detr-r50-cd45rb-7k-8ah / trainer_state.json
polejowska's picture
End of training
ed0efa2
{
"best_metric": 1.716400384902954,
"best_model_checkpoint": "detr-r50-cd45rb-7k-8ah\\checkpoint-8960",
"epoch": 10.0,
"global_step": 8960,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 9.007812500000001e-06,
"loss": 2.5817,
"step": 896
},
{
"epoch": 1.0,
"eval_loss": 1.9430588483810425,
"eval_runtime": 210.9493,
"eval_samples_per_second": 8.443,
"eval_steps_per_second": 1.057,
"step": 896
},
{
"epoch": 2.0,
"learning_rate": 8.0078125e-06,
"loss": 2.2882,
"step": 1792
},
{
"epoch": 2.0,
"eval_loss": 1.8638406991958618,
"eval_runtime": 195.3828,
"eval_samples_per_second": 9.115,
"eval_steps_per_second": 1.141,
"step": 1792
},
{
"epoch": 3.0,
"learning_rate": 7.008928571428572e-06,
"loss": 2.2236,
"step": 2688
},
{
"epoch": 3.0,
"eval_loss": 1.8089314699172974,
"eval_runtime": 203.3033,
"eval_samples_per_second": 8.76,
"eval_steps_per_second": 1.097,
"step": 2688
},
{
"epoch": 4.0,
"learning_rate": 6.008928571428571e-06,
"loss": 2.1649,
"step": 3584
},
{
"epoch": 4.0,
"eval_loss": 1.784340739250183,
"eval_runtime": 200.9407,
"eval_samples_per_second": 8.863,
"eval_steps_per_second": 1.11,
"step": 3584
},
{
"epoch": 5.0,
"learning_rate": 5.010044642857143e-06,
"loss": 2.1275,
"step": 4480
},
{
"epoch": 5.0,
"eval_loss": 1.7592535018920898,
"eval_runtime": 198.6049,
"eval_samples_per_second": 8.968,
"eval_steps_per_second": 1.123,
"step": 4480
},
{
"epoch": 6.0,
"learning_rate": 4.010044642857144e-06,
"loss": 2.1176,
"step": 5376
},
{
"epoch": 6.0,
"eval_loss": 1.7541559934616089,
"eval_runtime": 194.8788,
"eval_samples_per_second": 9.139,
"eval_steps_per_second": 1.144,
"step": 5376
},
{
"epoch": 7.0,
"learning_rate": 3.0100446428571435e-06,
"loss": 2.1037,
"step": 6272
},
{
"epoch": 7.0,
"eval_loss": 1.7385700941085815,
"eval_runtime": 195.2255,
"eval_samples_per_second": 9.123,
"eval_steps_per_second": 1.142,
"step": 6272
},
{
"epoch": 8.0,
"learning_rate": 2.010044642857143e-06,
"loss": 2.0969,
"step": 7168
},
{
"epoch": 8.0,
"eval_loss": 1.724243402481079,
"eval_runtime": 197.1145,
"eval_samples_per_second": 9.035,
"eval_steps_per_second": 1.131,
"step": 7168
},
{
"epoch": 9.0,
"learning_rate": 1.010044642857143e-06,
"loss": 2.0794,
"step": 8064
},
{
"epoch": 9.0,
"eval_loss": 1.7200037240982056,
"eval_runtime": 195.72,
"eval_samples_per_second": 9.1,
"eval_steps_per_second": 1.139,
"step": 8064
},
{
"epoch": 10.0,
"learning_rate": 1.0044642857142856e-08,
"loss": 2.0792,
"step": 8960
},
{
"epoch": 10.0,
"eval_loss": 1.716400384902954,
"eval_runtime": 194.8625,
"eval_samples_per_second": 9.14,
"eval_steps_per_second": 1.144,
"step": 8960
},
{
"epoch": 10.0,
"step": 8960,
"total_flos": 3.42314348583168e+19,
"train_loss": 2.1862755230494906,
"train_runtime": 11713.7226,
"train_samples_per_second": 6.115,
"train_steps_per_second": 0.765
}
],
"max_steps": 8960,
"num_train_epochs": 10,
"total_flos": 3.42314348583168e+19,
"trial_name": null,
"trial_params": null
}