DataBindu's picture
End of training
86481cc
{
"best_metric": 0.7129629629629629,
"best_model_checkpoint": "swinv2-large-patch4-window12to24-192to384-22kto1k-ft-microbes\\checkpoint-106",
"epoch": 7.868852459016393,
"eval_steps": 500,
"global_step": 120,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.66,
"learning_rate": 4.166666666666667e-05,
"loss": 3.8445,
"step": 10
},
{
"epoch": 0.98,
"eval_accuracy": 0.3194444444444444,
"eval_loss": 2.853494882583618,
"eval_runtime": 275.4409,
"eval_samples_per_second": 0.784,
"eval_steps_per_second": 0.025,
"step": 15
},
{
"epoch": 1.31,
"learning_rate": 4.62962962962963e-05,
"loss": 2.9233,
"step": 20
},
{
"epoch": 1.97,
"learning_rate": 4.166666666666667e-05,
"loss": 2.1358,
"step": 30
},
{
"epoch": 1.97,
"eval_accuracy": 0.44907407407407407,
"eval_loss": 1.9653794765472412,
"eval_runtime": 249.4789,
"eval_samples_per_second": 0.866,
"eval_steps_per_second": 0.028,
"step": 30
},
{
"epoch": 2.62,
"learning_rate": 3.7037037037037037e-05,
"loss": 1.5947,
"step": 40
},
{
"epoch": 2.95,
"eval_accuracy": 0.6203703703703703,
"eval_loss": 1.4172132015228271,
"eval_runtime": 248.0335,
"eval_samples_per_second": 0.871,
"eval_steps_per_second": 0.028,
"step": 45
},
{
"epoch": 3.28,
"learning_rate": 3.240740740740741e-05,
"loss": 1.2958,
"step": 50
},
{
"epoch": 3.93,
"learning_rate": 2.777777777777778e-05,
"loss": 1.045,
"step": 60
},
{
"epoch": 4.0,
"eval_accuracy": 0.6805555555555556,
"eval_loss": 1.169750452041626,
"eval_runtime": 249.6999,
"eval_samples_per_second": 0.865,
"eval_steps_per_second": 0.028,
"step": 61
},
{
"epoch": 4.59,
"learning_rate": 2.314814814814815e-05,
"loss": 0.985,
"step": 70
},
{
"epoch": 4.98,
"eval_accuracy": 0.6851851851851852,
"eval_loss": 1.1927063465118408,
"eval_runtime": 249.8277,
"eval_samples_per_second": 0.865,
"eval_steps_per_second": 0.028,
"step": 76
},
{
"epoch": 5.25,
"learning_rate": 1.8518518518518518e-05,
"loss": 0.8089,
"step": 80
},
{
"epoch": 5.9,
"learning_rate": 1.388888888888889e-05,
"loss": 0.775,
"step": 90
},
{
"epoch": 5.97,
"eval_accuracy": 0.6898148148148148,
"eval_loss": 1.1011860370635986,
"eval_runtime": 248.7957,
"eval_samples_per_second": 0.868,
"eval_steps_per_second": 0.028,
"step": 91
},
{
"epoch": 6.56,
"learning_rate": 9.259259259259259e-06,
"loss": 0.7207,
"step": 100
},
{
"epoch": 6.95,
"eval_accuracy": 0.7129629629629629,
"eval_loss": 1.0311119556427002,
"eval_runtime": 248.8611,
"eval_samples_per_second": 0.868,
"eval_steps_per_second": 0.028,
"step": 106
},
{
"epoch": 7.21,
"learning_rate": 4.6296296296296296e-06,
"loss": 0.6587,
"step": 110
},
{
"epoch": 7.87,
"learning_rate": 0.0,
"loss": 0.6611,
"step": 120
},
{
"epoch": 7.87,
"eval_accuracy": 0.6990740740740741,
"eval_loss": 1.0310794115066528,
"eval_runtime": 249.3479,
"eval_samples_per_second": 0.866,
"eval_steps_per_second": 0.028,
"step": 120
},
{
"epoch": 7.87,
"step": 120,
"total_flos": 7.925569593060557e+18,
"train_loss": 1.4540472984313966,
"train_runtime": 48373.2241,
"train_samples_per_second": 0.321,
"train_steps_per_second": 0.002
}
],
"logging_steps": 10,
"max_steps": 120,
"num_train_epochs": 8,
"save_steps": 500,
"total_flos": 7.925569593060557e+18,
"trial_name": null,
"trial_params": null
}