detr-r50-cd45rb-4ah-6l / trainer_state.json
polejowska's picture
End of training
1ab1d84
raw
history blame
3.87 kB
{
"best_metric": 1.6890008449554443,
"best_model_checkpoint": "detr-r50-cd45rb-4ah-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": 9.002171081198437e-06,
"loss": 2.7454,
"step": 4606
},
{
"epoch": 1.0,
"eval_loss": 2.0001132488250732,
"eval_runtime": 207.6969,
"eval_samples_per_second": 8.575,
"eval_steps_per_second": 1.074,
"step": 4606
},
{
"epoch": 2.0,
"learning_rate": 8.002605297438126e-06,
"loss": 2.4366,
"step": 9212
},
{
"epoch": 2.0,
"eval_loss": 1.8949499130249023,
"eval_runtime": 207.0756,
"eval_samples_per_second": 8.601,
"eval_steps_per_second": 1.077,
"step": 9212
},
{
"epoch": 3.0,
"learning_rate": 7.0028224055579685e-06,
"loss": 2.3351,
"step": 13818
},
{
"epoch": 3.0,
"eval_loss": 1.828635811805725,
"eval_runtime": 206.5853,
"eval_samples_per_second": 8.621,
"eval_steps_per_second": 1.079,
"step": 13818
},
{
"epoch": 4.0,
"learning_rate": 6.003256621797656e-06,
"loss": 2.2927,
"step": 18424
},
{
"epoch": 4.0,
"eval_loss": 1.794113039970398,
"eval_runtime": 206.1352,
"eval_samples_per_second": 8.64,
"eval_steps_per_second": 1.082,
"step": 18424
},
{
"epoch": 5.0,
"learning_rate": 5.003690838037343e-06,
"loss": 2.2604,
"step": 23030
},
{
"epoch": 5.0,
"eval_loss": 1.791698694229126,
"eval_runtime": 204.7452,
"eval_samples_per_second": 8.699,
"eval_steps_per_second": 1.089,
"step": 23030
},
{
"epoch": 6.0,
"learning_rate": 4.004342162396874e-06,
"loss": 2.2195,
"step": 27636
},
{
"epoch": 6.0,
"eval_loss": 1.7718113660812378,
"eval_runtime": 204.9683,
"eval_samples_per_second": 8.689,
"eval_steps_per_second": 1.088,
"step": 27636
},
{
"epoch": 7.0,
"learning_rate": 3.0047763786365614e-06,
"loss": 2.1933,
"step": 32242
},
{
"epoch": 7.0,
"eval_loss": 1.7202998399734497,
"eval_runtime": 206.0092,
"eval_samples_per_second": 8.645,
"eval_steps_per_second": 1.082,
"step": 32242
},
{
"epoch": 8.0,
"learning_rate": 2.004993486756405e-06,
"loss": 2.1642,
"step": 36848
},
{
"epoch": 8.0,
"eval_loss": 1.7172293663024902,
"eval_runtime": 195.6771,
"eval_samples_per_second": 9.102,
"eval_steps_per_second": 1.14,
"step": 36848
},
{
"epoch": 9.0,
"learning_rate": 1.0054277029960922e-06,
"loss": 2.1453,
"step": 41454
},
{
"epoch": 9.0,
"eval_loss": 1.6982392072677612,
"eval_runtime": 205.3012,
"eval_samples_per_second": 8.675,
"eval_steps_per_second": 1.086,
"step": 41454
},
{
"epoch": 10.0,
"learning_rate": 5.644811115935737e-09,
"loss": 2.1342,
"step": 46060
},
{
"epoch": 10.0,
"eval_loss": 1.6890008449554443,
"eval_runtime": 205.1625,
"eval_samples_per_second": 8.681,
"eval_steps_per_second": 1.087,
"step": 46060
},
{
"epoch": 10.0,
"step": 46060,
"total_flos": 8.803311016032e+19,
"train_loss": 0.0,
"train_runtime": 0.2355,
"train_samples_per_second": 782222.791,
"train_steps_per_second": 195587.546
}
],
"max_steps": 46060,
"num_train_epochs": 10,
"total_flos": 8.803311016032e+19,
"trial_name": null,
"trial_params": null
}