|
{ |
|
"best_metric": 2.297297239303589, |
|
"best_model_checkpoint": "detr-r50-cd45rb-8ah-2l-corrected\\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": 9.00173686495875e-06, |
|
"loss": 3.7108, |
|
"step": 4606 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 2.788823366165161, |
|
"eval_runtime": 201.429, |
|
"eval_samples_per_second": 8.842, |
|
"eval_steps_per_second": 1.107, |
|
"step": 4606 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 8.001953973078594e-06, |
|
"loss": 3.3322, |
|
"step": 9212 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 2.5539309978485107, |
|
"eval_runtime": 191.3942, |
|
"eval_samples_per_second": 9.305, |
|
"eval_steps_per_second": 1.165, |
|
"step": 9212 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 7.002605297438124e-06, |
|
"loss": 3.2038, |
|
"step": 13818 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 2.472801446914673, |
|
"eval_runtime": 193.9159, |
|
"eval_samples_per_second": 9.184, |
|
"eval_steps_per_second": 1.15, |
|
"step": 13818 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 6.002605297438124e-06, |
|
"loss": 3.1338, |
|
"step": 18424 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_loss": 2.415332317352295, |
|
"eval_runtime": 200.4695, |
|
"eval_samples_per_second": 8.884, |
|
"eval_steps_per_second": 1.112, |
|
"step": 18424 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 5.003039513677812e-06, |
|
"loss": 3.0774, |
|
"step": 23030 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_loss": 2.405374526977539, |
|
"eval_runtime": 198.2697, |
|
"eval_samples_per_second": 8.983, |
|
"eval_steps_per_second": 1.125, |
|
"step": 23030 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"learning_rate": 4.003473729917499e-06, |
|
"loss": 3.0301, |
|
"step": 27636 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_loss": 2.347100257873535, |
|
"eval_runtime": 200.7358, |
|
"eval_samples_per_second": 8.872, |
|
"eval_steps_per_second": 1.111, |
|
"step": 27636 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"learning_rate": 3.00412505427703e-06, |
|
"loss": 2.9925, |
|
"step": 32242 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_loss": 2.33319091796875, |
|
"eval_runtime": 211.5504, |
|
"eval_samples_per_second": 8.419, |
|
"eval_steps_per_second": 1.054, |
|
"step": 32242 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"learning_rate": 2.0043421623968738e-06, |
|
"loss": 2.9639, |
|
"step": 36848 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_loss": 2.3220808506011963, |
|
"eval_runtime": 209.8171, |
|
"eval_samples_per_second": 8.488, |
|
"eval_steps_per_second": 1.063, |
|
"step": 36848 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"learning_rate": 1.0045592705167174e-06, |
|
"loss": 2.944, |
|
"step": 41454 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_loss": 2.308002471923828, |
|
"eval_runtime": 214.3311, |
|
"eval_samples_per_second": 8.31, |
|
"eval_steps_per_second": 1.04, |
|
"step": 41454 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 4.99348675640469e-09, |
|
"loss": 2.9248, |
|
"step": 46060 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"eval_loss": 2.297297239303589, |
|
"eval_runtime": 202.002, |
|
"eval_samples_per_second": 8.817, |
|
"eval_steps_per_second": 1.104, |
|
"step": 46060 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"step": 46060, |
|
"total_flos": 6.346863839946241e+19, |
|
"train_loss": 3.1313368644499024, |
|
"train_runtime": 27542.5728, |
|
"train_samples_per_second": 6.688, |
|
"train_steps_per_second": 1.672 |
|
} |
|
], |
|
"max_steps": 46060, |
|
"num_train_epochs": 10, |
|
"total_flos": 6.346863839946241e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|