ahmedALM1221's picture
Training in progress, epoch 1
f1cd62d
raw
history blame
6.09 kB
{
"best_metric": 0.8795454545454545,
"best_model_checkpoint": "swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-eurosat-50/checkpoint-330",
"epoch": 6.0,
"global_step": 330,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.18,
"learning_rate": 6.060606060606061e-07,
"loss": 2.0126,
"step": 10
},
{
"epoch": 0.36,
"learning_rate": 1.2121212121212122e-06,
"loss": 2.0149,
"step": 20
},
{
"epoch": 0.55,
"learning_rate": 1.8181818181818183e-06,
"loss": 1.9557,
"step": 30
},
{
"epoch": 0.73,
"learning_rate": 2.4242424242424244e-06,
"loss": 1.9057,
"step": 40
},
{
"epoch": 0.91,
"learning_rate": 3.0303030303030305e-06,
"loss": 1.8498,
"step": 50
},
{
"epoch": 1.0,
"eval_accuracy": 0.32727272727272727,
"eval_loss": 1.734784483909607,
"eval_runtime": 359.3738,
"eval_samples_per_second": 2.449,
"eval_steps_per_second": 0.153,
"step": 55
},
{
"epoch": 1.09,
"learning_rate": 3.6363636363636366e-06,
"loss": 1.7745,
"step": 60
},
{
"epoch": 1.27,
"learning_rate": 4.242424242424243e-06,
"loss": 1.7178,
"step": 70
},
{
"epoch": 1.45,
"learning_rate": 4.848484848484849e-06,
"loss": 1.5662,
"step": 80
},
{
"epoch": 1.64,
"learning_rate": 5.4545454545454545e-06,
"loss": 1.4263,
"step": 90
},
{
"epoch": 1.82,
"learning_rate": 6.060606060606061e-06,
"loss": 1.2797,
"step": 100
},
{
"epoch": 2.0,
"learning_rate": 6.666666666666667e-06,
"loss": 1.1886,
"step": 110
},
{
"epoch": 2.0,
"eval_accuracy": 0.6102272727272727,
"eval_loss": 1.019785761833191,
"eval_runtime": 11.0093,
"eval_samples_per_second": 79.933,
"eval_steps_per_second": 4.996,
"step": 110
},
{
"epoch": 2.18,
"learning_rate": 7.272727272727273e-06,
"loss": 1.099,
"step": 120
},
{
"epoch": 2.36,
"learning_rate": 7.87878787878788e-06,
"loss": 1.0145,
"step": 130
},
{
"epoch": 2.55,
"learning_rate": 8.484848484848486e-06,
"loss": 0.9682,
"step": 140
},
{
"epoch": 2.73,
"learning_rate": 9.090909090909091e-06,
"loss": 0.9164,
"step": 150
},
{
"epoch": 2.91,
"learning_rate": 9.696969696969698e-06,
"loss": 0.8636,
"step": 160
},
{
"epoch": 3.0,
"eval_accuracy": 0.7397727272727272,
"eval_loss": 0.6859003305435181,
"eval_runtime": 10.9928,
"eval_samples_per_second": 80.052,
"eval_steps_per_second": 5.003,
"step": 165
},
{
"epoch": 3.09,
"learning_rate": 9.696969696969698e-06,
"loss": 0.8709,
"step": 170
},
{
"epoch": 3.27,
"learning_rate": 9.090909090909091e-06,
"loss": 0.749,
"step": 180
},
{
"epoch": 3.45,
"learning_rate": 8.484848484848486e-06,
"loss": 0.7015,
"step": 190
},
{
"epoch": 3.64,
"learning_rate": 7.87878787878788e-06,
"loss": 0.6916,
"step": 200
},
{
"epoch": 3.82,
"learning_rate": 7.272727272727273e-06,
"loss": 0.6508,
"step": 210
},
{
"epoch": 4.0,
"learning_rate": 6.666666666666667e-06,
"loss": 0.576,
"step": 220
},
{
"epoch": 4.0,
"eval_accuracy": 0.8477272727272728,
"eval_loss": 0.4356772005558014,
"eval_runtime": 10.9979,
"eval_samples_per_second": 80.015,
"eval_steps_per_second": 5.001,
"step": 220
},
{
"epoch": 4.18,
"learning_rate": 6.060606060606061e-06,
"loss": 0.51,
"step": 230
},
{
"epoch": 4.36,
"learning_rate": 5.4545454545454545e-06,
"loss": 0.5592,
"step": 240
},
{
"epoch": 4.55,
"learning_rate": 4.848484848484849e-06,
"loss": 0.5314,
"step": 250
},
{
"epoch": 4.73,
"learning_rate": 4.242424242424243e-06,
"loss": 0.5021,
"step": 260
},
{
"epoch": 4.91,
"learning_rate": 3.6363636363636366e-06,
"loss": 0.5875,
"step": 270
},
{
"epoch": 5.0,
"eval_accuracy": 0.8386363636363636,
"eval_loss": 0.418759286403656,
"eval_runtime": 10.9077,
"eval_samples_per_second": 80.677,
"eval_steps_per_second": 5.042,
"step": 275
},
{
"epoch": 5.09,
"learning_rate": 3.0303030303030305e-06,
"loss": 0.4782,
"step": 280
},
{
"epoch": 5.27,
"learning_rate": 2.4242424242424244e-06,
"loss": 0.521,
"step": 290
},
{
"epoch": 5.45,
"learning_rate": 1.8181818181818183e-06,
"loss": 0.451,
"step": 300
},
{
"epoch": 5.64,
"learning_rate": 1.2121212121212122e-06,
"loss": 0.4403,
"step": 310
},
{
"epoch": 5.82,
"learning_rate": 6.060606060606061e-07,
"loss": 0.4929,
"step": 320
},
{
"epoch": 6.0,
"learning_rate": 0.0,
"loss": 0.4677,
"step": 330
},
{
"epoch": 6.0,
"eval_accuracy": 0.8795454545454545,
"eval_loss": 0.3292839825153351,
"eval_runtime": 10.9849,
"eval_samples_per_second": 80.11,
"eval_steps_per_second": 5.007,
"step": 330
},
{
"epoch": 6.0,
"step": 330,
"total_flos": 4.860822854913491e+18,
"train_loss": 1.0101308201298569,
"train_runtime": 2441.1089,
"train_samples_per_second": 8.647,
"train_steps_per_second": 0.135
}
],
"max_steps": 330,
"num_train_epochs": 6,
"total_flos": 4.860822854913491e+18,
"trial_name": null,
"trial_params": null
}