| { |
| "best_metric": 0.9496, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0567/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": 0.391593337059021, |
| "learning_rate": 9.330127018922194e-05, |
| "loss": 0.6071, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9184, |
| "eval_loss": 0.2801703214645386, |
| "eval_runtime": 11.006, |
| "eval_samples_per_second": 340.724, |
| "eval_steps_per_second": 5.361, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.01844128593802452, |
| "learning_rate": 7.500000000000001e-05, |
| "loss": 0.1246, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9274666666666667, |
| "eval_loss": 0.24184323847293854, |
| "eval_runtime": 10.5796, |
| "eval_samples_per_second": 354.455, |
| "eval_steps_per_second": 5.577, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 6.22901725769043, |
| "learning_rate": 5e-05, |
| "loss": 0.0407, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9397333333333333, |
| "eval_loss": 0.22854876518249512, |
| "eval_runtime": 10.3058, |
| "eval_samples_per_second": 363.874, |
| "eval_steps_per_second": 5.725, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.01756214164197445, |
| "learning_rate": 2.500000000000001e-05, |
| "loss": 0.0146, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9426666666666667, |
| "eval_loss": 0.22950071096420288, |
| "eval_runtime": 10.3553, |
| "eval_samples_per_second": 362.132, |
| "eval_steps_per_second": 5.698, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.03717679902911186, |
| "learning_rate": 6.698729810778065e-06, |
| "loss": 0.0043, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9496, |
| "eval_loss": 0.22032542526721954, |
| "eval_runtime": 10.3539, |
| "eval_samples_per_second": 362.182, |
| "eval_steps_per_second": 5.698, |
| "step": 1665 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1998, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "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 |
| } |
|
|
