| { |
| "best_metric": 0.8728, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0934/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": 5.8963141441345215, |
| "learning_rate": 0.0003, |
| "loss": 0.6743, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8568, |
| "eval_loss": 0.45808646082878113, |
| "eval_runtime": 13.3719, |
| "eval_samples_per_second": 280.438, |
| "eval_steps_per_second": 4.412, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.3345813751220703, |
| "learning_rate": 0.0003, |
| "loss": 0.3321, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8504, |
| "eval_loss": 0.4905170202255249, |
| "eval_runtime": 13.3698, |
| "eval_samples_per_second": 280.483, |
| "eval_steps_per_second": 4.413, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 4.335965633392334, |
| "learning_rate": 0.0003, |
| "loss": 0.2414, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8584, |
| "eval_loss": 0.4952050745487213, |
| "eval_runtime": 13.4316, |
| "eval_samples_per_second": 279.193, |
| "eval_steps_per_second": 4.393, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.2297867238521576, |
| "learning_rate": 0.0003, |
| "loss": 0.1989, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8626666666666667, |
| "eval_loss": 0.5066379308700562, |
| "eval_runtime": 13.3645, |
| "eval_samples_per_second": 280.595, |
| "eval_steps_per_second": 4.415, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 2.341506004333496, |
| "learning_rate": 0.0003, |
| "loss": 0.1653, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8728, |
| "eval_loss": 0.48815885186195374, |
| "eval_runtime": 13.2463, |
| "eval_samples_per_second": 283.099, |
| "eval_steps_per_second": 4.454, |
| "step": 1665 |
| } |
| ], |
| "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": 8.2370660311296e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
