dvs's picture
End of training
4236339
{
"best_metric": 1.0,
"best_model_checkpoint": "swin-tiny-patch4-window7-224-mulder-v-scully-colab2/checkpoint-8",
"epoch": 20.0,
"global_step": 20,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.5,
"eval_loss": 0.6898614168167114,
"eval_runtime": 0.0706,
"eval_samples_per_second": 56.662,
"eval_steps_per_second": 14.165,
"step": 1
},
{
"epoch": 2.0,
"eval_accuracy": 0.25,
"eval_loss": 0.6700608730316162,
"eval_runtime": 0.0661,
"eval_samples_per_second": 60.508,
"eval_steps_per_second": 15.127,
"step": 2
},
{
"epoch": 3.0,
"eval_accuracy": 0.5,
"eval_loss": 0.6308517456054688,
"eval_runtime": 0.0675,
"eval_samples_per_second": 59.3,
"eval_steps_per_second": 14.825,
"step": 3
},
{
"epoch": 4.0,
"eval_accuracy": 0.5,
"eval_loss": 0.6049411296844482,
"eval_runtime": 0.0756,
"eval_samples_per_second": 52.927,
"eval_steps_per_second": 13.232,
"step": 4
},
{
"epoch": 5.0,
"eval_accuracy": 0.5,
"eval_loss": 0.5827720165252686,
"eval_runtime": 0.0665,
"eval_samples_per_second": 60.157,
"eval_steps_per_second": 15.039,
"step": 5
},
{
"epoch": 6.0,
"eval_accuracy": 0.75,
"eval_loss": 0.564973771572113,
"eval_runtime": 0.0671,
"eval_samples_per_second": 59.633,
"eval_steps_per_second": 14.908,
"step": 6
},
{
"epoch": 7.0,
"eval_accuracy": 0.75,
"eval_loss": 0.5485844016075134,
"eval_runtime": 0.0664,
"eval_samples_per_second": 60.197,
"eval_steps_per_second": 15.049,
"step": 7
},
{
"epoch": 8.0,
"eval_accuracy": 1.0,
"eval_loss": 0.5343573093414307,
"eval_runtime": 0.0738,
"eval_samples_per_second": 54.186,
"eval_steps_per_second": 13.547,
"step": 8
},
{
"epoch": 9.0,
"eval_accuracy": 1.0,
"eval_loss": 0.5239884853363037,
"eval_runtime": 0.0694,
"eval_samples_per_second": 57.596,
"eval_steps_per_second": 14.399,
"step": 9
},
{
"epoch": 10.0,
"learning_rate": 2.777777777777778e-05,
"loss": 0.2978,
"step": 10
},
{
"epoch": 10.0,
"eval_accuracy": 1.0,
"eval_loss": 0.5149481296539307,
"eval_runtime": 0.0723,
"eval_samples_per_second": 55.291,
"eval_steps_per_second": 13.823,
"step": 10
},
{
"epoch": 11.0,
"eval_accuracy": 1.0,
"eval_loss": 0.5065804719924927,
"eval_runtime": 0.067,
"eval_samples_per_second": 59.67,
"eval_steps_per_second": 14.918,
"step": 11
},
{
"epoch": 12.0,
"eval_accuracy": 1.0,
"eval_loss": 0.49803948402404785,
"eval_runtime": 0.0682,
"eval_samples_per_second": 58.642,
"eval_steps_per_second": 14.66,
"step": 12
},
{
"epoch": 13.0,
"eval_accuracy": 1.0,
"eval_loss": 0.48803186416625977,
"eval_runtime": 0.0722,
"eval_samples_per_second": 55.406,
"eval_steps_per_second": 13.851,
"step": 13
},
{
"epoch": 14.0,
"eval_accuracy": 1.0,
"eval_loss": 0.46994858980178833,
"eval_runtime": 0.0706,
"eval_samples_per_second": 56.647,
"eval_steps_per_second": 14.162,
"step": 14
},
{
"epoch": 15.0,
"eval_accuracy": 1.0,
"eval_loss": 0.4506602883338928,
"eval_runtime": 0.0711,
"eval_samples_per_second": 56.227,
"eval_steps_per_second": 14.057,
"step": 15
},
{
"epoch": 16.0,
"eval_accuracy": 1.0,
"eval_loss": 0.4310106039047241,
"eval_runtime": 0.0688,
"eval_samples_per_second": 58.137,
"eval_steps_per_second": 14.534,
"step": 16
},
{
"epoch": 17.0,
"eval_accuracy": 1.0,
"eval_loss": 0.41549980640411377,
"eval_runtime": 0.0686,
"eval_samples_per_second": 58.309,
"eval_steps_per_second": 14.577,
"step": 17
},
{
"epoch": 18.0,
"eval_accuracy": 1.0,
"eval_loss": 0.4053996503353119,
"eval_runtime": 0.0697,
"eval_samples_per_second": 57.365,
"eval_steps_per_second": 14.341,
"step": 18
},
{
"epoch": 19.0,
"eval_accuracy": 1.0,
"eval_loss": 0.39938098192214966,
"eval_runtime": 0.0762,
"eval_samples_per_second": 52.495,
"eval_steps_per_second": 13.124,
"step": 19
},
{
"epoch": 20.0,
"learning_rate": 0.0,
"loss": 0.1751,
"step": 20
},
{
"epoch": 20.0,
"eval_accuracy": 1.0,
"eval_loss": 0.3969520628452301,
"eval_runtime": 0.0677,
"eval_samples_per_second": 59.119,
"eval_steps_per_second": 14.78,
"step": 20
},
{
"epoch": 20.0,
"step": 20,
"total_flos": 1.789631206981632e+16,
"train_loss": 0.23643767833709717,
"train_runtime": 85.6091,
"train_samples_per_second": 8.41,
"train_steps_per_second": 0.234
}
],
"max_steps": 20,
"num_train_epochs": 20,
"total_flos": 1.789631206981632e+16,
"trial_name": null,
"trial_params": null
}