| { |
| "best_metric": 0.9568, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0176/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": 0.34915345907211304, |
| "learning_rate": 8.554359905560886e-05, |
| "loss": 0.5851, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9349333333333333, |
| "eval_loss": 0.23471485078334808, |
| "eval_runtime": 7.6951, |
| "eval_samples_per_second": 487.321, |
| "eval_steps_per_second": 7.667, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.12741610407829285, |
| "learning_rate": 7.305704108364301e-05, |
| "loss": 0.1194, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9413333333333334, |
| "eval_loss": 0.2188463807106018, |
| "eval_runtime": 6.8653, |
| "eval_samples_per_second": 546.223, |
| "eval_steps_per_second": 8.594, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.029941780492663383, |
| "learning_rate": 5.501344202803415e-05, |
| "loss": 0.0529, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9474666666666667, |
| "eval_loss": 0.21127639710903168, |
| "eval_runtime": 7.3239, |
| "eval_samples_per_second": 512.025, |
| "eval_steps_per_second": 8.056, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.010094042867422104, |
| "learning_rate": 3.498655797196586e-05, |
| "loss": 0.0187, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9514666666666667, |
| "eval_loss": 0.2051754891872406, |
| "eval_runtime": 6.7984, |
| "eval_samples_per_second": 551.598, |
| "eval_steps_per_second": 8.678, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.032509926706552505, |
| "learning_rate": 1.6942958916356995e-05, |
| "loss": 0.0065, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9546666666666667, |
| "eval_loss": 0.20179493725299835, |
| "eval_runtime": 6.6414, |
| "eval_samples_per_second": 564.642, |
| "eval_steps_per_second": 8.884, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.04027043655514717, |
| "learning_rate": 4.456400944391144e-06, |
| "loss": 0.0034, |
| "step": 1998 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9568, |
| "eval_loss": 0.20129036903381348, |
| "eval_runtime": 7.0765, |
| "eval_samples_per_second": 529.92, |
| "eval_steps_per_second": 8.337, |
| "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 |
| } |
|
|
