detr-r50-cd45rb-8ah-4l-1cost / trainer_state.json
polejowska's picture
End of training
f9d68cd
raw
history blame
3.88 kB
{
"best_metric": 1.122222661972046,
"best_model_checkpoint": "detr-r50-cd45rb-8ah-4l-1cost\\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": 9.001736864958749e-07,
"loss": 1.7758,
"step": 4606
},
{
"epoch": 1.0,
"eval_loss": 1.3047956228256226,
"eval_runtime": 202.7594,
"eval_samples_per_second": 8.784,
"eval_steps_per_second": 1.1,
"step": 4606
},
{
"epoch": 2.0,
"learning_rate": 8.001953973078592e-07,
"loss": 1.6314,
"step": 9212
},
{
"epoch": 2.0,
"eval_loss": 1.2280656099319458,
"eval_runtime": 201.0252,
"eval_samples_per_second": 8.86,
"eval_steps_per_second": 1.109,
"step": 9212
},
{
"epoch": 3.0,
"learning_rate": 7.002171081198437e-07,
"loss": 1.5709,
"step": 13818
},
{
"epoch": 3.0,
"eval_loss": 1.1943721771240234,
"eval_runtime": 201.1593,
"eval_samples_per_second": 8.854,
"eval_steps_per_second": 1.109,
"step": 13818
},
{
"epoch": 4.0,
"learning_rate": 6.002605297438123e-07,
"loss": 1.5368,
"step": 18424
},
{
"epoch": 4.0,
"eval_loss": 1.1701624393463135,
"eval_runtime": 201.4465,
"eval_samples_per_second": 8.841,
"eval_steps_per_second": 1.107,
"step": 18424
},
{
"epoch": 5.0,
"learning_rate": 5.003039513677811e-07,
"loss": 1.5132,
"step": 23030
},
{
"epoch": 5.0,
"eval_loss": 1.149705171585083,
"eval_runtime": 201.015,
"eval_samples_per_second": 8.86,
"eval_steps_per_second": 1.109,
"step": 23030
},
{
"epoch": 6.0,
"learning_rate": 4.003256621797655e-07,
"loss": 1.4929,
"step": 27636
},
{
"epoch": 6.0,
"eval_loss": 1.1418626308441162,
"eval_runtime": 200.9658,
"eval_samples_per_second": 8.862,
"eval_steps_per_second": 1.11,
"step": 27636
},
{
"epoch": 7.0,
"learning_rate": 3.0036908380373426e-07,
"loss": 1.4803,
"step": 32242
},
{
"epoch": 7.0,
"eval_loss": 1.1298332214355469,
"eval_runtime": 201.243,
"eval_samples_per_second": 8.85,
"eval_steps_per_second": 1.108,
"step": 32242
},
{
"epoch": 8.0,
"learning_rate": 2.003907946157186e-07,
"loss": 1.4703,
"step": 36848
},
{
"epoch": 8.0,
"eval_loss": 1.1245805025100708,
"eval_runtime": 200.8739,
"eval_samples_per_second": 8.866,
"eval_steps_per_second": 1.11,
"step": 36848
},
{
"epoch": 9.0,
"learning_rate": 1.0041250542770299e-07,
"loss": 1.4655,
"step": 41454
},
{
"epoch": 9.0,
"eval_loss": 1.1222434043884277,
"eval_runtime": 200.6019,
"eval_samples_per_second": 8.878,
"eval_steps_per_second": 1.112,
"step": 41454
},
{
"epoch": 10.0,
"learning_rate": 4.776378636561007e-10,
"loss": 1.4625,
"step": 46060
},
{
"epoch": 10.0,
"eval_loss": 1.122222661972046,
"eval_runtime": 200.6227,
"eval_samples_per_second": 8.877,
"eval_steps_per_second": 1.112,
"step": 46060
},
{
"epoch": 10.0,
"step": 46060,
"total_flos": 7.575060159014402e+19,
"train_loss": 1.5399620039588309,
"train_runtime": 28443.8043,
"train_samples_per_second": 6.476,
"train_steps_per_second": 1.619
}
],
"max_steps": 46060,
"num_train_epochs": 10,
"total_flos": 7.575060159014402e+19,
"trial_name": null,
"trial_params": null
}