detr-r50-cd45rb-2ah-6l-corrected / trainer_state.json
polejowska's picture
End of training
dd9b62a
raw
history blame
3.89 kB
{
"best_metric": 1.8622814416885376,
"best_model_checkpoint": "detr-r50-cd45rb-2ah-6l-corrected\\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": 3.4312,
"step": 4606
},
{
"epoch": 1.0,
"eval_loss": 2.442598342895508,
"eval_runtime": 204.3572,
"eval_samples_per_second": 8.715,
"eval_steps_per_second": 1.091,
"step": 4606
},
{
"epoch": 2.0,
"learning_rate": 8.002388189318281e-06,
"loss": 2.9035,
"step": 9212
},
{
"epoch": 2.0,
"eval_loss": 2.1671295166015625,
"eval_runtime": 204.0022,
"eval_samples_per_second": 8.73,
"eval_steps_per_second": 1.093,
"step": 9212
},
{
"epoch": 3.0,
"learning_rate": 7.0028224055579685e-06,
"loss": 2.6788,
"step": 13818
},
{
"epoch": 3.0,
"eval_loss": 2.0924932956695557,
"eval_runtime": 203.9348,
"eval_samples_per_second": 8.733,
"eval_steps_per_second": 1.093,
"step": 13818
},
{
"epoch": 4.0,
"learning_rate": 6.003256621797656e-06,
"loss": 2.5847,
"step": 18424
},
{
"epoch": 4.0,
"eval_loss": 2.021491765975952,
"eval_runtime": 201.6799,
"eval_samples_per_second": 8.831,
"eval_steps_per_second": 1.106,
"step": 18424
},
{
"epoch": 5.0,
"learning_rate": 5.0034737299175e-06,
"loss": 2.5075,
"step": 23030
},
{
"epoch": 5.0,
"eval_loss": 1.9688512086868286,
"eval_runtime": 205.2053,
"eval_samples_per_second": 8.679,
"eval_steps_per_second": 1.087,
"step": 23030
},
{
"epoch": 6.0,
"learning_rate": 4.0041250542770305e-06,
"loss": 2.445,
"step": 27636
},
{
"epoch": 6.0,
"eval_loss": 1.9527798891067505,
"eval_runtime": 205.1637,
"eval_samples_per_second": 8.681,
"eval_steps_per_second": 1.087,
"step": 27636
},
{
"epoch": 7.0,
"learning_rate": 3.0045592705167175e-06,
"loss": 2.4078,
"step": 32242
},
{
"epoch": 7.0,
"eval_loss": 1.9058469533920288,
"eval_runtime": 205.1138,
"eval_samples_per_second": 8.683,
"eval_steps_per_second": 1.087,
"step": 32242
},
{
"epoch": 8.0,
"learning_rate": 2.004993486756405e-06,
"loss": 2.3794,
"step": 36848
},
{
"epoch": 8.0,
"eval_loss": 1.888853907585144,
"eval_runtime": 205.5976,
"eval_samples_per_second": 8.663,
"eval_steps_per_second": 1.085,
"step": 36848
},
{
"epoch": 9.0,
"learning_rate": 1.0049934867564047e-06,
"loss": 2.3572,
"step": 41454
},
{
"epoch": 9.0,
"eval_loss": 1.875107765197754,
"eval_runtime": 202.1582,
"eval_samples_per_second": 8.81,
"eval_steps_per_second": 1.103,
"step": 41454
},
{
"epoch": 10.0,
"learning_rate": 5.427702996092055e-09,
"loss": 2.3374,
"step": 46060
},
{
"epoch": 10.0,
"eval_loss": 1.8622814416885376,
"eval_runtime": 202.8571,
"eval_samples_per_second": 8.78,
"eval_steps_per_second": 1.099,
"step": 46060
},
{
"epoch": 10.0,
"step": 46060,
"total_flos": 8.803256478082562e+19,
"train_loss": 2.603237603635204,
"train_runtime": 29457.3491,
"train_samples_per_second": 6.253,
"train_steps_per_second": 1.564
}
],
"max_steps": 46060,
"num_train_epochs": 10,
"total_flos": 8.803256478082562e+19,
"trial_name": null,
"trial_params": null
}