phunc20's picture
End of training
d98b3dd
raw
history blame
6.03 kB
{
"best_metric": 0.7953054904937744,
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-wuhan/checkpoint-3",
"epoch": 20.0,
"global_step": 60,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.4,
"eval_loss": 0.7953054904937744,
"eval_runtime": 38.7172,
"eval_samples_per_second": 1.162,
"eval_steps_per_second": 0.026,
"step": 3
},
{
"epoch": 2.0,
"eval_accuracy": 0.4,
"eval_loss": 0.9477012753486633,
"eval_runtime": 2.1877,
"eval_samples_per_second": 20.569,
"eval_steps_per_second": 0.457,
"step": 6
},
{
"epoch": 3.0,
"eval_accuracy": 0.4,
"eval_loss": 1.010606050491333,
"eval_runtime": 2.1562,
"eval_samples_per_second": 20.87,
"eval_steps_per_second": 0.464,
"step": 9
},
{
"epoch": 3.33,
"learning_rate": 4.62962962962963e-05,
"loss": 0.5883,
"step": 10
},
{
"epoch": 4.0,
"eval_accuracy": 0.4,
"eval_loss": 1.417040228843689,
"eval_runtime": 2.225,
"eval_samples_per_second": 20.225,
"eval_steps_per_second": 0.449,
"step": 12
},
{
"epoch": 5.0,
"eval_accuracy": 0.4,
"eval_loss": 1.7435767650604248,
"eval_runtime": 2.2394,
"eval_samples_per_second": 20.095,
"eval_steps_per_second": 0.447,
"step": 15
},
{
"epoch": 6.0,
"eval_accuracy": 0.4,
"eval_loss": 2.5379722118377686,
"eval_runtime": 2.1794,
"eval_samples_per_second": 20.648,
"eval_steps_per_second": 0.459,
"step": 18
},
{
"epoch": 6.67,
"learning_rate": 3.7037037037037037e-05,
"loss": 0.241,
"step": 20
},
{
"epoch": 7.0,
"eval_accuracy": 0.4,
"eval_loss": 3.8802621364593506,
"eval_runtime": 2.1868,
"eval_samples_per_second": 20.578,
"eval_steps_per_second": 0.457,
"step": 21
},
{
"epoch": 8.0,
"eval_accuracy": 0.2222222222222222,
"eval_loss": 2.4039711952209473,
"eval_runtime": 2.2635,
"eval_samples_per_second": 19.881,
"eval_steps_per_second": 0.442,
"step": 24
},
{
"epoch": 9.0,
"eval_accuracy": 0.4,
"eval_loss": 3.9967715740203857,
"eval_runtime": 2.2078,
"eval_samples_per_second": 20.382,
"eval_steps_per_second": 0.453,
"step": 27
},
{
"epoch": 10.0,
"learning_rate": 2.777777777777778e-05,
"loss": 0.125,
"step": 30
},
{
"epoch": 10.0,
"eval_accuracy": 0.4,
"eval_loss": 3.27313494682312,
"eval_runtime": 2.2426,
"eval_samples_per_second": 20.066,
"eval_steps_per_second": 0.446,
"step": 30
},
{
"epoch": 11.0,
"eval_accuracy": 0.2222222222222222,
"eval_loss": 3.2202415466308594,
"eval_runtime": 2.281,
"eval_samples_per_second": 19.728,
"eval_steps_per_second": 0.438,
"step": 33
},
{
"epoch": 12.0,
"eval_accuracy": 0.4,
"eval_loss": 4.70084285736084,
"eval_runtime": 2.2753,
"eval_samples_per_second": 19.777,
"eval_steps_per_second": 0.439,
"step": 36
},
{
"epoch": 13.0,
"eval_accuracy": 0.35555555555555557,
"eval_loss": 4.558761119842529,
"eval_runtime": 2.2218,
"eval_samples_per_second": 20.254,
"eval_steps_per_second": 0.45,
"step": 39
},
{
"epoch": 13.33,
"learning_rate": 1.8518518518518518e-05,
"loss": 0.0766,
"step": 40
},
{
"epoch": 14.0,
"eval_accuracy": 0.24444444444444444,
"eval_loss": 4.54338264465332,
"eval_runtime": 2.2251,
"eval_samples_per_second": 20.223,
"eval_steps_per_second": 0.449,
"step": 42
},
{
"epoch": 15.0,
"eval_accuracy": 0.26666666666666666,
"eval_loss": 4.979237079620361,
"eval_runtime": 2.4295,
"eval_samples_per_second": 18.522,
"eval_steps_per_second": 0.412,
"step": 45
},
{
"epoch": 16.0,
"eval_accuracy": 0.26666666666666666,
"eval_loss": 5.409503936767578,
"eval_runtime": 2.1939,
"eval_samples_per_second": 20.512,
"eval_steps_per_second": 0.456,
"step": 48
},
{
"epoch": 16.67,
"learning_rate": 9.259259259259259e-06,
"loss": 0.0239,
"step": 50
},
{
"epoch": 17.0,
"eval_accuracy": 0.2222222222222222,
"eval_loss": 5.850742816925049,
"eval_runtime": 2.2566,
"eval_samples_per_second": 19.942,
"eval_steps_per_second": 0.443,
"step": 51
},
{
"epoch": 18.0,
"eval_accuracy": 0.2222222222222222,
"eval_loss": 6.102282524108887,
"eval_runtime": 2.2779,
"eval_samples_per_second": 19.755,
"eval_steps_per_second": 0.439,
"step": 54
},
{
"epoch": 19.0,
"eval_accuracy": 0.2222222222222222,
"eval_loss": 6.166590213775635,
"eval_runtime": 2.257,
"eval_samples_per_second": 19.938,
"eval_steps_per_second": 0.443,
"step": 57
},
{
"epoch": 20.0,
"learning_rate": 0.0,
"loss": 0.0129,
"step": 60
},
{
"epoch": 20.0,
"eval_accuracy": 0.2222222222222222,
"eval_loss": 6.194781303405762,
"eval_runtime": 2.3123,
"eval_samples_per_second": 19.461,
"eval_steps_per_second": 0.432,
"step": 60
},
{
"epoch": 20.0,
"step": 60,
"total_flos": 1.7747176135901184e+17,
"train_loss": 0.1779410476485888,
"train_runtime": 979.9272,
"train_samples_per_second": 7.286,
"train_steps_per_second": 0.061
}
],
"max_steps": 60,
"num_train_epochs": 20,
"total_flos": 1.7747176135901184e+17,
"trial_name": null,
"trial_params": null
}