polejowska's picture
End of training
c33e3e8
raw
history blame
5.13 kB
{
"best_metric": 0.9768518518518519,
"best_model_checkpoint": "convnext-tiny-224-finetuned-eurosat/checkpoint-336",
"epoch": 1.9955555555555555,
"global_step": 336,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.06,
"learning_rate": 1.4705882352941177e-05,
"loss": 2.3032,
"step": 10
},
{
"epoch": 0.12,
"learning_rate": 2.9411764705882354e-05,
"loss": 2.2221,
"step": 20
},
{
"epoch": 0.18,
"learning_rate": 4.411764705882353e-05,
"loss": 2.0497,
"step": 30
},
{
"epoch": 0.24,
"learning_rate": 4.900662251655629e-05,
"loss": 1.7565,
"step": 40
},
{
"epoch": 0.3,
"learning_rate": 4.735099337748345e-05,
"loss": 1.4608,
"step": 50
},
{
"epoch": 0.36,
"learning_rate": 4.56953642384106e-05,
"loss": 1.1119,
"step": 60
},
{
"epoch": 0.41,
"learning_rate": 4.403973509933775e-05,
"loss": 0.8738,
"step": 70
},
{
"epoch": 0.47,
"learning_rate": 4.23841059602649e-05,
"loss": 0.686,
"step": 80
},
{
"epoch": 0.53,
"learning_rate": 4.0728476821192055e-05,
"loss": 0.5653,
"step": 90
},
{
"epoch": 0.59,
"learning_rate": 3.907284768211921e-05,
"loss": 0.4671,
"step": 100
},
{
"epoch": 0.65,
"learning_rate": 3.741721854304636e-05,
"loss": 0.3921,
"step": 110
},
{
"epoch": 0.71,
"learning_rate": 3.576158940397351e-05,
"loss": 0.3261,
"step": 120
},
{
"epoch": 0.77,
"learning_rate": 3.410596026490066e-05,
"loss": 0.2757,
"step": 130
},
{
"epoch": 0.83,
"learning_rate": 3.2450331125827816e-05,
"loss": 0.262,
"step": 140
},
{
"epoch": 0.89,
"learning_rate": 3.079470198675497e-05,
"loss": 0.2301,
"step": 150
},
{
"epoch": 0.95,
"learning_rate": 2.913907284768212e-05,
"loss": 0.206,
"step": 160
},
{
"epoch": 1.0,
"eval_accuracy": 0.9612962962962963,
"eval_loss": 0.17533423006534576,
"eval_runtime": 35.5662,
"eval_samples_per_second": 151.829,
"eval_steps_per_second": 4.752,
"step": 168
},
{
"epoch": 1.01,
"learning_rate": 2.7483443708609274e-05,
"loss": 0.1966,
"step": 170
},
{
"epoch": 1.07,
"learning_rate": 2.5827814569536424e-05,
"loss": 0.1539,
"step": 180
},
{
"epoch": 1.13,
"learning_rate": 2.4172185430463578e-05,
"loss": 0.1506,
"step": 190
},
{
"epoch": 1.19,
"learning_rate": 2.2516556291390732e-05,
"loss": 0.1292,
"step": 200
},
{
"epoch": 1.25,
"learning_rate": 2.0860927152317882e-05,
"loss": 0.1197,
"step": 210
},
{
"epoch": 1.31,
"learning_rate": 1.9205298013245036e-05,
"loss": 0.1274,
"step": 220
},
{
"epoch": 1.37,
"learning_rate": 1.7549668874172186e-05,
"loss": 0.1167,
"step": 230
},
{
"epoch": 1.43,
"learning_rate": 1.589403973509934e-05,
"loss": 0.1136,
"step": 240
},
{
"epoch": 1.49,
"learning_rate": 1.4238410596026492e-05,
"loss": 0.1105,
"step": 250
},
{
"epoch": 1.55,
"learning_rate": 1.2582781456953644e-05,
"loss": 0.1294,
"step": 260
},
{
"epoch": 1.6,
"learning_rate": 1.0927152317880796e-05,
"loss": 0.1268,
"step": 270
},
{
"epoch": 1.66,
"learning_rate": 9.271523178807948e-06,
"loss": 0.1165,
"step": 280
},
{
"epoch": 1.72,
"learning_rate": 7.6158940397350995e-06,
"loss": 0.1092,
"step": 290
},
{
"epoch": 1.78,
"learning_rate": 5.9602649006622515e-06,
"loss": 0.1002,
"step": 300
},
{
"epoch": 1.84,
"learning_rate": 4.304635761589404e-06,
"loss": 0.1134,
"step": 310
},
{
"epoch": 1.9,
"learning_rate": 2.6490066225165563e-06,
"loss": 0.1148,
"step": 320
},
{
"epoch": 1.96,
"learning_rate": 9.933774834437087e-07,
"loss": 0.0904,
"step": 330
},
{
"epoch": 2.0,
"eval_accuracy": 0.9768518518518519,
"eval_loss": 0.09591178596019745,
"eval_runtime": 34.4727,
"eval_samples_per_second": 156.646,
"eval_steps_per_second": 4.902,
"step": 336
},
{
"epoch": 2.0,
"step": 336,
"total_flos": 1.0833412255308841e+18,
"train_loss": 0.5169055745715186,
"train_runtime": 771.9486,
"train_samples_per_second": 55.962,
"train_steps_per_second": 0.435
}
],
"max_steps": 336,
"num_train_epochs": 2,
"total_flos": 1.0833412255308841e+18,
"trial_name": null,
"trial_params": null
}