|
{ |
|
"best_metric": 1.631255865097046, |
|
"best_model_checkpoint": "detr-r50-cd45rb-8ah-6l\\checkpoint-46060", |
|
"epoch": 10.0, |
|
"global_step": 46060, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 8.003907946157187e-06, |
|
"loss": 2.4794, |
|
"step": 4606 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 1.8245322704315186, |
|
"eval_runtime": 201.5413, |
|
"eval_samples_per_second": 8.837, |
|
"eval_steps_per_second": 1.106, |
|
"step": 4606 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 6.004776378636562e-06, |
|
"loss": 2.2469, |
|
"step": 9212 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 1.7593357563018799, |
|
"eval_runtime": 206.2392, |
|
"eval_samples_per_second": 8.636, |
|
"eval_steps_per_second": 1.081, |
|
"step": 9212 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 4.005644811115936e-06, |
|
"loss": 2.1817, |
|
"step": 13818 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 1.7108566761016846, |
|
"eval_runtime": 206.9329, |
|
"eval_samples_per_second": 8.607, |
|
"eval_steps_per_second": 1.078, |
|
"step": 13818 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 2.0065132435953105e-06, |
|
"loss": 2.1418, |
|
"step": 18424 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_loss": 1.6976348161697388, |
|
"eval_runtime": 206.348, |
|
"eval_samples_per_second": 8.631, |
|
"eval_steps_per_second": 1.081, |
|
"step": 18424 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 6.947459834997829e-09, |
|
"loss": 2.118, |
|
"step": 23030 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_loss": 1.6694599390029907, |
|
"eval_runtime": 206.6437, |
|
"eval_samples_per_second": 8.619, |
|
"eval_steps_per_second": 1.079, |
|
"step": 23030 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"learning_rate": 4.003907946157187e-06, |
|
"loss": 2.1237, |
|
"step": 27636 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_loss": 1.6780959367752075, |
|
"eval_runtime": 207.7036, |
|
"eval_samples_per_second": 8.575, |
|
"eval_steps_per_second": 1.074, |
|
"step": 27636 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"learning_rate": 3.004342162396874e-06, |
|
"loss": 2.1025, |
|
"step": 32242 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_loss": 1.6574461460113525, |
|
"eval_runtime": 206.2072, |
|
"eval_samples_per_second": 8.637, |
|
"eval_steps_per_second": 1.081, |
|
"step": 32242 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"learning_rate": 2.0043421623968738e-06, |
|
"loss": 2.0796, |
|
"step": 36848 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_loss": 1.6417841911315918, |
|
"eval_runtime": 206.3439, |
|
"eval_samples_per_second": 8.631, |
|
"eval_steps_per_second": 1.081, |
|
"step": 36848 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"learning_rate": 1.0049934867564047e-06, |
|
"loss": 2.0672, |
|
"step": 41454 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_loss": 1.6333234310150146, |
|
"eval_runtime": 205.3701, |
|
"eval_samples_per_second": 8.672, |
|
"eval_steps_per_second": 1.086, |
|
"step": 41454 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 5.210594876248372e-09, |
|
"loss": 2.0597, |
|
"step": 46060 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"eval_loss": 1.631255865097046, |
|
"eval_runtime": 206.8618, |
|
"eval_samples_per_second": 8.61, |
|
"eval_steps_per_second": 1.078, |
|
"step": 46060 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"step": 46060, |
|
"total_flos": 8.803311016032e+19, |
|
"train_loss": 1.0432621427892965, |
|
"train_runtime": 14963.7217, |
|
"train_samples_per_second": 12.31, |
|
"train_steps_per_second": 3.078 |
|
} |
|
], |
|
"max_steps": 46060, |
|
"num_train_epochs": 10, |
|
"total_flos": 8.803311016032e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|