detr-r50-cd45rb-4ah-12l / trainer_state.json
polejowska's picture
End of training
dae98cb
{
"best_metric": 2.129838705062866,
"best_model_checkpoint": "detr-r50-cd45rb-4ah-12l\\checkpoint-23030",
"epoch": 5.0,
"global_step": 23030,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 8.004776378636561e-06,
"loss": 3.6967,
"step": 4606
},
{
"epoch": 1.0,
"eval_loss": 2.725353956222534,
"eval_runtime": 377.8115,
"eval_samples_per_second": 4.714,
"eval_steps_per_second": 0.59,
"step": 4606
},
{
"epoch": 2.0,
"learning_rate": 6.005210594876249e-06,
"loss": 3.2687,
"step": 9212
},
{
"epoch": 2.0,
"eval_loss": 2.4866549968719482,
"eval_runtime": 379.2433,
"eval_samples_per_second": 4.696,
"eval_steps_per_second": 0.588,
"step": 9212
},
{
"epoch": 3.0,
"learning_rate": 4.006079027355623e-06,
"loss": 3.0302,
"step": 13818
},
{
"epoch": 3.0,
"eval_loss": 2.3064959049224854,
"eval_runtime": 344.4488,
"eval_samples_per_second": 5.171,
"eval_steps_per_second": 0.647,
"step": 13818
},
{
"epoch": 4.0,
"learning_rate": 2.0065132435953105e-06,
"loss": 2.8744,
"step": 18424
},
{
"epoch": 4.0,
"eval_loss": 2.1857481002807617,
"eval_runtime": 204.3032,
"eval_samples_per_second": 8.717,
"eval_steps_per_second": 1.092,
"step": 18424
},
{
"epoch": 5.0,
"learning_rate": 7.815892314372558e-09,
"loss": 2.7778,
"step": 23030
},
{
"epoch": 5.0,
"eval_loss": 2.129838705062866,
"eval_runtime": 203.9229,
"eval_samples_per_second": 8.734,
"eval_steps_per_second": 1.094,
"step": 23030
},
{
"epoch": 5.0,
"step": 23030,
"total_flos": 6.24394998661824e+19,
"train_loss": 3.1295408248073167,
"train_runtime": 21432.1088,
"train_samples_per_second": 4.298,
"train_steps_per_second": 1.075
}
],
"max_steps": 23030,
"num_train_epochs": 5,
"total_flos": 6.24394998661824e+19,
"trial_name": null,
"trial_params": null
}