ahmedALM1221's picture
Training in progress, epoch 1
b809a67
raw
history blame
6.06 kB
{
"best_metric": 0.9659090909090909,
"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": 0.3989,
"step": 10
},
{
"epoch": 0.36,
"learning_rate": 1.2121212121212122e-06,
"loss": 0.4458,
"step": 20
},
{
"epoch": 0.55,
"learning_rate": 1.8181818181818183e-06,
"loss": 0.4395,
"step": 30
},
{
"epoch": 0.73,
"learning_rate": 2.4242424242424244e-06,
"loss": 0.4139,
"step": 40
},
{
"epoch": 0.91,
"learning_rate": 3.0303030303030305e-06,
"loss": 0.4562,
"step": 50
},
{
"epoch": 1.0,
"eval_accuracy": 0.8897727272727273,
"eval_loss": 0.3206745386123657,
"eval_runtime": 10.9207,
"eval_samples_per_second": 80.581,
"eval_steps_per_second": 5.036,
"step": 55
},
{
"epoch": 1.09,
"learning_rate": 3.6363636363636366e-06,
"loss": 0.424,
"step": 60
},
{
"epoch": 1.27,
"learning_rate": 4.242424242424243e-06,
"loss": 0.4218,
"step": 70
},
{
"epoch": 1.45,
"learning_rate": 4.848484848484849e-06,
"loss": 0.3912,
"step": 80
},
{
"epoch": 1.64,
"learning_rate": 5.4545454545454545e-06,
"loss": 0.3665,
"step": 90
},
{
"epoch": 1.82,
"learning_rate": 6.060606060606061e-06,
"loss": 0.3969,
"step": 100
},
{
"epoch": 2.0,
"learning_rate": 6.666666666666667e-06,
"loss": 0.372,
"step": 110
},
{
"epoch": 2.0,
"eval_accuracy": 0.9068181818181819,
"eval_loss": 0.2666811943054199,
"eval_runtime": 10.9113,
"eval_samples_per_second": 80.65,
"eval_steps_per_second": 5.041,
"step": 110
},
{
"epoch": 2.18,
"learning_rate": 7.272727272727273e-06,
"loss": 0.35,
"step": 120
},
{
"epoch": 2.36,
"learning_rate": 7.87878787878788e-06,
"loss": 0.275,
"step": 130
},
{
"epoch": 2.55,
"learning_rate": 8.484848484848486e-06,
"loss": 0.2911,
"step": 140
},
{
"epoch": 2.73,
"learning_rate": 9.090909090909091e-06,
"loss": 0.2794,
"step": 150
},
{
"epoch": 2.91,
"learning_rate": 9.696969696969698e-06,
"loss": 0.2776,
"step": 160
},
{
"epoch": 3.0,
"eval_accuracy": 0.9125,
"eval_loss": 0.2862165570259094,
"eval_runtime": 11.069,
"eval_samples_per_second": 79.501,
"eval_steps_per_second": 4.969,
"step": 165
},
{
"epoch": 3.09,
"learning_rate": 9.696969696969698e-06,
"loss": 0.3096,
"step": 170
},
{
"epoch": 3.27,
"learning_rate": 9.090909090909091e-06,
"loss": 0.2071,
"step": 180
},
{
"epoch": 3.45,
"learning_rate": 8.484848484848486e-06,
"loss": 0.2234,
"step": 190
},
{
"epoch": 3.64,
"learning_rate": 7.87878787878788e-06,
"loss": 0.2446,
"step": 200
},
{
"epoch": 3.82,
"learning_rate": 7.272727272727273e-06,
"loss": 0.1926,
"step": 210
},
{
"epoch": 4.0,
"learning_rate": 6.666666666666667e-06,
"loss": 0.2018,
"step": 220
},
{
"epoch": 4.0,
"eval_accuracy": 0.9397727272727273,
"eval_loss": 0.19657106697559357,
"eval_runtime": 10.9849,
"eval_samples_per_second": 80.11,
"eval_steps_per_second": 5.007,
"step": 220
},
{
"epoch": 4.18,
"learning_rate": 6.060606060606061e-06,
"loss": 0.1894,
"step": 230
},
{
"epoch": 4.36,
"learning_rate": 5.4545454545454545e-06,
"loss": 0.2126,
"step": 240
},
{
"epoch": 4.55,
"learning_rate": 4.848484848484849e-06,
"loss": 0.2101,
"step": 250
},
{
"epoch": 4.73,
"learning_rate": 4.242424242424243e-06,
"loss": 0.2062,
"step": 260
},
{
"epoch": 4.91,
"learning_rate": 3.6363636363636366e-06,
"loss": 0.2751,
"step": 270
},
{
"epoch": 5.0,
"eval_accuracy": 0.9375,
"eval_loss": 0.1937328726053238,
"eval_runtime": 10.9353,
"eval_samples_per_second": 80.474,
"eval_steps_per_second": 5.03,
"step": 275
},
{
"epoch": 5.09,
"learning_rate": 3.0303030303030305e-06,
"loss": 0.219,
"step": 280
},
{
"epoch": 5.27,
"learning_rate": 2.4242424242424244e-06,
"loss": 0.2875,
"step": 290
},
{
"epoch": 5.45,
"learning_rate": 1.8181818181818183e-06,
"loss": 0.2401,
"step": 300
},
{
"epoch": 5.64,
"learning_rate": 1.2121212121212122e-06,
"loss": 0.2208,
"step": 310
},
{
"epoch": 5.82,
"learning_rate": 6.060606060606061e-07,
"loss": 0.2734,
"step": 320
},
{
"epoch": 6.0,
"learning_rate": 0.0,
"loss": 0.2764,
"step": 330
},
{
"epoch": 6.0,
"eval_accuracy": 0.9659090909090909,
"eval_loss": 0.11989254504442215,
"eval_runtime": 11.0047,
"eval_samples_per_second": 79.966,
"eval_steps_per_second": 4.998,
"step": 330
},
{
"epoch": 6.0,
"step": 330,
"total_flos": 4.860822854913491e+18,
"train_loss": 0.3027138883417303,
"train_runtime": 956.6189,
"train_samples_per_second": 22.065,
"train_steps_per_second": 0.345
}
],
"max_steps": 330,
"num_train_epochs": 6,
"total_flos": 4.860822854913491e+18,
"trial_name": null,
"trial_params": null
}