| { |
| "best_metric": 0.9517333333333333, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0152/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": 11.992453575134277, |
| "learning_rate": 6.125e-05, |
| "loss": 0.6704, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9370666666666667, |
| "eval_loss": 0.2349431961774826, |
| "eval_runtime": 7.4818, |
| "eval_samples_per_second": 501.214, |
| "eval_steps_per_second": 7.886, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.3094987869262695, |
| "learning_rate": 5.2499999999999995e-05, |
| "loss": 0.1033, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9424, |
| "eval_loss": 0.1960998922586441, |
| "eval_runtime": 7.2459, |
| "eval_samples_per_second": 517.535, |
| "eval_steps_per_second": 8.143, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.46896395087242126, |
| "learning_rate": 4.374999999999999e-05, |
| "loss": 0.0355, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9378666666666666, |
| "eval_loss": 0.23240768909454346, |
| "eval_runtime": 8.3137, |
| "eval_samples_per_second": 451.063, |
| "eval_steps_per_second": 7.097, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.026342779397964478, |
| "learning_rate": 3.5e-05, |
| "loss": 0.0131, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9432, |
| "eval_loss": 0.2329043298959732, |
| "eval_runtime": 6.4767, |
| "eval_samples_per_second": 579.0, |
| "eval_steps_per_second": 9.11, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.02381139248609543, |
| "learning_rate": 2.6249999999999998e-05, |
| "loss": 0.0048, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9498666666666666, |
| "eval_loss": 0.2158871740102768, |
| "eval_runtime": 7.4164, |
| "eval_samples_per_second": 505.635, |
| "eval_steps_per_second": 7.955, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.017770184203982353, |
| "learning_rate": 1.75e-05, |
| "loss": 0.0021, |
| "step": 1998 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9517333333333333, |
| "eval_loss": 0.21296058595180511, |
| "eval_runtime": 7.7997, |
| "eval_samples_per_second": 480.788, |
| "eval_steps_per_second": 7.564, |
| "step": 1998 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2664, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 8, |
| "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 |
| } |
|
|
