detr-r50-cd45rb-8ah-6l-50q / trainer_state.json
polejowska's picture
End of training
0c4dfe2
{
"best_metric": 1.3713387250900269,
"best_model_checkpoint": "detr-r50-cd45rb-8ah-6l-50q\\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": 9.002171081198437e-06,
"loss": 2.6802,
"step": 4606
},
{
"epoch": 1.0,
"eval_loss": 1.6289299726486206,
"eval_runtime": 234.7675,
"eval_samples_per_second": 7.586,
"eval_steps_per_second": 0.95,
"step": 4606
},
{
"epoch": 2.0,
"learning_rate": 8.002171081198438e-06,
"loss": 2.4126,
"step": 9212
},
{
"epoch": 2.0,
"eval_loss": 1.5596286058425903,
"eval_runtime": 232.1594,
"eval_samples_per_second": 7.671,
"eval_steps_per_second": 0.961,
"step": 9212
},
{
"epoch": 3.0,
"learning_rate": 7.0028224055579685e-06,
"loss": 2.308,
"step": 13818
},
{
"epoch": 3.0,
"eval_loss": 1.4870882034301758,
"eval_runtime": 234.4645,
"eval_samples_per_second": 7.596,
"eval_steps_per_second": 0.951,
"step": 13818
},
{
"epoch": 4.0,
"learning_rate": 6.003039513677812e-06,
"loss": 2.2692,
"step": 18424
},
{
"epoch": 4.0,
"eval_loss": 1.4606939554214478,
"eval_runtime": 231.4388,
"eval_samples_per_second": 7.695,
"eval_steps_per_second": 0.964,
"step": 18424
},
{
"epoch": 5.0,
"learning_rate": 5.0034737299175e-06,
"loss": 2.2392,
"step": 23030
},
{
"epoch": 5.0,
"eval_loss": 1.4228224754333496,
"eval_runtime": 204.4774,
"eval_samples_per_second": 8.71,
"eval_steps_per_second": 1.091,
"step": 23030
},
{
"epoch": 6.0,
"learning_rate": 4.003690838037343e-06,
"loss": 2.1909,
"step": 27636
},
{
"epoch": 6.0,
"eval_loss": 1.4164729118347168,
"eval_runtime": 236.3511,
"eval_samples_per_second": 7.535,
"eval_steps_per_second": 0.944,
"step": 27636
},
{
"epoch": 7.0,
"learning_rate": 3.0039079461571864e-06,
"loss": 2.1743,
"step": 32242
},
{
"epoch": 7.0,
"eval_loss": 1.3968850374221802,
"eval_runtime": 236.4351,
"eval_samples_per_second": 7.533,
"eval_steps_per_second": 0.943,
"step": 32242
},
{
"epoch": 8.0,
"learning_rate": 2.0043421623968738e-06,
"loss": 2.1477,
"step": 36848
},
{
"epoch": 8.0,
"eval_loss": 1.3891478776931763,
"eval_runtime": 236.5509,
"eval_samples_per_second": 7.529,
"eval_steps_per_second": 0.943,
"step": 36848
},
{
"epoch": 9.0,
"learning_rate": 1.0049934867564047e-06,
"loss": 2.1356,
"step": 41454
},
{
"epoch": 9.0,
"eval_loss": 1.378079891204834,
"eval_runtime": 236.0898,
"eval_samples_per_second": 7.544,
"eval_steps_per_second": 0.945,
"step": 41454
},
{
"epoch": 10.0,
"learning_rate": 5.210594876248372e-09,
"loss": 2.125,
"step": 46060
},
{
"epoch": 10.0,
"eval_loss": 1.3713387250900269,
"eval_runtime": 238.472,
"eval_samples_per_second": 7.468,
"eval_steps_per_second": 0.935,
"step": 46060
},
{
"epoch": 10.0,
"step": 46060,
"total_flos": 8.803256478082562e+19,
"train_loss": 2.26826483543883,
"train_runtime": 34163.9546,
"train_samples_per_second": 5.392,
"train_steps_per_second": 1.348
}
],
"max_steps": 46060,
"num_train_epochs": 10,
"total_flos": 8.803256478082562e+19,
"trial_name": null,
"trial_params": null
}