| { |
| "best_metric": 0.7912, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0463/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": 116.60176849365234, |
| "learning_rate": 4.522542485937369e-05, |
| "loss": 3.6505, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5170666666666667, |
| "eval_loss": 3.0610756874084473, |
| "eval_runtime": 8.1426, |
| "eval_samples_per_second": 460.542, |
| "eval_steps_per_second": 7.246, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 195.0125732421875, |
| "learning_rate": 3.272542485937369e-05, |
| "loss": 1.8143, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.7149333333333333, |
| "eval_loss": 1.2078837156295776, |
| "eval_runtime": 7.95, |
| "eval_samples_per_second": 471.701, |
| "eval_steps_per_second": 7.421, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 119.47186279296875, |
| "learning_rate": 1.7274575140626318e-05, |
| "loss": 0.961, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.7674666666666666, |
| "eval_loss": 0.8656033873558044, |
| "eval_runtime": 7.7674, |
| "eval_samples_per_second": 482.785, |
| "eval_steps_per_second": 7.596, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 393.1180114746094, |
| "learning_rate": 4.7745751406263165e-06, |
| "loss": 0.764, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.7869333333333334, |
| "eval_loss": 0.7642391324043274, |
| "eval_runtime": 7.6472, |
| "eval_samples_per_second": 490.375, |
| "eval_steps_per_second": 7.715, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 355.0673828125, |
| "learning_rate": 0.0, |
| "loss": 0.7206, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.7912, |
| "eval_loss": 0.7895246148109436, |
| "eval_runtime": 7.5932, |
| "eval_samples_per_second": 493.862, |
| "eval_steps_per_second": 7.77, |
| "step": 1665 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1665, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.088214619776e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
