_per_second": 278.637, |
| "eval_steps_per_second": 4.384, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 2.1993515491485596, |
| "learning_rate": 3.498655797196586e-05, |
| "loss": 0.0349, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9392, |
| "eval_loss": 0.2194860577583313, |
| "eval_runtime": 13.3854, |
| "eval_samples_per_second": 280.155, |
| "eval_steps_per_second": 4.408, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.018878912553191185, |
| "learning_rate": 1.6942958916356995e-05, |
| "loss": 0.0162, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9442666666666667, |
| "eval_loss": 0.20987868309020996, |
| "eval_runtime": 13.3658, |
| "eval_samples_per_second": 280.568, |
| "eval_steps_per_second": 4.414, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.03677493333816528, |
| "learning_rate": 4.456400944391144e-06, |
| "loss": 0.0066, |
| "step": 1998 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9466666666666667, |
| "eval_loss": 0.21417169272899628, |
| "eval_runtime": 13.3804, |
| "eval_samples_per_second": 280.26, |
| "eval_steps_per_second": 4.409, |
| "step": 1998 |
| } |
| ], |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9.88447923735552e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
