| { |
| "best_metric": 0.9458666666666666, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0549/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": 2.156658411026001, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.6361, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9221333333333334, |
| "eval_loss": 0.26098117232322693, |
| "eval_runtime": 11.7788, |
| "eval_samples_per_second": 318.369, |
| "eval_steps_per_second": 5.009, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.06605652719736099, |
| "learning_rate": 8.122714722185695e-05, |
| "loss": 0.1627, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9213333333333333, |
| "eval_loss": 0.271833598613739, |
| "eval_runtime": 11.7825, |
| "eval_samples_per_second": 318.268, |
| "eval_steps_per_second": 5.007, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.23455910384655, |
| "learning_rate": 6.119173426442958e-05, |
| "loss": 0.0837, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9285333333333333, |
| "eval_loss": 0.2525620758533478, |
| "eval_runtime": 11.8513, |
| "eval_samples_per_second": 316.421, |
| "eval_steps_per_second": 4.978, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.049513235688209534, |
| "learning_rate": 3.893966107831872e-05, |
| "loss": 0.0373, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9365333333333333, |
| "eval_loss": 0.2386544644832611, |
| "eval_runtime": 12.0715, |
| "eval_samples_per_second": 310.649, |
| "eval_steps_per_second": 4.888, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.007493677083402872, |
| "learning_rate": 1.887822366180192e-05, |
| "loss": 0.0132, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9413333333333334, |
| "eval_loss": 0.21934093534946442, |
| "eval_runtime": 11.7282, |
| "eval_samples_per_second": 319.743, |
| "eval_steps_per_second": 5.031, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.1142546683549881, |
| "learning_rate": 4.980835732604045e-06, |
| "loss": 0.0064, |
| "step": 1998 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9458666666666666, |
| "eval_loss": 0.21871425211429596, |
| "eval_runtime": 11.8949, |
| "eval_samples_per_second": 315.261, |
| "eval_steps_per_second": 4.96, |
| "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 |
| } |
|
|
