|
{ |
|
"best_metric": 0.8869333333333334, |
|
"best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0294/checkpoints/checkpoint-999", |
|
"epoch": 3.0, |
|
"eval_steps": 500, |
|
"global_step": 999, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"grad_norm": 37.78125762939453, |
|
"learning_rate": 0.00025606601717798207, |
|
"loss": 1.6207, |
|
"step": 333 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.8250666666666666, |
|
"eval_loss": 0.58643639087677, |
|
"eval_runtime": 16.9706, |
|
"eval_samples_per_second": 220.97, |
|
"eval_steps_per_second": 3.477, |
|
"step": 333 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"grad_norm": 65.42376708984375, |
|
"learning_rate": 0.00015, |
|
"loss": 0.446, |
|
"step": 666 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.8722666666666666, |
|
"eval_loss": 0.42990630865097046, |
|
"eval_runtime": 17.6214, |
|
"eval_samples_per_second": 212.81, |
|
"eval_steps_per_second": 3.348, |
|
"step": 666 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"grad_norm": 40.66435623168945, |
|
"learning_rate": 4.3933982822017876e-05, |
|
"loss": 0.2402, |
|
"step": 999 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.8869333333333334, |
|
"eval_loss": 0.3746914565563202, |
|
"eval_runtime": 17.3532, |
|
"eval_samples_per_second": 216.098, |
|
"eval_steps_per_second": 3.4, |
|
"step": 999 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 1332, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 4, |
|
"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": 2.4529287718656e+18, |
|
"train_batch_size": 64, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|