detr-r50-cd45rb-8ah-4l-f-c / trainer_state.json
polejowska's picture
End of training
5571b11
raw
history blame
3.89 kB
{
"best_metric": 0.9491861462593079,
"best_model_checkpoint": "detr-r50-cd45rb-8ah-4l-f-c\\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": 9.001519756838908e-06,
"loss": 1.9191,
"step": 4606
},
{
"epoch": 1.0,
"eval_loss": 1.2036592960357666,
"eval_runtime": 233.3951,
"eval_samples_per_second": 7.631,
"eval_steps_per_second": 0.955,
"step": 4606
},
{
"epoch": 2.0,
"learning_rate": 8.002171081198438e-06,
"loss": 1.5088,
"step": 9212
},
{
"epoch": 2.0,
"eval_loss": 1.09281587600708,
"eval_runtime": 232.4582,
"eval_samples_per_second": 7.662,
"eval_steps_per_second": 0.959,
"step": 9212
},
{
"epoch": 3.0,
"learning_rate": 7.0023881893182814e-06,
"loss": 1.4004,
"step": 13818
},
{
"epoch": 3.0,
"eval_loss": 1.0351686477661133,
"eval_runtime": 231.5449,
"eval_samples_per_second": 7.692,
"eval_steps_per_second": 0.963,
"step": 13818
},
{
"epoch": 4.0,
"learning_rate": 6.002822405557969e-06,
"loss": 1.3481,
"step": 18424
},
{
"epoch": 4.0,
"eval_loss": 1.0199804306030273,
"eval_runtime": 230.3809,
"eval_samples_per_second": 7.731,
"eval_steps_per_second": 0.968,
"step": 18424
},
{
"epoch": 5.0,
"learning_rate": 5.0034737299175e-06,
"loss": 1.3104,
"step": 23030
},
{
"epoch": 5.0,
"eval_loss": 1.0002790689468384,
"eval_runtime": 231.2382,
"eval_samples_per_second": 7.702,
"eval_steps_per_second": 0.964,
"step": 23030
},
{
"epoch": 6.0,
"learning_rate": 4.003907946157187e-06,
"loss": 1.2791,
"step": 27636
},
{
"epoch": 6.0,
"eval_loss": 1.0887064933776855,
"eval_runtime": 195.9195,
"eval_samples_per_second": 9.09,
"eval_steps_per_second": 1.138,
"step": 27636
},
{
"epoch": 7.0,
"learning_rate": 3.00412505427703e-06,
"loss": 1.2555,
"step": 32242
},
{
"epoch": 7.0,
"eval_loss": 0.9726870656013489,
"eval_runtime": 197.9362,
"eval_samples_per_second": 8.998,
"eval_steps_per_second": 1.127,
"step": 32242
},
{
"epoch": 8.0,
"learning_rate": 2.0045592705167173e-06,
"loss": 1.2354,
"step": 36848
},
{
"epoch": 8.0,
"eval_loss": 0.9574904441833496,
"eval_runtime": 198.5985,
"eval_samples_per_second": 8.968,
"eval_steps_per_second": 1.123,
"step": 36848
},
{
"epoch": 9.0,
"learning_rate": 1.0049934867564047e-06,
"loss": 1.2231,
"step": 41454
},
{
"epoch": 9.0,
"eval_loss": 0.9551559090614319,
"eval_runtime": 197.7002,
"eval_samples_per_second": 9.009,
"eval_steps_per_second": 1.128,
"step": 41454
},
{
"epoch": 10.0,
"learning_rate": 5.427702996092055e-09,
"loss": 1.212,
"step": 46060
},
{
"epoch": 10.0,
"eval_loss": 0.9491861462593079,
"eval_runtime": 216.4233,
"eval_samples_per_second": 8.229,
"eval_steps_per_second": 1.03,
"step": 46060
},
{
"epoch": 10.0,
"step": 46060,
"total_flos": 7.575060159014402e+19,
"train_loss": 1.3691692582535009,
"train_runtime": 30392.7009,
"train_samples_per_second": 6.061,
"train_steps_per_second": 1.515
}
],
"max_steps": 46060,
"num_train_epochs": 10,
"total_flos": 7.575060159014402e+19,
"trial_name": null,
"trial_params": null
}